diff --git a/feed_monthly.xml b/feed_monthly.xml index 59505f0..86ef88d 100644 --- a/feed_monthly.xml +++ b/feed_monthly.xml @@ -7,741 +7,741 @@ http://www.rssboard.org/rss-specification python-feedgen en - Fri, 01 Aug 2025 00:14:52 +0000 + Mon, 01 Sep 2025 00:14:08 +0000 - Radial Attention: O(nlog n) Sparse Attention with Energy Decay for Long Video Generation - https://arxiv.org/abs/2506.19852 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.19852.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xingyang Li, Muyang Li, Tianle Cai, Haocheng Xi, Shuo Yang, Yujun Lin, Lvmin Zhang, Songlin Yang, Jinbo Hu, Kelly Peng, Maneesh Agrawala, Ion Stoica, Kurt Keutzer, Song Han</p><p><b>Upvotes:</b> 40</p><p><b>Summary:</b> Recent advances in diffusion models have enabled high-quality video generation, but the additional temporal dimension significantly increases computational costs, making training and inference on long videos prohibitively expensive. In this paper, we identify a phenomenon we term Spatiotemporal Energy Decay in video diffusion models: post-softmax attention scores diminish as spatial and temporal distance between tokens increase, akin to the physical decay of signal or waves over space and time in nature. Motivated by this, we propose Radial Attention, a scalable sparse attention mechanism with O(n log n) complexity that translates energy decay into exponentially decaying compute density, which is significantly more efficient than standard O(n^2) dense attention and more expressive than linear attention. Specifically, Radial Attention employs a simple, static attention mask where each token attends to spatially nearby tokens, with the attention window size shrinking with temporal distance. Moreover, it allows pre-trained video diffusion models to extend their generation length with efficient LoRA-based fine-tuning. Extensive experiments show that Radial Attention maintains video quality across Wan2.1-14B, HunyuanVideo, and Mochi 1, achieving up to a 1.9times speedup over the original dense attention. With minimal tuning, it enables video generation up to 4times longer while reducing training costs by up to 4.4times compared to direct fine-tuning and accelerating inference by up to 3.7times compared to dense attention inference.</p> - https://arxiv.org/abs/2506.19852 - Tue, 24 Jun 2025 17:59:59 +0000 + Efficient Agents: Building Effective Agents While Reducing Cost + https://arxiv.org/abs/2508.02694 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.02694.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ningning Wang, Xavier Hu, Pai Liu, He Zhu, Yue Hou, Heyuan Huang, Shengyu Zhang, Jian Yang, Jiaheng Liu, Ge Zhang, Changwang Zhang, Jun Wang, Yuchen Eleanor Jiang, Wangchunshu Zhou</p><p><b>Upvotes:</b> 84</p><p><b>Summary:</b> The remarkable capabilities of Large Language Model (LLM)-driven agents have enabled sophisticated systems to tackle complex, multi-step tasks, but their escalating costs threaten scalability and accessibility. This work presents the first systematic study of the efficiency-effectiveness trade-off in modern agent systems, addressing the critical need for cost-effective designs without sacrificing performance. We investigate three key questions: (1) How much complexity do agentic tasks inherently require? (2) When do additional modules yield diminishing returns? (3) How much efficiency can be gained through the design of efficient agent frameworks? Through an empirical analysis on the GAIA benchmark, we evaluate the impact of LLM backbone selection, agent framework designs, and test-time scaling strategies. Using the cost-of-pass metric, we quantify the efficiency-performance trade-off across these dimensions. Our findings inform the development of Efficient Agents , a novel agent framework that has an optimal complexity to task requirements. Efficient Agents retains 96.7% of the performance of OWL, one leading open-source agent framework, while reducing operational costs from 0.398 to 0.228, resulting in a 28.4% improvement in cost-of-pass. Our work provides actionable insights for designing efficient, high-performing agent systems, advancing the accessibility and sustainability of AI-driven solutions.</p> + https://arxiv.org/abs/2508.02694 + Thu, 24 Jul 2025 17:56:51 +0000 - Ovis-U1 Technical Report - https://arxiv.org/abs/2506.23044 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.23044.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Guo-Hua Wang, Shanshan Zhao, Xinjie Zhang, Liangfu Cao, Pengxin Zhan, Lunhao Duan, Shiyin Lu, Minghao Fu, Xiaohao Chen, Jianshan Zhao, Yang Li, Qing-Guo Chen</p><p><b>Upvotes:</b> 60</p><p><b>Summary:</b> In this report, we introduce Ovis-U1, a 3-billion-parameter unified model that integrates multimodal understanding, text-to-image generation, and image editing capabilities. Building on the foundation of the Ovis series, Ovis-U1 incorporates a diffusion-based visual decoder paired with a bidirectional token refiner, enabling image generation tasks comparable to leading models like GPT-4o. Unlike some previous models that use a frozen MLLM for generation tasks, Ovis-U1 utilizes a new unified training approach starting from a language model. Compared to training solely on understanding or generation tasks, unified training yields better performance, demonstrating the enhancement achieved by integrating these two tasks. Ovis-U1 achieves a score of 69.6 on the OpenCompass Multi-modal Academic Benchmark, surpassing recent state-of-the-art models such as Ristretto-3B and SAIL-VL-1.5-2B. In text-to-image generation, it excels with scores of 83.72 and 0.89 on the DPG-Bench and GenEval benchmarks, respectively. For image editing, it achieves 4.00 and 6.42 on the ImgEdit-Bench and GEdit-Bench-EN, respectively. As the initial version of the Ovis unified model series, Ovis-U1 pushes the boundaries of multimodal understanding, generation, and editing.</p> - https://arxiv.org/abs/2506.23044 - Sun, 29 Jun 2025 00:40:17 +0000 + RecGPT Technical Report + https://arxiv.org/abs/2507.22879 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.22879.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chao Yi, Dian Chen, Gaoyang Guo, Jiakai Tang, Jian Wu, Jing Yu, Sunhao Dai, Wen Chen, Wenjun Yang, Yuning Jiang, Zhujin Gao, Bo Zheng, Chi Li, Dimin Wang, Dixuan Wang, Fan Li, Fan Zhang, Haibin Chen, Haozhuang Liu, Jialin Zhu, Jiamang Wang, Jiawei Wu, Jin Cui, Ju Huang, Kai Zhang, Kan Liu, Lang Tian, Liang Rao, Longbin Li, Lulu Zhao, Mao Zhang, Na He, Peiyang Wang, Qiqi Huang, Tao Luo, Wenbo Su, Xiaoxiao He, Xin Tong, Xu Chen, Xunke Xi, Yang Li, Yaxuan Wu, Yeqiu Yang, Yi Hu, Yinnan Song, Yuchen Li, Yujie Luo, Yujin Yuan, Yuliang Yan, Zhengyang Wang, Zhibo Xiao, Zhixin Ma, Zile Zhou</p><p><b>Upvotes:</b> 37</p><p><b>Summary:</b> Recommender systems are among the most impactful applications of artificial intelligence, serving as critical infrastructure connecting users, merchants, and platforms. However, most current industrial systems remain heavily reliant on historical co-occurrence patterns and log-fitting objectives, i.e., optimizing for past user interactions without explicitly modeling user intent. This log-fitting approach often leads to overfitting to narrow historical preferences, failing to capture users' evolving and latent interests. As a result, it reinforces filter bubbles and long-tail phenomena, ultimately harming user experience and threatening the sustainability of the whole recommendation ecosystem. To address these challenges, we rethink the overall design paradigm of recommender systems and propose RecGPT, a next-generation framework that places user intent at the center of the recommendation pipeline. By integrating large language models (LLMs) into key stages of user interest mining, item retrieval, and explanation generation, RecGPT transforms log-fitting recommendation into an intent-centric process. To effectively align general-purpose LLMs to the above domain-specific recommendation tasks at scale, RecGPT incorporates a multi-stage training paradigm, which integrates reasoning-enhanced pre-alignment and self-training evolution, guided by a Human-LLM cooperative judge system. Currently, RecGPT has been fully deployed on the Taobao App. Online experiments demonstrate that RecGPT achieves consistent performance gains across stakeholders: users benefit from increased content diversity and satisfaction, merchants and the platform gain greater exposure and conversions. These comprehensive improvement results across all stakeholders validates that LLM-driven, intent-centric design can foster a more sustainable and mutually beneficial recommendation ecosystem.</p> + https://arxiv.org/abs/2507.22879 + Wed, 30 Jul 2025 17:55:06 +0000 - MoCa: Modality-aware Continual Pre-training Makes Better Bidirectional Multimodal Embeddings - https://arxiv.org/abs/2506.23115 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.23115.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haonan Chen, Hong Liu, Yuping Luo, Liang Wang, Nan Yang, Furu Wei, Zhicheng Dou</p><p><b>Upvotes:</b> 36</p><p><b>Summary:</b> Multimodal embedding models, built upon causal Vision Language Models (VLMs), have shown promise in various tasks. However, current approaches face three key limitations: the use of causal attention in VLM backbones is suboptimal for embedding tasks; scalability issues due to reliance on high-quality labeled paired data for contrastive learning; and limited diversity in training objectives and data. To address these issues, we propose MoCa, a two-stage framework for transforming pre-trained VLMs into effective bidirectional multimodal embedding models. The first stage, Modality-aware Continual Pre-training, introduces a joint reconstruction objective that simultaneously denoises interleaved text and image inputs, enhancing bidirectional context-aware reasoning. The second stage, Heterogeneous Contrastive Fine-tuning, leverages diverse, semantically rich multimodal data beyond simple image-caption pairs to enhance generalization and alignment. Our method addresses the stated limitations by introducing bidirectional attention through continual pre-training, scaling effectively with massive unlabeled datasets via joint reconstruction objectives, and utilizing diverse multimodal data for enhanced representation robustness. Experiments demonstrate that MoCa consistently improves performance across MMEB and ViDoRe-v2 benchmarks, achieving new state-of-the-art results, and exhibits strong scalability with both model size and training data on MMEB.</p> - https://arxiv.org/abs/2506.23115 - Sun, 29 Jun 2025 06:41:00 +0000 + PixNerd: Pixel Neural Field Diffusion + https://arxiv.org/abs/2507.23268 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.23268.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shuai Wang, Ziteng Gao, Chenhui Zhu, Weilin Huang, Limin Wang</p><p><b>Upvotes:</b> 51</p><p><b>Summary:</b> The current success of diffusion transformers heavily depends on the compressed latent space shaped by the pre-trained variational autoencoder(VAE). However, this two-stage training paradigm inevitably introduces accumulated errors and decoding artifacts. To address the aforementioned problems, researchers return to pixel space at the cost of complicated cascade pipelines and increased token complexity. In contrast to their efforts, we propose to model the patch-wise decoding with neural field and present a single-scale, single-stage, efficient, end-to-end solution, coined as pixel neural field diffusion~(PixelNerd). Thanks to the efficient neural field representation in PixNerd, we directly achieved 2.15 FID on ImageNet 256times256 and 2.84 FID on ImageNet 512times512 without any complex cascade pipeline or VAE. We also extend our PixNerd framework to text-to-image applications. Our PixNerd-XXL/16 achieved a competitive 0.73 overall score on the GenEval benchmark and 80.9 overall score on the DPG benchmark.</p> + https://arxiv.org/abs/2507.23268 + Thu, 31 Jul 2025 06:07:20 +0000 - Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers - https://arxiv.org/abs/2506.23918 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.23918.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhaochen Su, Peng Xia, Hangyu Guo, Zhenhua Liu, Yan Ma, Xiaoye Qu, Jiaqi Liu, Yanshu Li, Kaide Zeng, Zhengyuan Yang, Linjie Li, Yu Cheng, Heng Ji, Junxian He, Yi R. Fung</p><p><b>Upvotes:</b> 84</p><p><b>Summary:</b> Recent progress in multimodal reasoning has been significantly advanced by textual Chain-of-Thought (CoT), a paradigm where models conduct reasoning within language. This text-centric approach, however, treats vision as a static, initial context, creating a fundamental "semantic gap" between rich perceptual data and discrete symbolic thought. Human cognition often transcends language, utilizing vision as a dynamic mental sketchpad. A similar evolution is now unfolding in AI, marking a fundamental paradigm shift from models that merely think about images to those that can truly think with images. This emerging paradigm is characterized by models leveraging visual information as intermediate steps in their thought process, transforming vision from a passive input into a dynamic, manipulable cognitive workspace. In this survey, we chart this evolution of intelligence along a trajectory of increasing cognitive autonomy, which unfolds across three key stages: from external tool exploration, through programmatic manipulation, to intrinsic imagination. To structure this rapidly evolving field, our survey makes four key contributions. (1) We establish the foundational principles of the think with image paradigm and its three-stage framework. (2) We provide a comprehensive review of the core methods that characterize each stage of this roadmap. (3) We analyze the critical landscape of evaluation benchmarks and transformative applications. (4) We identify significant challenges and outline promising future directions. By providing this structured overview, we aim to offer a clear roadmap for future research towards more powerful and human-aligned multimodal AI.</p> - https://arxiv.org/abs/2506.23918 - Mon, 30 Jun 2025 14:48:35 +0000 + iLRM: An Iterative Large 3D Reconstruction Model + https://arxiv.org/abs/2507.23277 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.23277.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Gyeongjin Kang, Seungtae Nam, Xiangyu Sun, Sameh Khamis, Abdelrahman Mohamed, Eunbyung Park</p><p><b>Upvotes:</b> 31</p><p><b>Summary:</b> Feed-forward 3D modeling has emerged as a promising approach for rapid and high-quality 3D reconstruction. In particular, directly generating explicit 3D representations, such as 3D Gaussian splatting, has attracted significant attention due to its fast and high-quality rendering, as well as numerous applications. However, many state-of-the-art methods, primarily based on transformer architectures, suffer from severe scalability issues because they rely on full attention across image tokens from multiple input views, resulting in prohibitive computational costs as the number of views or image resolution increases. Toward a scalable and efficient feed-forward 3D reconstruction, we introduce an iterative Large 3D Reconstruction Model (iLRM) that generates 3D Gaussian representations through an iterative refinement mechanism, guided by three core principles: (1) decoupling the scene representation from input-view images to enable compact 3D representations; (2) decomposing fully-attentional multi-view interactions into a two-stage attention scheme to reduce computational costs; and (3) injecting high-resolution information at every layer to achieve high-fidelity reconstruction. Experimental results on widely used datasets, such as RE10K and DL3DV, demonstrate that iLRM outperforms existing methods in both reconstruction quality and speed. Notably, iLRM exhibits superior scalability, delivering significantly higher reconstruction quality under comparable computational cost by efficiently leveraging a larger number of input views.</p> + https://arxiv.org/abs/2507.23277 + Thu, 31 Jul 2025 06:33:07 +0000 - SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning - https://arxiv.org/abs/2506.24119 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.24119.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bo Liu, Leon Guertler, Simon Yu, Zichen Liu, Penghui Qi, Daniel Balcells, Mickel Liu, Cheston Tan, Weiyan Shi, Min Lin, Wee Sun Lee, Natasha Jaques</p><p><b>Upvotes:</b> 46</p><p><b>Summary:</b> Recent advances in reinforcement learning have shown that language models can develop sophisticated reasoning through training on tasks with verifiable rewards, but these approaches depend on human-curated problem-answer pairs and domain-specific reward engineering. We introduce SPIRAL, a self-play framework where models learn by playing multi-turn, zero-sum games against continuously improving versions of themselves, eliminating the need for human supervision. Through self-play, SPIRAL generates an infinite curriculum of progressively challenging problems as models must constantly adapt to stronger opponents. To enable this self-play training at scale, We implement a fully online, multi-turn, multi-agent reinforcement learning system for LLMs and propose role-conditioned advantage estimation (RAE) to stabilize multi-agent training. Using SPIRAL, self-play on zero-sum games produces reasoning capabilities that transfer broadly. Training Qwen3-4B-Base on Kuhn Poker alone achieves 8.6% improvement on math and 8.4% on general reasoning, outperforming SFT on 25,000 expert game trajectories. Analysis reveals that this transfer occurs through three cognitive patterns: systematic decomposition, expected value calculation, and case-by-case analysis. Multi-game training (TicTacToe, Kuhn Poker, Simple Negotiation) further enhances performance as each game develops distinct reasoning strengths. Applying SPIRAL to a strong reasoning model (DeepSeek-R1-Distill-Qwen-7B) can still lead to 2.0% average improvement. These results demonstrate that zero-sum games naturally develop transferable reasoning capabilities, highlighting a promising direction for autonomous reasoning development.</p> - https://arxiv.org/abs/2506.24119 - Mon, 30 Jun 2025 17:58:13 +0000 + Seed-Prover: Deep and Broad Reasoning for Automated Theorem Proving + https://arxiv.org/abs/2507.23726 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.23726.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Luoxin Chen, Jinming Gu, Liankai Huang, Wenhao Huang, Zhicheng Jiang, Allan Jie, Xiaoran Jin, Xing Jin, Chenggang Li, Kaijing Ma, Cheng Ren, Jiawei Shen, Wenlei Shi, Tong Sun, He Sun, Jiahui Wang, Siran Wang, Zhihong Wang, Chenrui Wei, Shufa Wei, Yonghui Wu, Yuchen Wu, Yihang Xia, Huajian Xin, Fan Yang, Huaiyuan Ying, Hongyi Yuan, Zheng Yuan, Tianyang Zhan, Chi Zhang, Yue Zhang, Ge Zhang, Tianyun Zhao, Jianqiu Zhao, Yichi Zhou, Thomas Hanwen Zhu</p><p><b>Upvotes:</b> 112</p><p><b>Summary:</b> LLMs have demonstrated strong mathematical reasoning abilities by leveraging reinforcement learning with long chain-of-thought, yet they continue to struggle with theorem proving due to the lack of clear supervision signals when solely using natural language. Dedicated domain-specific languages like Lean provide clear supervision via formal verification of proofs, enabling effective training through reinforcement learning. In this work, we propose Seed-Prover, a lemma-style whole-proof reasoning model. Seed-Prover can iteratively refine its proof based on Lean feedback, proved lemmas, and self-summarization. To solve IMO-level contest problems, we design three test-time inference strategies that enable both deep and broad reasoning. Seed-Prover proves 78.1% of formalized past IMO problems, saturates MiniF2F, and achieves over 50\% on PutnamBench, outperforming the previous state-of-the-art by a large margin. To address the lack of geometry support in Lean, we introduce a geometry reasoning engine Seed-Geometry, which outperforms previous formal geometry engines. We use these two systems to participate in IMO 2025 and fully prove 5 out of 6 problems. This work represents a significant advancement in automated mathematical reasoning, demonstrating the effectiveness of formal verification with long chain-of-thought reasoning.</p> + https://arxiv.org/abs/2507.23726 + Thu, 31 Jul 2025 17:00:30 +0000 - Calligrapher: Freestyle Text Image Customization - https://arxiv.org/abs/2506.24123 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.24123.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yue Ma, Qingyan Bai, Hao Ouyang, Ka Leong Cheng, Qiuyu Wang, Hongyu Liu, Zichen Liu, Haofan Wang, Jingye Chen, Yujun Shen, Qifeng Chen</p><p><b>Upvotes:</b> 35</p><p><b>Summary:</b> We introduce Calligrapher, a novel diffusion-based framework that innovatively integrates advanced text customization with artistic typography for digital calligraphy and design applications. Addressing the challenges of precise style control and data dependency in typographic customization, our framework incorporates three key technical contributions. First, we develop a self-distillation mechanism that leverages the pre-trained text-to-image generative model itself alongside the large language model to automatically construct a style-centric typography benchmark. Second, we introduce a localized style injection framework via a trainable style encoder, which comprises both Qformer and linear layers, to extract robust style features from reference images. An in-context generation mechanism is also employed to directly embed reference images into the denoising process, further enhancing the refined alignment of target styles. Extensive quantitative and qualitative evaluations across diverse fonts and design contexts confirm Calligrapher's accurate reproduction of intricate stylistic details and precise glyph positioning. By automating high-quality, visually consistent typography, Calligrapher surpasses traditional models, empowering creative practitioners in digital art, branding, and contextual typographic design.</p> - https://arxiv.org/abs/2506.24123 - Mon, 30 Jun 2025 17:59:06 +0000 + Phi-Ground Tech Report: Advancing Perception in GUI Grounding + https://arxiv.org/abs/2507.23779 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.23779.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Miaosen Zhang, Ziqiang Xu, Jialiang Zhu, Qi Dai, Kai Qiu, Yifan Yang, Chong Luo, Tianyi Chen, Justin Wagle, Tim Franklin, Baining Guo</p><p><b>Upvotes:</b> 44</p><p><b>Summary:</b> With the development of multimodal reasoning models, Computer Use Agents (CUAs), akin to Jarvis from "Iron Man", are becoming a reality. GUI grounding is a core component for CUAs to execute actual actions, similar to mechanical control in robotics, and it directly leads to the success or failure of the system. It determines actions such as clicking and typing, as well as related parameters like the coordinates for clicks. Current end-to-end grounding models still achieve less than 65\% accuracy on challenging benchmarks like ScreenSpot-pro and UI-Vision, indicating they are far from being ready for deployment. % , as a single misclick can result in unacceptable consequences. In this work, we conduct an empirical study on the training of grounding models, examining details from data collection to model training. Ultimately, we developed the Phi-Ground model family, which achieves state-of-the-art performance across all five grounding benchmarks for models under 10B parameters in agent settings. In the end-to-end model setting, our model still achieves SOTA results with scores of \textbf{43.2} on ScreenSpot-pro and \textbf{27.2} on UI-Vision. We believe that the various details discussed in this paper, along with our successes and failures, not only clarify the construction of grounding models but also benefit other perception tasks. Project homepage: https://zhangmiaosen2000.github.io/Phi-Ground/{https://zhangmiaosen2000.github.io/Phi-Ground/}</p> + https://arxiv.org/abs/2507.23779 + Thu, 31 Jul 2025 17:59:09 +0000 - Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning - https://arxiv.org/abs/2507.00432 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.00432.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Maggie Huan, Yuetai Li, Tuney Zheng, Xiaoyu Xu, Seungone Kim, Minxin Du, Radha Poovendran, Graham Neubig, Xiang Yue</p><p><b>Upvotes:</b> 72</p><p><b>Summary:</b> Math reasoning has become the poster child of progress in large language models (LLMs), with new models rapidly surpassing human-level performance on benchmarks like MATH and AIME. But as math leaderboards improve week by week, it is worth asking: do these gains reflect broader problem-solving ability or just narrow overfitting? To answer this question, we evaluate over 20 open-weight reasoning-tuned models across a broad suite of tasks, including math, scientific QA, agent planning, coding, and standard instruction-following. We surprisingly find that most models that succeed in math fail to transfer their gains to other domains. To rigorously study this phenomenon, we conduct controlled experiments on Qwen3-14B models using math-only data but different tuning methods. We find that reinforcement learning (RL)-tuned models generalize well across domains, while supervised fine-tuning (SFT)-tuned models often forget general capabilities. Latent-space representation and token-space distribution shift analyses reveal that SFT induces substantial representation and output drift, while RL preserves general-domain structure. Our results suggest a need to rethink standard post-training recipes, particularly the reliance on SFT-distilled data for advancing reasoning models.</p> - https://arxiv.org/abs/2507.00432 - Tue, 01 Jul 2025 05:23:05 +0000 + Cognitive Kernel-Pro: A Framework for Deep Research Agents and Agent Foundation Models Training + https://arxiv.org/abs/2508.00414 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.00414.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tianqing Fang, Zhisong Zhang, Xiaoyang Wang, Rui Wang, Can Qin, Yuxuan Wan, Jun-Yu Ma, Ce Zhang, Jiaqi Chen, Xiyun Li, Hongming Zhang, Haitao Mi, Dong Yu</p><p><b>Upvotes:</b> 89</p><p><b>Summary:</b> General AI Agents are increasingly recognized as foundational frameworks for the next generation of artificial intelligence, enabling complex reasoning, web interaction, coding, and autonomous research capabilities. However, current agent systems are either closed-source or heavily reliant on a variety of paid APIs and proprietary tools, limiting accessibility and reproducibility for the research community. In this work, we present Cognitive Kernel-Pro, a fully open-source and (to the maximum extent) free multi-module agent framework designed to democratize the development and evaluation of advanced AI agents. Within Cognitive Kernel-Pro, we systematically investigate the curation of high-quality training data for Agent Foundation Models, focusing on the construction of queries, trajectories, and verifiable answers across four key domains: web, file, code, and general reasoning. Furthermore, we explore novel strategies for agent test-time reflection and voting to enhance agent robustness and performance. We evaluate Cognitive Kernel-Pro on GAIA, achieving state-of-the-art results among open-source and free agents. Notably, our 8B-parameter open-source model surpasses previous leading systems such as WebDancer and WebSailor, establishing a new performance standard for accessible, high-capability AI agents. Code is available at https://github.com/Tencent/CognitiveKernel-Pro</p> + https://arxiv.org/abs/2508.00414 + Fri, 01 Aug 2025 08:11:31 +0000 - Should We Still Pretrain Encoders with Masked Language Modeling? - https://arxiv.org/abs/2507.00994 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.00994.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hippolyte Gisserot-Boukhlef, Nicolas Boizard, Manuel Faysse, Duarte M. Alves, Emmanuel Malherbe, André F. T. Martins, Céline Hudelot, Pierre Colombo</p><p><b>Upvotes:</b> 74</p><p><b>Summary:</b> Learning high-quality text representations is fundamental to a wide range of NLP tasks. While encoder pretraining has traditionally relied on Masked Language Modeling (MLM), recent evidence suggests that decoder models pretrained with Causal Language Modeling (CLM) can be effectively repurposed as encoders, often surpassing traditional encoders on text representation benchmarks. However, it remains unclear whether these gains reflect an inherent advantage of the CLM objective or arise from confounding factors such as model and data scale. In this paper, we address this question through a series of large-scale, carefully controlled pretraining ablations, training a total of 30 models ranging from 210 million to 1 billion parameters, and conducting over 15,000 fine-tuning and evaluation runs. We find that while training with MLM generally yields better performance across text representation tasks, CLM-trained models are more data-efficient and demonstrate improved fine-tuning stability. Building on these findings, we experimentally show that a biphasic training strategy that sequentially applies CLM and then MLM, achieves optimal performance under a fixed computational training budget. Moreover, we demonstrate that this strategy becomes more appealing when initializing from readily available pretrained CLM models (from the existing LLM ecosystem), reducing the computational burden needed to train best-in-class encoder models. We release all project artifacts at https://hf.co/MLMvsCLM to foster further research.</p> - https://arxiv.org/abs/2507.00994 - Tue, 01 Jul 2025 17:45:48 +0000 + Beyond Fixed: Variable-Length Denoising for Diffusion Large Language Models + https://arxiv.org/abs/2508.00819 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.00819.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jinsong Li, Xiaoyi Dong, Yuhang Zang, Yuhang Cao, Jiaqi Wang, Dahua Lin</p><p><b>Upvotes:</b> 62</p><p><b>Summary:</b> Diffusion Large Language Models (DLLMs) are emerging as a powerful alternative to the dominant Autoregressive Large Language Models, offering efficient parallel generation and capable global context modeling. However, the practical application of DLLMs is hindered by a critical architectural constraint: the need for a statically predefined generation length. This static length allocation leads to a problematic trade-off: insufficient lengths cripple performance on complex tasks, while excessive lengths incur significant computational overhead and sometimes result in performance degradation. While the inference framework is rigid, we observe that the model itself possesses internal signals that correlate with the optimal response length for a given task. To bridge this gap, we leverage these latent signals and introduce DAEDAL, a novel training-free denoising strategy that enables Dynamic Adaptive Length Expansion for Diffusion Large Language Models. DAEDAL operates in two phases: 1) Before the denoising process, DAEDAL starts from a short initial length and iteratively expands it to a coarse task-appropriate length, guided by a sequence completion metric. 2) During the denoising process, DAEDAL dynamically intervenes by pinpointing and expanding insufficient generation regions through mask token insertion, ensuring the final output is fully developed. Extensive experiments on DLLMs demonstrate that DAEDAL achieves performance comparable, and in some cases superior, to meticulously tuned fixed-length baselines, while simultaneously enhancing computational efficiency by achieving a higher effective token ratio. By resolving the static length constraint, DAEDAL unlocks new potential for DLLMs, bridging a critical gap with their Autoregressive counterparts and paving the way for more efficient and capable generation.</p> + https://arxiv.org/abs/2508.00819 + Fri, 01 Aug 2025 17:56:07 +0000 - SciArena: An Open Evaluation Platform for Foundation Models in Scientific Literature Tasks - https://arxiv.org/abs/2507.01001 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.01001.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yilun Zhao, Kaiyan Zhang, Tiansheng Hu, Sihong Wu, Ronan Le Bras, Taira Anderson, Jonathan Bragg, Joseph Chee Chang, Jesse Dodge, Matt Latzke, Yixin Liu, Charles McGrady, Xiangru Tang, Zihang Wang, Chen Zhao, Hannaneh Hajishirzi, Doug Downey, Arman Cohan</p><p><b>Upvotes:</b> 43</p><p><b>Summary:</b> We present SciArena, an open and collaborative platform for evaluating foundation models on scientific literature tasks. Unlike traditional benchmarks for scientific literature understanding and synthesis, SciArena engages the research community directly, following the Chatbot Arena evaluation approach of community voting on model comparisons. By leveraging collective intelligence, SciArena offers a community-driven evaluation of model performance on open-ended scientific tasks that demand literature-grounded, long-form responses. The platform currently supports 23 open-source and proprietary foundation models and has collected over 13,000 votes from trusted researchers across diverse scientific domains. We analyze the data collected so far and confirm that the submitted questions are diverse, aligned with real-world literature needs, and that participating researchers demonstrate strong self-consistency and inter-annotator agreement in their evaluations. We discuss the results and insights based on the model ranking leaderboard. To further promote research in building model-based automated evaluation systems for literature tasks, we release SciArena-Eval, a meta-evaluation benchmark based on our collected preference data. The benchmark measures the accuracy of models in judging answer quality by comparing their pairwise assessments with human votes. Our experiments highlight the benchmark's challenges and emphasize the need for more reliable automated evaluation methods.</p> - https://arxiv.org/abs/2507.01001 - Tue, 01 Jul 2025 17:51:59 +0000 + Llama-3.1-FoundationAI-SecurityLLM-8B-Instruct Technical Report + https://arxiv.org/abs/2508.01059 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.01059.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sajana Weerawardhena, Paul Kassianik, Blaine Nelson, Baturay Saglam, Anu Vellore, Aman Priyanshu, Supriti Vijay, Massimo Aufiero, Arthur Goldblatt, Fraser Burch, Ed Li, Jianliang He, Dhruv Kedia, Kojin Oshiba, Zhouran Yang, Yaron Singer, Amin Karbasi</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> Large language models (LLMs) have shown remarkable success across many domains, yet their integration into cybersecurity applications remains limited due to a lack of general-purpose cybersecurity data, representational complexity, and safety and regulatory concerns. To address this gap, we previously introduced Foundation-Sec-8B, a cybersecurity-focused LLM suitable for fine-tuning on downstream tasks. That model, however, was not designed for chat-style interactions or instruction-following. In this report, we release Foundation-Sec-8B-Instruct: a model specifically trained for general-purpose cybersecurity dialogue. Built on Foundation-Sec-8B, it combines domain-specific knowledge with instruction-following, conversational capabilities, and alignment with human preferences to produce high-quality, relevant responses. Comprehensive evaluations show that Foundation-Sec-8B-Instruct outperforms Llama 3.1-8B-Instruct on a range of cybersecurity tasks while matching its instruction-following performance. It is also competitive with GPT-4o-mini on cyber threat intelligence and instruction-following tasks. We envision Foundation-Sec-8B-Instruct becoming an indispensable assistant in the daily workflows of cybersecurity professionals. We release the model publicly at https://huggingface.co/fdtn-ai/Foundation-Sec-8B-Instruct.</p> + https://arxiv.org/abs/2508.01059 + Fri, 01 Aug 2025 20:25:57 +0000 - GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning - https://arxiv.org/abs/2507.01006 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.01006.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wenyi Hong, Wenmeng Yu, Xiaotao Gu, Guo Wang, Guobing Gan, Haomiao Tang, Jiale Cheng, Ji Qi, Junhui Ji, Lihang Pan, Shuaiqi Duan, Weihan Wang, Yan Wang, Yean Cheng, Zehai He, Zhe Su, Zhen Yang, Ziyang Pan, Aohan Zeng, Baoxu Wang, Boyan Shi, Changyu Pang, Chenhui Zhang, Da Yin, Fan Yang, Guoqing Chen, Jiazheng Xu, Jiali Chen, Jing Chen, Jinhao Chen, Jinghao Lin, Jinjiang Wang, Junjie Chen, Leqi Lei, Leyi Pan, Mingzhi Zhang, Qinkai Zheng, Sheng Yang, Shi Zhong, Shiyu Huang, Shuyuan Zhao, Siyan Xue, Shangqin Tu, Shengbiao Meng, Tianshu Zhang, Tianwei Luo, Tianxiang Hao, Tianle Gong, Wenkai Li, Wei Jia, Xin Lyu, Xuancheng Huang, Yanling Wang, Yadong Xue, Yanfeng Wang, Yifan An, Yifan Du, Yiming Shi, Yiheng Huang, Yilin Niu, Yuan Wang, Yuanchang Yue, Yuchen Li, Yutao Zhang, Yuxuan Zhang, Zhanxiao Du, Zhenyu Hou, Zhao Xue, Zhengxiao Du, Zihan Wang, Peng Zhang, Debing Liu, Bin Xu, Juanzi Li, Minlie Huang, Yuxiao Dong, Jie Tang</p><p><b>Upvotes:</b> 205</p><p><b>Summary:</b> We present GLM-4.1V-Thinking, a vision-language model (VLM) designed to advance general-purpose multimodal reasoning. In this report, we share our key findings in the development of the reasoning-centric training framework. We first develop a capable vision foundation model with significant potential through large-scale pre-training, which arguably sets the upper bound for the final performance. Reinforcement Learning with Curriculum Sampling (RLCS) then unlocks the full potential of the model, leading to comprehensive capability enhancement across a diverse range of tasks, including STEM problem solving, video understanding, content recognition, coding, grounding, GUI-based agents, and long document understanding, among others. To facilitate research in this field, we open-source GLM-4.1V-9B-Thinking, which achieves state-of-the-art performance among models of comparable size. In a comprehensive evaluation across 28 public benchmarks, our model outperforms Qwen2.5-VL-7B on nearly all tasks and achieves comparable or even superior performance on 18 benchmarks relative to the significantly larger Qwen2.5-VL-72B. Notably, GLM-4.1V-9B-Thinking also demonstrates competitive or superior performance compared to closed-source models such as GPT-4o on challenging tasks including long document understanding and STEM reasoning, further underscoring its strong capabilities. Code, models and more information are released at https://github.com/THUDM/GLM-4.1V-Thinking.</p> - https://arxiv.org/abs/2507.01006 - Tue, 01 Jul 2025 17:55:04 +0000 + Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens + https://arxiv.org/abs/2508.01191 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.01191.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chengshuai Zhao, Zhen Tan, Pingchuan Ma, Dawei Li, Bohan Jiang, Yancheng Wang, Yingzhen Yang, Huan Liu</p><p><b>Upvotes:</b> 228</p><p><b>Summary:</b> Chain-of-Thought (CoT) prompting has been shown to improve Large Language Model (LLM) performance on various tasks. With this approach, LLMs appear to produce human-like reasoning steps before providing answers (a.k.a., CoT reasoning), which often leads to the perception that they engage in deliberate inferential processes. However, some initial findings suggest that CoT reasoning may be more superficial than it appears, motivating us to explore further. In this paper, we study CoT reasoning via a data distribution lens and investigate if CoT reasoning reflects a structured inductive bias learned from in-distribution data, allowing the model to conditionally generate reasoning paths that approximate those seen during training. Thus, its effectiveness is fundamentally bounded by the degree of distribution discrepancy between the training data and the test queries. With this lens, we dissect CoT reasoning via three dimensions: task, length, and format. To investigate each dimension, we design DataAlchemy, an isolated and controlled environment to train LLMs from scratch and systematically probe them under various distribution conditions. Our results reveal that CoT reasoning is a brittle mirage that vanishes when it is pushed beyond training distributions. This work offers a deeper understanding of why and when CoT reasoning fails, emphasizing the ongoing challenge of achieving genuine and generalizable reasoning.</p> + https://arxiv.org/abs/2508.01191 + Sat, 02 Aug 2025 04:37:28 +0000 - Skywork-Reward-V2: Scaling Preference Data Curation via Human-AI Synergy - https://arxiv.org/abs/2507.01352 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.01352.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chris Yuhao Liu, Liang Zeng, Yuzhen Xiao, Jujie He, Jiacai Liu, Chaojie Wang, Rui Yan, Wei Shen, Fuxiang Zhang, Jiacheng Xu, Yang Liu, Yahui Zhou</p><p><b>Upvotes:</b> 51</p><p><b>Summary:</b> Despite the critical role of reward models (RMs) in reinforcement learning from human feedback (RLHF), current state-of-the-art open RMs perform poorly on most existing evaluation benchmarks, failing to capture the spectrum of nuanced and sophisticated human preferences. Even approaches that incorporate advanced training techniques have not yielded meaningful performance improvements. We hypothesize that this brittleness stems primarily from limitations in preference datasets, which are often narrowly scoped, synthetically labeled, or lack rigorous quality control. To address these challenges, we present a large-scale preference dataset comprising 40 million preference pairs, named SynPref-40M. To enable data curation at scale, we design a human-AI synergistic two-stage pipeline that leverages the complementary strengths of human annotation quality and AI scalability. In this pipeline, humans provide verified annotations, while large language models perform automatic curation based on human guidance. Training on this preference mixture, we introduce Skywork-Reward-V2, a suite of eight reward models ranging from 0.6B to 8B parameters, trained on a carefully curated subset of 26 million preference pairs from SynPref-40M. We demonstrate that Skywork-Reward-V2 is versatile across a wide range of capabilities, including alignment with human preferences, objective correctness, safety, resistance to stylistic biases, and best-of-N scaling, achieving state-of-the-art performance across seven major reward model benchmarks. Ablation studies confirm that the effectiveness of our approach stems not only from data scale but also from high-quality curation. The Skywork-Reward-V2 series represents substantial progress in open reward models, highlighting the untapped potential of existing preference datasets and demonstrating how human-AI curation synergy can unlock significantly higher data quality.</p> - https://arxiv.org/abs/2507.01352 - Wed, 02 Jul 2025 04:40:29 +0000 + SitEmb-v1.5: Improved Context-Aware Dense Retrieval for Semantic Association and Long Story Comprehension + https://arxiv.org/abs/2508.01959 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.01959.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junjie Wu, Jiangnan Li, Yuqing Li, Lemao Liu, Liyan Xu, Jiwei Li, Dit-Yan Yeung, Jie Zhou, Mo Yu</p><p><b>Upvotes:</b> 56</p><p><b>Summary:</b> Retrieval-augmented generation (RAG) over long documents typically involves splitting the text into smaller chunks, which serve as the basic units for retrieval. However, due to dependencies across the original document, contextual information is often essential for accurately interpreting each chunk. To address this, prior work has explored encoding longer context windows to produce embeddings for longer chunks. Despite these efforts, gains in retrieval and downstream tasks remain limited. This is because (1) longer chunks strain the capacity of embedding models due to the increased amount of information they must encode, and (2) many real-world applications still require returning localized evidence due to constraints on model or human bandwidth. We propose an alternative approach to this challenge by representing short chunks in a way that is conditioned on a broader context window to enhance retrieval performance -- i.e., situating a chunk's meaning within its context. We further show that existing embedding models are not well-equipped to encode such situated context effectively, and thus introduce a new training paradigm and develop the situated embedding models (SitEmb). To evaluate our method, we curate a book-plot retrieval dataset specifically designed to assess situated retrieval capabilities. On this benchmark, our SitEmb-v1 model based on BGE-M3 substantially outperforms state-of-the-art embedding models, including several with up to 7-8B parameters, with only 1B parameters. Our 8B SitEmb-v1.5 model further improves performance by over 10% and shows strong results across different languages and several downstream applications.</p> + https://arxiv.org/abs/2508.01959 + Sun, 03 Aug 2025 23:59:31 +0000 - Depth Anything at Any Condition - https://arxiv.org/abs/2507.01634 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.01634.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Boyuan Sun, Modi Jin, Bowen Yin, Qibin Hou</p><p><b>Upvotes:</b> 48</p><p><b>Summary:</b> We present Depth Anything at Any Condition (DepthAnything-AC), a foundation monocular depth estimation (MDE) model capable of handling diverse environmental conditions. Previous foundation MDE models achieve impressive performance across general scenes but not perform well in complex open-world environments that involve challenging conditions, such as illumination variations, adverse weather, and sensor-induced distortions. To overcome the challenges of data scarcity and the inability of generating high-quality pseudo-labels from corrupted images, we propose an unsupervised consistency regularization finetuning paradigm that requires only a relatively small amount of unlabeled data. Furthermore, we propose the Spatial Distance Constraint to explicitly enforce the model to learn patch-level relative relationships, resulting in clearer semantic boundaries and more accurate details. Experimental results demonstrate the zero-shot capabilities of DepthAnything-AC across diverse benchmarks, including real-world adverse weather benchmarks, synthetic corruption benchmarks, and general benchmarks. Project Page: https://ghost233lism.github.io/depthanything-AC-page Code: https://github.com/HVision-NKU/DepthAnythingAC</p> - https://arxiv.org/abs/2507.01634 - Wed, 02 Jul 2025 12:05:57 +0000 + Beyond the Trade-off: Self-Supervised Reinforcement Learning for Reasoning Models' Instruction Following + https://arxiv.org/abs/2508.02150 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.02150.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qingyu Ren, Qianyu He, Bowei Zhang, Jie Zeng, Jiaqing Liang, Yanghua Xiao, Weikang Zhou, Zeye Sun, Fei Yu</p><p><b>Upvotes:</b> 35</p><p><b>Summary:</b> Reasoning models excel in complex problem solving but exhibit a concerning trade off between reasoning capabilities and instruction following abilities. Existing approaches for improving instruction following rely on stronger external models, creating methodological bottlenecks and practical limitations including increased costs and accessibility constraints. We propose a self-supervised RL framework that leverages reasoning models' own internal signals to improve instruction following capabilities without external supervision. Extensive experiments demonstrate that our framework significantly improves instruction following capabilities while maintaining reasoning performance, offering a scalable and cost-effective approach to enhance instruction following in reasoning models. The data and code are publicly available at https://github.com/Rainier-rq/verl-if.</p> + https://arxiv.org/abs/2508.02150 + Mon, 04 Aug 2025 07:48:59 +0000 - A Survey on Vision-Language-Action Models: An Action Tokenization Perspective - https://arxiv.org/abs/2507.01925 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.01925.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yifan Zhong, Fengshuo Bai, Shaofei Cai, Xuchuan Huang, Zhang Chen, Xiaowei Zhang, Yuanfei Wang, Shaoyang Guo, Tianrui Guan, Ka Nam Lui, Zhiquan Qi, Yitao Liang, Yuanpei Chen, Yaodong Yang</p><p><b>Upvotes:</b> 35</p><p><b>Summary:</b> The remarkable advancements of vision and language foundation models in multimodal understanding, reasoning, and generation has sparked growing efforts to extend such intelligence to the physical world, fueling the flourishing of vision-language-action (VLA) models. Despite seemingly diverse approaches, we observe that current VLA models can be unified under a single framework: vision and language inputs are processed by a series of VLA modules, producing a chain of action tokens that progressively encode more grounded and actionable information, ultimately generating executable actions. We further determine that the primary design choice distinguishing VLA models lies in how action tokens are formulated, which can be categorized into language description, code, affordance, trajectory, goal state, latent representation, raw action, and reasoning. However, there remains a lack of comprehensive understanding regarding action tokens, significantly impeding effective VLA development and obscuring future directions. Therefore, this survey aims to categorize and interpret existing VLA research through the lens of action tokenization, distill the strengths and limitations of each token type, and identify areas for improvement. Through this systematic review and analysis, we offer a synthesized outlook on the broader evolution of VLA models, highlight underexplored yet promising directions, and contribute guidance for future research, hoping to bring the field closer to general-purpose intelligence.</p> - https://arxiv.org/abs/2507.01925 - Wed, 02 Jul 2025 17:34:52 +0000 + Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference + https://arxiv.org/abs/2508.02193 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.02193.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuxuan Song, Zheng Zhang, Cheng Luo, Pengyang Gao, Fan Xia, Hao Luo, Zheng Li, Yuehang Yang, Hongli Yu, Xingwei Qu, Yuwei Fu, Jing Su, Ge Zhang, Wenhao Huang, Mingxuan Wang, Lin Yan, Xiaoying Jia, Jingjing Liu, Wei-Ying Ma, Ya-Qin Zhang, Yonghui Wu, Hao Zhou</p><p><b>Upvotes:</b> 128</p><p><b>Summary:</b> We present Seed Diffusion Preview, a large-scale language model based on discrete-state diffusion, offering remarkably fast inference speed. Thanks to non-sequential, parallel generation, discrete diffusion models provide a notable speedup to mitigate the inherent latency of token-by-token decoding, as demonstrated recently (e.g., Mercury Coder, Gemini Diffusion). Seed Diffusion Preview achieves an inference speed of 2,146 token/s over H20 GPUs while maintaining competitive performance across a sweep of standard code evaluation benchmarks, significantly faster than contemporary Mercury and Gemini Diffusion, establishing new state of the art on the speed-quality Pareto frontier for code models.</p> + https://arxiv.org/abs/2508.02193 + Mon, 04 Aug 2025 08:43:01 +0000 - LongAnimation: Long Animation Generation with Dynamic Global-Local Memory - https://arxiv.org/abs/2507.01945 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.01945.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Nan Chen, Mengqi Huang, Yihao Meng, Zhendong Mao</p><p><b>Upvotes:</b> 74</p><p><b>Summary:</b> Animation colorization is a crucial part of real animation industry production. Long animation colorization has high labor costs. Therefore, automated long animation colorization based on the video generation model has significant research value. Existing studies are limited to short-term colorization. These studies adopt a local paradigm, fusing overlapping features to achieve smooth transitions between local segments. However, the local paradigm neglects global information, failing to maintain long-term color consistency. In this study, we argue that ideal long-term color consistency can be achieved through a dynamic global-local paradigm, i.e., dynamically extracting global color-consistent features relevant to the current generation. Specifically, we propose LongAnimation, a novel framework, which mainly includes a SketchDiT, a Dynamic Global-Local Memory (DGLM), and a Color Consistency Reward. The SketchDiT captures hybrid reference features to support the DGLM module. The DGLM module employs a long video understanding model to dynamically compress global historical features and adaptively fuse them with the current generation features. To refine the color consistency, we introduce a Color Consistency Reward. During inference, we propose a color consistency fusion to smooth the video segment transition. Extensive experiments on both short-term (14 frames) and long-term (average 500 frames) animations show the effectiveness of LongAnimation in maintaining short-term and long-term color consistency for open-domain animation colorization task. The code can be found at https://cn-makers.github.io/long_animation_web/.</p> - https://arxiv.org/abs/2507.01945 - Wed, 02 Jul 2025 17:55:50 +0000 + CellForge: Agentic Design of Virtual Cell Models + https://arxiv.org/abs/2508.02276 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.02276.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiangru Tang, Zhuoyun Yu, Jiapeng Chen, Yan Cui, Daniel Shao, Weixu Wang, Fang Wu, Yuchen Zhuang, Wenqi Shi, Zhi Huang, Arman Cohan, Xihong Lin, Fabian Theis, Smita Krishnaswamy, Mark Gerstein</p><p><b>Upvotes:</b> 38</p><p><b>Summary:</b> Virtual cell modeling represents an emerging frontier at the intersection of artificial intelligence and biology, aiming to predict quantities such as responses to diverse perturbations quantitatively. However, autonomously building computational models for virtual cells is challenging due to the complexity of biological systems, the heterogeneity of data modalities, and the need for domain-specific expertise across multiple disciplines. Here, we introduce CellForge, an agentic system that leverages a multi-agent framework that transforms presented biological datasets and research objectives directly into optimized computational models for virtual cells. More specifically, given only raw single-cell multi-omics data and task descriptions as input, CellForge outputs both an optimized model architecture and executable code for training virtual cell models and inference. The framework integrates three core modules: Task Analysis for presented dataset characterization and relevant literature retrieval, Method Design, where specialized agents collaboratively develop optimized modeling strategies, and Experiment Execution for automated generation of code. The agents in the Design module are separated into experts with differing perspectives and a central moderator, and have to collaboratively exchange solutions until they achieve a reasonable consensus. We demonstrate CellForge's capabilities in single-cell perturbation prediction, using six diverse datasets that encompass gene knockouts, drug treatments, and cytokine stimulations across multiple modalities. CellForge consistently outperforms task-specific state-of-the-art methods. Overall, CellForge demonstrates how iterative interaction between LLM agents with differing perspectives provides better solutions than directly addressing a modeling challenge. Our code is publicly available at https://github.com/gersteinlab/CellForge.</p> + https://arxiv.org/abs/2508.02276 + Mon, 04 Aug 2025 10:43:31 +0000 - Kwai Keye-VL Technical Report - https://arxiv.org/abs/2507.01949 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.01949.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kwai Keye Team, Biao Yang, Bin Wen, Changyi Liu, Chenglong Chu, Chengru Song, Chongling Rao, Chuan Yi, Da Li, Dunju Zang, Fan Yang, Guorui Zhou, Hao Peng, Haojie Ding, Jiaming Huang, Jiangxia Cao, Jiankang Chen, Jingyun Hua, Jin Ouyang, Kaibing Chen, Kaiyu Jiang, Kaiyu Tang, Kun Gai, Shengnan Zhang, Siyang Mao, Sui Huang, Tianke Zhang, Tingting Gao, Wei Chen, Wei Yuan, Xiangyu Wu, Xiao Hu, Xingyu Lu, Yang Zhou, Yi-Fan Zhang, Yiping Yang, Yulong Chen, Zhenhua Wu, Zhenyu Li, Zhixin Ling, Ziming Li, Dehua Ma, Di Xu, Haixuan Gao, Hang Li, Jiawei Guo, Jing Wang, Lejian Ren, Muhao Wei, Qianqian Wang, Qigen Hu, Shiyao Wang, Tao Yu, Xinchen Luo, Yan Li, Yiming Liang, Yuhang Hu, Zeyi Lu, Zhuoran Yang, Zixing Zhang</p><p><b>Upvotes:</b> 126</p><p><b>Summary:</b> While Multimodal Large Language Models (MLLMs) demonstrate remarkable capabilities on static images, they often fall short in comprehending dynamic, information-dense short-form videos, a dominant medium in today's digital landscape. To bridge this gap, we introduce Kwai Keye-VL, an 8-billion-parameter multimodal foundation model engineered for leading-edge performance in short-video understanding while maintaining robust general-purpose vision-language abilities. The development of Keye-VL rests on two core pillars: a massive, high-quality dataset exceeding 600 billion tokens with a strong emphasis on video, and an innovative training recipe. This recipe features a four-stage pre-training process for solid vision-language alignment, followed by a meticulous two-phase post-training process. The first post-training stage enhances foundational capabilities like instruction following, while the second phase focuses on stimulating advanced reasoning. In this second phase, a key innovation is our five-mode ``cold-start'' data mixture, which includes ``thinking'', ``non-thinking'', ``auto-think'', ``think with image'', and high-quality video data. This mixture teaches the model to decide when and how to reason. Subsequent reinforcement learning (RL) and alignment steps further enhance these reasoning capabilities and correct abnormal model behaviors, such as repetitive outputs. To validate our approach, we conduct extensive evaluations, showing that Keye-VL achieves state-of-the-art results on public video benchmarks and remains highly competitive on general image-based tasks (Figure 1). Furthermore, we develop and release the KC-MMBench, a new benchmark tailored for real-world short-video scenarios, where Keye-VL shows a significant advantage.</p> - https://arxiv.org/abs/2507.01949 - Wed, 02 Jul 2025 17:57:28 +0000 + Qwen-Image Technical Report + https://arxiv.org/abs/2508.02324 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.02324.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chenfei Wu, Jiahao Li, Jingren Zhou, Junyang Lin, Kaiyuan Gao, Kun Yan, Sheng-ming Yin, Shuai Bai, Xiao Xu, Yilei Chen, Yuxiang Chen, Zecheng Tang, Zekai Zhang, Zhengyi Wang, An Yang, Bowen Yu, Chen Cheng, Dayiheng Liu, Deqing Li, Hang Zhang, Hao Meng, Hu Wei, Jingyuan Ni, Kai Chen, Kuan Cao, Liang Peng, Lin Qu, Minggang Wu, Peng Wang, Shuting Yu, Tingkun Wen, Wensen Feng, Xiaoxiao Xu, Yi Wang, Yichang Zhang, Yongqiang Zhu, Yujia Wu, Yuxuan Cai, Zenan Liu</p><p><b>Upvotes:</b> 239</p><p><b>Summary:</b> We present Qwen-Image, an image generation foundation model in the Qwen series that achieves significant advances in complex text rendering and precise image editing. To address the challenges of complex text rendering, we design a comprehensive data pipeline that includes large-scale data collection, filtering, annotation, synthesis, and balancing. Moreover, we adopt a progressive training strategy that starts with non-text-to-text rendering, evolves from simple to complex textual inputs, and gradually scales up to paragraph-level descriptions. This curriculum learning approach substantially enhances the model's native text rendering capabilities. As a result, Qwen-Image not only performs exceptionally well in alphabetic languages such as English, but also achieves remarkable progress on more challenging logographic languages like Chinese. To enhance image editing consistency, we introduce an improved multi-task training paradigm that incorporates not only traditional text-to-image (T2I) and text-image-to-image (TI2I) tasks but also image-to-image (I2I) reconstruction, effectively aligning the latent representations between Qwen2.5-VL and MMDiT. Furthermore, we separately feed the original image into Qwen2.5-VL and the VAE encoder to obtain semantic and reconstructive representations, respectively. This dual-encoding mechanism enables the editing module to strike a balance between preserving semantic consistency and maintaining visual fidelity. Qwen-Image achieves state-of-the-art performance, demonstrating its strong capabilities in both image generation and editing across multiple benchmarks.</p> + https://arxiv.org/abs/2508.02324 + Mon, 04 Aug 2025 11:49:20 +0000 - Test-Time Scaling with Reflective Generative Model - https://arxiv.org/abs/2507.01951 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.01951.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zixiao Wang, Yuxin Wang, Xiaorui Wang, Mengting Xing, Jie Gao, Jianjun Xu, Guangcan Liu, Chenhui Jin, Zhuo Wang, Shengzhuo Zhang, Hongtao Xie</p><p><b>Upvotes:</b> 98</p><p><b>Summary:</b> We introduce our first reflective generative model MetaStone-S1, which obtains OpenAI o3's performance via the self-supervised process reward model (SPRM). Through sharing the backbone network and using task-specific heads for next token prediction and process scoring respectively, SPRM successfully integrates the policy model and process reward model(PRM) into a unified interface without extra process annotation, reducing over 99% PRM parameters for efficient reasoning. Equipped with SPRM, MetaStone-S1 is naturally suitable for test time scaling (TTS), and we provide three reasoning effort modes (low, medium, and high), based on the controllable thinking length. Moreover, we empirically establish a scaling law that reveals the relationship between total thinking computation and TTS performance. Experiments demonstrate that our MetaStone-S1 achieves comparable performance to OpenAI-o3-mini's series with only 32B parameter size. To support the research community, we have open-sourced MetaStone-S1 at https://github.com/MetaStone-AI/MetaStone-S1.</p> - https://arxiv.org/abs/2507.01951 - Wed, 02 Jul 2025 17:58:01 +0000 + Skywork UniPic: Unified Autoregressive Modeling for Visual Understanding and Generation + https://arxiv.org/abs/2508.03320 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.03320.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Peiyu Wang, Yi Peng, Yimeng Gan, Liang Hu, Tianyidan Xie, Xiaokun Wang, Yichen Wei, Chuanxin Tang, Bo Zhu, Changshi Li, Hongyang Wei, Eric Li, Xuchen Song, Yang Liu, Yahui Zhou</p><p><b>Upvotes:</b> 59</p><p><b>Summary:</b> We introduce Skywork UniPic, a 1.5 billion-parameter autoregressive model that unifies image understanding, text-to-image generation, and image editing within a single architecture-eliminating the need for task-specific adapters or inter-module connectors-and demonstrate that compact multimodal systems can achieve state-of-the-art performance on commodity hardware. Skywork UniPic achieves a GenEval score of 0.86, surpassing most existing unified models; sets a new DPG-Bench complex-generation record of 85.5; attains 5.83 on GEditBench-EN and 3.49 on ImgEdit-Bench for image editing; and generates 1024 x 1024 images with under 15 GB of GPU memory (e.g., RTX 4090). (1) a decoupled encoding strategy that leverages a masked autoregressive encoder for synthesis and a SigLIP2 encoder for understanding, all feeding a shared autoregressive decoder; (2) a progressive, resolution-aware training schedule scaling from 256 x 256 to 1024 x 1024 while dynamically unfreezing parameters to balance capacity and stability; and (3) meticulously curated, 100 million-scale datasets augmented with task-specific reward models to refine generation and editing objectives. By demonstrating that high-fidelity multimodal integration need not incur prohibitive resource demands, Skywork UniPic establishes a practical paradigm for deployable, high-fidelity multimodal AI. Code and weights are publicly available at https://huggingface.co/Skywork/Skywork-UniPic-1.5B.</p> + https://arxiv.org/abs/2508.03320 + Tue, 05 Aug 2025 10:59:01 +0000 - How Well Does GPT-4o Understand Vision? Evaluating Multimodal Foundation Models on Standard Computer Vision Tasks - https://arxiv.org/abs/2507.01955 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.01955.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Rahul Ramachandran, Ali Garjani, Roman Bachmann, Andrei Atanov, Oğuzhan Fatih Kar, Amir Zamir</p><p><b>Upvotes:</b> 34</p><p><b>Summary:</b> Multimodal foundation models, such as GPT-4o, have recently made remarkable progress, but it is not clear where exactly these models stand in terms of understanding vision. In this paper, we benchmark the performance of popular multimodal foundation models (GPT-4o, o4-mini, Gemini 1.5 Pro and Gemini 2.0 Flash, Claude 3.5 Sonnet, Qwen2-VL, Llama 3.2) on standard computer vision tasks (semantic segmentation, object detection, image classification, depth and surface normal prediction) using established datasets (e.g., COCO, ImageNet and its variants, etc). The main challenges to performing this are: 1) most models are trained to output text and cannot natively express versatile domains, such as segments or 3D geometry, and 2) many leading models are proprietary and accessible only at an API level, i.e., there is no weight access to adapt them. We address these challenges by translating standard vision tasks into equivalent text-promptable and API-compatible tasks via prompt chaining to create a standardized benchmarking framework. We observe that 1) the models are not close to the state-of-the-art specialist models at any task. However, 2) they are respectable generalists; this is remarkable as they are presumably trained on primarily image-text-based tasks. 3) They perform semantic tasks notably better than geometric ones. 4) While the prompt-chaining techniques affect performance, better models exhibit less sensitivity to prompt variations. 5) GPT-4o performs the best among non-reasoning models, securing the top position in 4 out of 6 tasks, 6) reasoning models, e.g. o3, show improvements in geometric tasks, and 7) a preliminary analysis of models with native image generation, like the latest GPT-4o, shows they exhibit quirks like hallucinations and spatial misalignments.</p> - https://arxiv.org/abs/2507.01955 - Wed, 02 Jul 2025 17:59:07 +0000 + Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning + https://arxiv.org/abs/2508.03501 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.03501.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Alexander Golubev, Maria Trofimova, Sergei Polezhaev, Ibragim Badertdinov, Maksim Nekrashevich, Anton Shevtsov, Simon Karasik, Sergey Abramov, Andrei Andriushchenko, Filipp Fisin, Sergei Skvortsov, Boris Yangel</p><p><b>Upvotes:</b> 55</p><p><b>Summary:</b> Research on applications of Reinforcement Learning (RL) to Large Language Models (LLMs) has mostly been focused on single-turn problems, such as mathematical reasoning or single-shot code generation. While these problems can be viewed as token-level multi-turn MDPs, this view corresponds to a degenerate case of multi-turn interaction where the environment provides no feedback. This contrasts with many real-world domains, such as software engineering (SWE), which require rich multi-turn interactions with a stateful environment that responds to each action with a non-trivial observation. To bridge this gap, we demonstrate the successful application of RL to this general regime. Using a modified Decoupled Advantage Policy Optimization (DAPO) algorithm, we train an agent based on Qwen2.5-72B-Instruct to solve real-world software engineering tasks. Our approach increases the agent's success rate on the SWE-bench Verified benchmark from a 20% rejection fine-tuned baseline to 39%, without relying on any teacher models. On SWE-rebench, our agent matches or outperforms leading open-weight models such as DeepSeek-V3-0324 and Qwen3-235B-A22B using an identical scaffolding, offering a viable path toward building more capable autonomous agents for complex real-world problems based on open models.</p> + https://arxiv.org/abs/2508.03501 + Tue, 05 Aug 2025 14:30:47 +0000 - Energy-Based Transformers are Scalable Learners and Thinkers - https://arxiv.org/abs/2507.02092 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.02092.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Alexi Gladstone, Ganesh Nanduru, Md Mofijul Islam, Peixuan Han, Hyeonjeong Ha, Aman Chadha, Yilun Du, Heng Ji, Jundong Li, Tariq Iqbal</p><p><b>Upvotes:</b> 57</p><p><b>Summary:</b> Inference-time computation techniques, analogous to human System 2 Thinking, have recently become popular for improving model performances. However, most existing approaches suffer from several limitations: they are modality-specific (e.g., working only in text), problem-specific (e.g., verifiable domains like math and coding), or require additional supervision/training on top of unsupervised pretraining (e.g., verifiers or verifiable rewards). In this paper, we ask the question "Is it possible to generalize these System 2 Thinking approaches, and develop models that learn to think solely from unsupervised learning?" Interestingly, we find the answer is yes, by learning to explicitly verify the compatibility between inputs and candidate-predictions, and then re-framing prediction problems as optimization with respect to this verifier. Specifically, we train Energy-Based Transformers (EBTs) -- a new class of Energy-Based Models (EBMs) -- to assign an energy value to every input and candidate-prediction pair, enabling predictions through gradient descent-based energy minimization until convergence. Across both discrete (text) and continuous (visual) modalities, we find EBTs scale faster than the dominant Transformer++ approach during training, achieving an up to 35% higher scaling rate with respect to data, batch size, parameters, FLOPs, and depth. During inference, EBTs improve performance with System 2 Thinking by 29% more than the Transformer++ on language tasks, and EBTs outperform Diffusion Transformers on image denoising while using fewer forward passes. Further, we find that EBTs achieve better results than existing models on most downstream tasks given the same or worse pretraining performance, suggesting that EBTs generalize better than existing approaches. Consequently, EBTs are a promising new paradigm for scaling both the learning and thinking capabilities of models.</p> - https://arxiv.org/abs/2507.02092 - Wed, 02 Jul 2025 19:17:29 +0000 + Agent Lightning: Train ANY AI Agents with Reinforcement Learning + https://arxiv.org/abs/2508.03680 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.03680.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xufang Luo, Yuge Zhang, Zhiyuan He, Zilong Wang, Siyun Zhao, Dongsheng Li, Luna K. Qiu, Yuqing Yang</p><p><b>Upvotes:</b> 65</p><p><b>Summary:</b> We present Agent Lightning, a flexible and extensible framework that enables Reinforcement Learning (RL)-based training of Large Language Models (LLMs) for any AI agent. Unlike existing methods that tightly couple RL training with agent or rely on sequence concatenation with masking, Agent Lightning achieves complete decoupling between agent execution and training, allowing seamless integration with existing agents developed via diverse ways (e.g., using frameworks like LangChain, OpenAI Agents SDK, AutoGen, and building from scratch) with almost ZERO code modifications. By formulating agent execution as Markov decision process, we define an unified data interface and propose a hierarchical RL algorithm, LightningRL, which contains a credit assignment module, allowing us to decompose trajectories generated by ANY agents into training transition. This enables RL to handle complex interaction logic, such as multi-agent scenarios and dynamic workflows. For the system design, we introduce a Training-Agent Disaggregation architecture, and brings agent observability frameworks into agent runtime, providing a standardized agent finetuning interface. Experiments across text-to-SQL, retrieval-augmented generation, and math tool-use tasks demonstrate stable, continuous improvements, showcasing the framework's potential for real-world agent training and deployment.</p> + https://arxiv.org/abs/2508.03680 + Tue, 05 Aug 2025 17:50:13 +0000 - Heeding the Inner Voice: Aligning ControlNet Training via Intermediate Features Feedback - https://arxiv.org/abs/2507.02321 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.02321.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Nina Konovalova, Maxim Nikolaev, Andrey Kuznetsov, Aibek Alanov</p><p><b>Upvotes:</b> 38</p><p><b>Summary:</b> Despite significant progress in text-to-image diffusion models, achieving precise spatial control over generated outputs remains challenging. ControlNet addresses this by introducing an auxiliary conditioning module, while ControlNet++ further refines alignment through a cycle consistency loss applied only to the final denoising steps. However, this approach neglects intermediate generation stages, limiting its effectiveness. We propose InnerControl, a training strategy that enforces spatial consistency across all diffusion steps. Our method trains lightweight convolutional probes to reconstruct input control signals (e.g., edges, depth) from intermediate UNet features at every denoising step. These probes efficiently extract signals even from highly noisy latents, enabling pseudo ground truth controls for training. By minimizing the discrepancy between predicted and target conditions throughout the entire diffusion process, our alignment loss improves both control fidelity and generation quality. Combined with established techniques like ControlNet++, InnerControl achieves state-of-the-art performance across diverse conditioning methods (e.g., edges, depth).</p> - https://arxiv.org/abs/2507.02321 - Thu, 03 Jul 2025 05:25:53 +0000 + CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward + https://arxiv.org/abs/2508.03686 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.03686.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shudong Liu, Hongwei Liu, Junnan Liu, Linchen Xiao, Songyang Gao, Chengqi Lyu, Yuzhe Gu, Wenwei Zhang, Derek F. Wong, Songyang Zhang, Kai Chen</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> Answer verification is crucial not only for evaluating large language models (LLMs) by matching their unstructured outputs against standard answers, but also serves as the reward model to guide LLM optimization. Most evaluation frameworks rely on regularized matching or employ general LLMs for answer verification, which demands extensive, repetitive customization for regex rules or evaluation prompts. Two fundamental limitations persist in current methodologies: 1) the absence of comprehensive benchmarks that systematically evaluate verification capabilities across different LLMs; and 2) the nascent stage of verifier development, where existing approaches lack both the robustness to handle complex edge cases and the generalizability across different domains. In this work, we develop CompassVerifier, an accurate and robust lightweight verifier model for evaluation and outcome reward. It demonstrates multi-domain competency spanning math, knowledge, and diverse reasoning tasks, with the capability to process various answer types, including multi-subproblems, formulas, and sequence answers, while effectively identifying abnormal/invalid responses. We introduce VerifierBench benchmark comprising model outputs collected from multiple data sources, augmented through manual analysis of metaerror patterns to enhance CompassVerifier. We anticipate that CompassVerifier and VerifierBench will facilitate answer verification, evaluation protocols, and reinforcement learning research. Code and dataset are available at https://github.com/open-compass/CompassVerifier.</p> + https://arxiv.org/abs/2508.03686 + Tue, 05 Aug 2025 17:55:24 +0000 - WebSailor: Navigating Super-human Reasoning for Web Agent - https://arxiv.org/abs/2507.02592 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.02592.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kuan Li, Zhongwang Zhang, Huifeng Yin, Liwen Zhang, Litu Ou, Jialong Wu, Wenbiao Yin, Baixuan Li, Zhengwei Tao, Xinyu Wang, Weizhou Shen, Junkai Zhang, Dingchu Zhang, Xixi Wu, Yong Jiang, Ming Yan, Pengjun Xie, Fei Huang, Jingren Zhou</p><p><b>Upvotes:</b> 101</p><p><b>Summary:</b> Transcending human cognitive limitations represents a critical frontier in LLM training. Proprietary agentic systems like DeepResearch have demonstrated superhuman capabilities on extremely complex information-seeking benchmarks such as BrowseComp, a feat previously unattainable. We posit that their success hinges on a sophisticated reasoning pattern absent in open-source models: the ability to systematically reduce extreme uncertainty when navigating vast information landscapes. Based on this insight, we introduce WebSailor, a complete post-training methodology designed to instill this crucial capability. Our approach involves generating novel, high-uncertainty tasks through structured sampling and information obfuscation, RFT cold start, and an efficient agentic RL training algorithm, Duplicating Sampling Policy Optimization (DUPO). With this integrated pipeline, WebSailor significantly outperforms all opensource agents in complex information-seeking tasks, matching proprietary agents' performance and closing the capability gap.</p> - https://arxiv.org/abs/2507.02592 - Thu, 03 Jul 2025 12:59:07 +0000 + LongVie: Multimodal-Guided Controllable Ultra-Long Video Generation + https://arxiv.org/abs/2508.03694 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.03694.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jianxiong Gao, Zhaoxi Chen, Xian Liu, Jianfeng Feng, Chenyang Si, Yanwei Fu, Yu Qiao, Ziwei Liu</p><p><b>Upvotes:</b> 50</p><p><b>Summary:</b> Controllable ultra-long video generation is a fundamental yet challenging task. Although existing methods are effective for short clips, they struggle to scale due to issues such as temporal inconsistency and visual degradation. In this paper, we initially investigate and identify three key factors: separate noise initialization, independent control signal normalization, and the limitations of single-modality guidance. To address these issues, we propose LongVie, an end-to-end autoregressive framework for controllable long video generation. LongVie introduces two core designs to ensure temporal consistency: 1) a unified noise initialization strategy that maintains consistent generation across clips, and 2) global control signal normalization that enforces alignment in the control space throughout the entire video. To mitigate visual degradation, LongVie employs 3) a multi-modal control framework that integrates both dense (e.g., depth maps) and sparse (e.g., keypoints) control signals, complemented by 4) a degradation-aware training strategy that adaptively balances modality contributions over time to preserve visual quality. We also introduce LongVGenBench, a comprehensive benchmark consisting of 100 high-resolution videos spanning diverse real-world and synthetic environments, each lasting over one minute. Extensive experiments show that LongVie achieves state-of-the-art performance in long-range controllability, consistency, and quality.</p> + https://arxiv.org/abs/2508.03694 + Tue, 05 Aug 2025 17:59:58 +0000 - LangScene-X: Reconstruct Generalizable 3D Language-Embedded Scenes with TriMap Video Diffusion - https://arxiv.org/abs/2507.02813 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.02813.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fangfu Liu, Hao Li, Jiawei Chi, Hanyang Wang, Minghui Yang, Fudong Wang, Yueqi Duan</p><p><b>Upvotes:</b> 59</p><p><b>Summary:</b> Recovering 3D structures with open-vocabulary scene understanding from 2D images is a fundamental but daunting task. Recent developments have achieved this by performing per-scene optimization with embedded language information. However, they heavily rely on the calibrated dense-view reconstruction paradigm, thereby suffering from severe rendering artifacts and implausible semantic synthesis when limited views are available. In this paper, we introduce a novel generative framework, coined LangScene-X, to unify and generate 3D consistent multi-modality information for reconstruction and understanding. Powered by the generative capability of creating more consistent novel observations, we can build generalizable 3D language-embedded scenes from only sparse views. Specifically, we first train a TriMap video diffusion model that can generate appearance (RGBs), geometry (normals), and semantics (segmentation maps) from sparse inputs through progressive knowledge integration. Furthermore, we propose a Language Quantized Compressor (LQC), trained on large-scale image datasets, to efficiently encode language embeddings, enabling cross-scene generalization without per-scene retraining. Finally, we reconstruct the language surface fields by aligning language information onto the surface of 3D scenes, enabling open-ended language queries. Extensive experiments on real-world data demonstrate the superiority of our LangScene-X over state-of-the-art methods in terms of quality and generalizability. Project Page: https://liuff19.github.io/LangScene-X.</p> - https://arxiv.org/abs/2507.02813 - Thu, 03 Jul 2025 17:21:23 +0000 + VeriGUI: Verifiable Long-Chain GUI Dataset + https://arxiv.org/abs/2508.04026 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.04026.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shunyu Liu, Minghao Liu, Huichi Zhou, Zhenyu Cui, Yang Zhou, Yuhao Zhou, Wendong Fan, Ge Zhang, Jiajun Shi, Weihao Xuan, Jiaxing Huang, Shuang Luo, Fang Wu, Heli Qi, Qingcheng Zeng, Ziqi Ren, Jialiang Gao, Jindi Lv, Junjie Wang, Aosong Feng, Heng Zhou, Wangchunshu Zhou, Zhenfei Yin, Wenlong Zhang, Guohao Li, Wenhao Yu, Irene Li, Lei Ma, Lei Bai, Qunshu Lin, Mingli Song, Dacheng Tao</p><p><b>Upvotes:</b> 156</p><p><b>Summary:</b> Recent studies have delved into constructing autonomous agents capable of performing complex Graphical User Interface (GUI)-based computer tasks, with the potential to revolutionize human-computer interaction. Despite encouraging results, existing efforts mainly focus on short-term interactions and rely on outcome-only verification, thereby limiting their scalability in real-world GUI applications that demand long-horizon task decomposition and execution. In this work, we introduce VeriGUI, a novel verifiable long-chain GUI dataset designed to facilitate the development and evaluation of generalist GUI agents operating in realistic computer environments. Our dataset emphasizes two critical dimensions: (1) long-chain complexity, with tasks decomposed into a sequence of interdependent subtasks spanning hundreds of steps, explicitly designed to allow any subtask to serve as a valid starting point; and (2) subtask-level verifiability, which enables diverse exploration strategies within each subtask, while ensuring that each subtask-level goal remains verifiable and consistent. The dataset consists of GUI task trajectories across both desktop and web, annotated by human experts. Extensive experiments on VeriGUI using various agents with different foundation models reveal significant performance gaps in handling long-horizon tasks, highlighting the need for more robust planning and decision-making capabilities in GUI agents.</p> + https://arxiv.org/abs/2508.04026 + Wed, 06 Aug 2025 02:38:18 +0000 - MemOS: A Memory OS for AI System - https://arxiv.org/abs/2507.03724 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.03724.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhiyu Li, Shichao Song, Chenyang Xi, Hanyu Wang, Chen Tang, Simin Niu, Ding Chen, Jiawei Yang, Chunyu Li, Qingchen Yu, Jihao Zhao, Yezhaohui Wang, Peng Liu, Zehao Lin, Pengyuan Wang, Jiahao Huo, Tianyi Chen, Kai Chen, Kehang Li, Zhen Tao, Junpeng Ren, Huayi Lai, Hao Wu, Bo Tang, Zhenren Wang, Zhaoxin Fan, Ningyu Zhang, Linfeng Zhang, Junchi Yan, Mingchuan Yang, Tong Xu, Wei Xu, Huajun Chen, Haofeng Wang, Hongkang Yang, Wentao Zhang, Zhi-Qin John Xu, Siheng Chen, Feiyu Xiong</p><p><b>Upvotes:</b> 141</p><p><b>Summary:</b> Large Language Models (LLMs) have become an essential infrastructure for Artificial General Intelligence (AGI), yet their lack of well-defined memory management systems hinders the development of long-context reasoning, continual personalization, and knowledge consistency.Existing models mainly rely on static parameters and short-lived contextual states, limiting their ability to track user preferences or update knowledge over extended periods.While Retrieval-Augmented Generation (RAG) introduces external knowledge in plain text, it remains a stateless workaround without lifecycle control or integration with persistent representations.Recent work has modeled the training and inference cost of LLMs from a memory hierarchy perspective, showing that introducing an explicit memory layer between parameter memory and external retrieval can substantially reduce these costs by externalizing specific knowledge. Beyond computational efficiency, LLMs face broader challenges arising from how information is distributed over time and context, requiring systems capable of managing heterogeneous knowledge spanning different temporal scales and sources. To address this challenge, we propose MemOS, a memory operating system that treats memory as a manageable system resource. It unifies the representation, scheduling, and evolution of plaintext, activation-based, and parameter-level memories, enabling cost-efficient storage and retrieval. As the basic unit, a MemCube encapsulates both memory content and metadata such as provenance and versioning. MemCubes can be composed, migrated, and fused over time, enabling flexible transitions between memory types and bridging retrieval with parameter-based learning. MemOS establishes a memory-centric system framework that brings controllability, plasticity, and evolvability to LLMs, laying the foundation for continual learning and personalized modeling.</p> - https://arxiv.org/abs/2507.03724 - Fri, 04 Jul 2025 17:21:46 +0000 + Enhancing Vision-Language Model Training with Reinforcement Learning in Synthetic Worlds for Real-World Success + https://arxiv.org/abs/2508.04280 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.04280.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> George Bredis, Stanislav Dereka, Viacheslav Sinii, Ruslan Rakhimov, Daniil Gavrilov</p><p><b>Upvotes:</b> 35</p><p><b>Summary:</b> Interactive multimodal agents must convert raw visual observations into coherent sequences of language-conditioned actions -- a capability that current vision-language models (VLMs) still lack. Earlier reinforcement-learning (RL) efforts could, in principle, endow VLMs with such skills, but they have seldom tested whether the learned behaviours generalize beyond their training simulators, and they depend either on brittle hyperparameter tuning or on dense-reward environments with low state variability. We introduce Vision-Language Decoupled Actor-Critic (VL-DAC), a lightweight, hyperparameter-free RL algorithm. VL-DAC applies PPO updates to action tokens while learning value only at the environment-step level: an arrangement, to our knowledge, not previously explored for large VLMs or LLMs. This simple decoupling removes unstable weighting terms and yields faster, more reliable convergence. Training a single VLM with VL-DAC in one inexpensive simulator at a time (MiniWorld, Gym-Cards, ALFWorld, or WebShop) already produces policies that generalize widely: +50\% relative on BALROG (game-centric agentic control), +5\% relative on the hardest part of VSI-Bench (spatial planning), and +2\% on VisualWebBench (web navigation), all without degrading general image understanding accuracy. These results provide the first evidence that a simple RL algorithm can train VLMs entirely in cheap synthetic worlds while delivering measurable gains on real-image agentic, spatial-reasoning, and web-navigation benchmarks.</p> + https://arxiv.org/abs/2508.04280 + Wed, 06 Aug 2025 10:08:48 +0000 - Easy Dataset: A Unified and Extensible Framework for Synthesizing LLM Fine-Tuning Data from Unstructured Documents - https://arxiv.org/abs/2507.04009 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.04009.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ziyang Miao, Qiyu Sun, Jingyuan Wang, Yuchen Gong, Yaowei Zheng, Shiqi Li, Richong Zhang</p><p><b>Upvotes:</b> 38</p><p><b>Summary:</b> Large language models (LLMs) have shown impressive performance on general-purpose tasks, yet adapting them to specific domains remains challenging due to the scarcity of high-quality domain data. Existing data synthesis tools often struggle to extract reliable fine-tuning data from heterogeneous documents effectively. To address this limitation, we propose Easy Dataset, a unified framework for synthesizing fine-tuning data from unstructured documents via an intuitive graphical user interface (GUI). Specifically, Easy Dataset allows users to easily configure text extraction models and chunking strategies to transform raw documents into coherent text chunks. It then leverages a persona-driven prompting approach to generate diverse question-answer pairs using public-available LLMs. Throughout the pipeline, a human-in-the-loop visual interface facilitates the review and refinement of intermediate outputs to ensure data quality. Experiments on a financial question-answering task show that fine-tuning LLMs on the synthesized dataset significantly improves domain-specific performance while preserving general knowledge. The source code and installable package are available at https://github.com/ConardLi/easy-dataset and have garnered over 9,000 GitHub stars.</p> - https://arxiv.org/abs/2507.04009 - Sat, 05 Jul 2025 11:38:59 +0000 + Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL + https://arxiv.org/abs/2508.13167 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.13167.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weizhen Li, Jianbo Lin, Zhuosong Jiang, Jingyi Cao, Xinpeng Liu, Jiayu Zhang, Zhenqiang Huang, Qianben Chen, Weichen Sun, Qiexiang Wang, Hongxuan Lu, Tianrui Qin, Chenghao Zhu, Yi Yao, Shuying Fan, Xiaowan Li, Tiannan Wang, Pai Liu, King Zhu, He Zhu, Dingfeng Shi, Piaohong Wang, Yeyi Guan, Xiangru Tang, Minghao Liu, Yuchen Eleanor Jiang, Jian Yang, Jiaheng Liu, Ge Zhang, Wangchunshu Zhou</p><p><b>Upvotes:</b> 119</p><p><b>Summary:</b> Recent advances in large language models (LLMs) and multi-agent systems have demonstrated remarkable capabilities in complex problem-solving tasks such as deep research, vibe coding, and mathematical reasoning. However, most existing multi-agent systems are built upon manual prompt/workflow engineering with sophisticated agent frameworks, making them computationally inefficient, less capable, and can not benefit from data-centric learning. In this work, we introduce Chain-of-Agents (CoA), a novel paradigm of LLM reasoning that enables native end-to-end complex problem-solving in the same way as a multi-agent system (i.e., multi-turn problem solving with multiple tools and multiple agents) within one model. In chain-of-agents problem-solving, the model dynamically activates different tool agents and role-playing agents to simulate multi-agent collaboration in an end-to-end fashion. To elicit end-to-end chain-of-agents problem-solving abilities in LLMs, we introduce a multi-agent distillation framework to distill state-of-the-art multi-agent systems into chain-of-agents trajectories for agentic supervised fine-tuning. We then use agentic reinforcement learning on verifiable agentic tasks to further improve the models' capabilities on chain-of-agents problem solving. We call the resulting models Agent Foundation Models (AFMs). Our empirical studies demonstrate that AFM establishes new state-of-the-art performance across diverse benchmarks in both web agent and code agent settings. We make the entire research, including the model weights, code for training and evaluation, and the training data, fully open-sourced, which offers a solid starting point for future research on agent models and agentic RL.</p> + https://arxiv.org/abs/2508.13167 + Wed, 06 Aug 2025 17:01:02 +0000 - How to Train Your LLM Web Agent: A Statistical Diagnosis - https://arxiv.org/abs/2507.04103 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.04103.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dheeraj Vattikonda, Santhoshi Ravichandran, Emiliano Penaloza, Hadi Nekoei, Megh Thakkar, Thibault Le Sellier de Chezelles, Nicolas Gontier, Miguel Muñoz-Mármol, Sahar Omidi Shayegan, Stefania Raimondo, Xue Liu, Alexandre Drouin, Laurent Charlin, Alexandre Piché, Alexandre Lacoste, Massimo Caccia</p><p><b>Upvotes:</b> 46</p><p><b>Summary:</b> LLM-based web agents have recently made significant progress, but much of it has occurred in closed-source systems, widening the gap with open-source alternatives. Progress has been held back by two key challenges: first, a narrow focus on single-step tasks that overlooks the complexity of multi-step web interactions; and second, the high compute costs required to post-train LLM-based web agents. To address this, we present the first statistically grounded study on compute allocation for LLM web-agent post-training. Our approach uses a two-stage pipeline, training a Llama 3.1 8B student to imitate a Llama 3.3 70B teacher via supervised fine-tuning (SFT), followed by on-policy reinforcement learning. We find this process highly sensitive to hyperparameter choices, making exhaustive sweeps impractical. To spare others from expensive trial-and-error, we sample 1,370 configurations and use bootstrapping to estimate effective hyperparameters. Our results show that combining SFT with on-policy RL consistently outperforms either approach alone on both WorkArena and MiniWob++. Further, this strategy requires only 55% of the compute to match the peak performance of pure SFT on MiniWob++, effectively pushing the compute-performance Pareto frontier, and is the only strategy that can close the gap with closed-source models.</p> - https://arxiv.org/abs/2507.04103 - Sat, 05 Jul 2025 17:12:33 +0000 + SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience + https://arxiv.org/abs/2508.04700 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.04700.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zeyi Sun, Ziyu Liu, Yuhang Zang, Yuhang Cao, Xiaoyi Dong, Tong Wu, Dahua Lin, Jiaqi Wang</p><p><b>Upvotes:</b> 50</p><p><b>Summary:</b> Repurposing large vision-language models (LVLMs) as computer use agents (CUAs) has led to substantial breakthroughs, primarily driven by human-labeled data. However, these models often struggle with novel and specialized software, particularly in scenarios lacking human annotations. To address this challenge, we propose SEAgent, an agentic self-evolving framework enabling CUAs to autonomously evolve through interactions with unfamiliar software. Specifically, SEAgent empowers computer-use agents to autonomously master novel software environments via experiential learning, where agents explore new software, learn through iterative trial-and-error, and progressively tackle auto-generated tasks organized from simple to complex. To achieve this goal, we design a World State Model for step-wise trajectory assessment, along with a Curriculum Generator that generates increasingly diverse and challenging tasks. The agent's policy is updated through experiential learning, comprised of adversarial imitation of failure actions and Group Relative Policy Optimization (GRPO) on successful ones. Furthermore, we introduce a specialist-to-generalist training strategy that integrates individual experiential insights from specialist agents, facilitating the development of a stronger generalist CUA capable of continuous autonomous evolution. This unified agent ultimately achieves performance surpassing ensembles of individual specialist agents on their specialized software. We validate the effectiveness of SEAgent across five novel software environments within OS-World. Our approach achieves a significant improvement of 23.2% in success rate, from 11.3% to 34.5%, over a competitive open-source CUA, i.e., UI-TARS.</p> + https://arxiv.org/abs/2508.04700 + Wed, 06 Aug 2025 17:58:46 +0000 - DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge - https://arxiv.org/abs/2507.04447 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.04447.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wenyao Zhang, Hongsi Liu, Zekun Qi, Yunnan Wang, XinQiang Yu, Jiazhao Zhang, Runpei Dong, Jiawei He, He Wang, Zhizheng Zhang, Li Yi, Wenjun Zeng, Xin Jin</p><p><b>Upvotes:</b> 42</p><p><b>Summary:</b> Recent advances in vision-language-action (VLA) models have shown promise in integrating image generation with action prediction to improve generalization and reasoning in robot manipulation. However, existing methods are limited to challenging image-based forecasting, which suffers from redundant information and lacks comprehensive and critical world knowledge, including dynamic, spatial and semantic information. To address these limitations, we propose DreamVLA, a novel VLA framework that integrates comprehensive world knowledge forecasting to enable inverse dynamics modeling, thereby establishing a perception-prediction-action loop for manipulation tasks. Specifically, DreamVLA introduces a dynamic-region-guided world knowledge prediction, integrated with the spatial and semantic cues, which provide compact yet comprehensive representations for action planning. This design aligns with how humans interact with the world by first forming abstract multimodal reasoning chains before acting. To mitigate interference among the dynamic, spatial and semantic information during training, we adopt a block-wise structured attention mechanism that masks their mutual attention, preventing information leakage and keeping each representation clean and disentangled. Moreover, to model the conditional distribution over future actions, we employ a diffusion-based transformer that disentangles action representations from shared latent features. Extensive experiments on both real-world and simulation environments demonstrate that DreamVLA achieves 76.7% success rate on real robot tasks and 4.44 average length on the CALVIN ABC-D benchmarks.</p> - https://arxiv.org/abs/2507.04447 - Sun, 06 Jul 2025 16:14:29 +0000 + Voost: A Unified and Scalable Diffusion Transformer for Bidirectional Virtual Try-On and Try-Off + https://arxiv.org/abs/2508.04825 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.04825.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Seungyong Lee, Jeong-gi Kwak</p><p><b>Upvotes:</b> 57</p><p><b>Summary:</b> Virtual try-on aims to synthesize a realistic image of a person wearing a target garment, but accurately modeling garment-body correspondence remains a persistent challenge, especially under pose and appearance variation. In this paper, we propose Voost - a unified and scalable framework that jointly learns virtual try-on and try-off with a single diffusion transformer. By modeling both tasks jointly, Voost enables each garment-person pair to supervise both directions and supports flexible conditioning over generation direction and garment category, enhancing garment-body relational reasoning without task-specific networks, auxiliary losses, or additional labels. In addition, we introduce two inference-time techniques: attention temperature scaling for robustness to resolution or mask variation, and self-corrective sampling that leverages bidirectional consistency between tasks. Extensive experiments demonstrate that Voost achieves state-of-the-art results on both try-on and try-off benchmarks, consistently outperforming strong baselines in alignment accuracy, visual fidelity, and generalization.</p> + https://arxiv.org/abs/2508.04825 + Wed, 06 Aug 2025 19:10:58 +0000 - 4DSloMo: 4D Reconstruction for High Speed Scene with Asynchronous Capture - https://arxiv.org/abs/2507.05163 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.05163.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yutian Chen, Shi Guo, Tianshuo Yang, Lihe Ding, Xiuyuan Yu, Jinwei Gu, Tianfan Xue</p><p><b>Upvotes:</b> 40</p><p><b>Summary:</b> Reconstructing fast-dynamic scenes from multi-view videos is crucial for high-speed motion analysis and realistic 4D reconstruction. However, the majority of 4D capture systems are limited to frame rates below 30 FPS (frames per second), and a direct 4D reconstruction of high-speed motion from low FPS input may lead to undesirable results. In this work, we propose a high-speed 4D capturing system only using low FPS cameras, through novel capturing and processing modules. On the capturing side, we propose an asynchronous capture scheme that increases the effective frame rate by staggering the start times of cameras. By grouping cameras and leveraging a base frame rate of 25 FPS, our method achieves an equivalent frame rate of 100-200 FPS without requiring specialized high-speed cameras. On processing side, we also propose a novel generative model to fix artifacts caused by 4D sparse-view reconstruction, as asynchrony reduces the number of viewpoints at each timestamp. Specifically, we propose to train a video-diffusion-based artifact-fix model for sparse 4D reconstruction, which refines missing details, maintains temporal consistency, and improves overall reconstruction quality. Experimental results demonstrate that our method significantly enhances high-speed 4D reconstruction compared to synchronous capture.</p> - https://arxiv.org/abs/2507.05163 - Mon, 07 Jul 2025 16:18:35 +0000 + R-Zero: Self-Evolving Reasoning LLM from Zero Data + https://arxiv.org/abs/2508.05004 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.05004.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chengsong Huang, Wenhao Yu, Xiaoyang Wang, Hongming Zhang, Zongxia Li, Ruosen Li, Jiaxin Huang, Haitao Mi, Dong Yu</p><p><b>Upvotes:</b> 123</p><p><b>Summary:</b> Self-evolving Large Language Models (LLMs) offer a scalable path toward super-intelligence by autonomously generating, refining, and learning from their own experiences. However, existing methods for training such models still rely heavily on vast human-curated tasks and labels, typically via fine-tuning or reinforcement learning, which poses a fundamental bottleneck to advancing AI systems toward capabilities beyond human intelligence. To overcome this limitation, we introduce R-Zero, a fully autonomous framework that generates its own training data from scratch. Starting from a single base LLM, R-Zero initializes two independent models with distinct roles, a Challenger and a Solver. These models are optimized separately and co-evolve through interaction: the Challenger is rewarded for proposing tasks near the edge of the Solver capability, and the Solver is rewarded for solving increasingly challenging tasks posed by the Challenger. This process yields a targeted, self-improving curriculum without any pre-existing tasks and labels. Empirically, R-Zero substantially improves reasoning capability across different backbone LLMs, e.g., boosting the Qwen3-4B-Base by +6.49 on math-reasoning benchmarks and +7.54 on general-domain reasoning benchmarks.</p> + https://arxiv.org/abs/2508.05004 + Thu, 07 Aug 2025 03:38:16 +0000 - Pre-Trained Policy Discriminators are General Reward Models - https://arxiv.org/abs/2507.05197 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.05197.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shihan Dou, Shichun Liu, Yuming Yang, Yicheng Zou, Yunhua Zhou, Shuhao Xing, Chenhao Huang, Qiming Ge, Demin Song, Haijun Lv, Songyang Gao, Chengqi Lv, Enyu Zhou, Honglin Guo, Zhiheng Xi, Wenwei Zhang, Qipeng Guo, Qi Zhang, Xipeng Qiu, Xuanjing Huang, Tao Gui, Kai Chen</p><p><b>Upvotes:</b> 37</p><p><b>Summary:</b> We offer a novel perspective on reward modeling by formulating it as a policy discriminator, which quantifies the difference between two policies to generate a reward signal, guiding the training policy towards a target policy with desired behaviors. Based on this conceptual insight, we propose a scalable pre-training method named Policy Discriminative Learning (POLAR), which trains a reward model (RM) to discern identical policies and discriminate different ones. Unlike traditional reward modeling methods relying on absolute preferences, POLAR captures the relative difference between one policy and an arbitrary target policy, which is a scalable, high-level optimization objective suitable for modeling generic ranking relationships. Leveraging the POLAR pre-training paradigm, we present a series of RMs with parameter scales from 1.8B to 7B. Empirical results show that POLAR substantially outperforms traditional non-pre-trained methods, significantly enhancing RM performance. For instance, POLAR-7B could improve preference accuracy from 54.8% to 81.0% on STEM tasks and from 57.9% to 85.5% on creative writing tasks compared to SOTA baselines. POLAR also shows robust generalization capabilities in RLHF using Reinforcement Fine-tuning (RFT), providing reliable reward signals and markedly enhancing policy performance--improving LLaMa3.1-8B from an average of 47.36% to 56.33% and Qwen2.5-32B from 64.49% to 70.47% on 20 benchmarks. Moreover, scaling experiments reveal a clear power-law relationship between computation and performance, supported by linear correlation coefficients approaching 0.99. The impressive performance, strong generalization, and scaling properties suggest that POLAR is a promising direction for developing general and strong reward models.</p> - https://arxiv.org/abs/2507.05197 - Mon, 07 Jul 2025 16:56:31 +0000 + SONAR-LLM: Autoregressive Transformer that Thinks in Sentence Embeddings and Speaks in Tokens + https://arxiv.org/abs/2508.05305 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.05305.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Nikita Dragunov, Temurbek Rahmatullaev, Elizaveta Goncharova, Andrey Kuznetsov, Anton Razzhigaev</p><p><b>Upvotes:</b> 45</p><p><b>Summary:</b> The recently proposed Large Concept Model (LCM) generates text by predicting a sequence of sentence-level embeddings and training with either mean-squared error or diffusion objectives. We present SONAR-LLM, a decoder-only transformer that "thinks" in the same continuous SONAR embedding space, yet is supervised through token-level cross-entropy propagated via the frozen SONAR decoder. This hybrid objective retains the semantic abstraction of LCM while eliminating its diffusion sampler and restoring a likelihood-based training signal. Across model sizes from 39M to 1.3B parameters, SONAR-LLM attains competitive generation quality. We report scaling trends, ablations, benchmark results, and release the complete training code and all pretrained checkpoints to foster reproducibility and future research.</p> + https://arxiv.org/abs/2508.05305 + Thu, 07 Aug 2025 12:03:44 +0000 - Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities - https://arxiv.org/abs/2507.06261 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.06261.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Gheorghe Comanici, Eric Bieber, Mike Schaekermann, Ice Pasupat, Noveen Sachdeva, Inderjit Dhillon, Marcel Blistein, Ori Ram, Dan Zhang, Evan Rosen, Luke Marris, Sam Petulla, Colin Gaffney, Asaf Aharoni, Nathan Lintz, Tiago Cardal Pais, Henrik Jacobsson, Idan Szpektor, Nan-Jiang Jiang, Krishna Haridasan, Ahmed Omran, Nikunj Saunshi, Dara Bahri, Gaurav Mishra, Eric Chu, Toby Boyd, Brad Hekman, Aaron Parisi, Chaoyi Zhang, Kornraphop Kawintiranon, Tania Bedrax-Weiss, Oliver Wang, Ya Xu, Ollie Purkiss, Uri Mendlovic, Ilaï Deutel, Nam Nguyen, Adam Langley, Flip Korn, Lucia Rossazza, Alexandre Ramé, Sagar Waghmare, Helen Miller, Vaishakh Keshava, Ying Jian, Xiaofan Zhang, Raluca Ada Popa, Kedar Dhamdhere, Blaž Bratanič, Kyuyeun Kim, Terry Koo, Ferran Alet, Yi-ting Chen, Arsha Nagrani, Hannah Muckenhirn, Zhiyuan Zhang, Corbin Quick, Filip Pavetić, Duc Dung Nguyen, Joao Carreira, Michael Elabd, Haroon Qureshi, Fabian Mentzer, Yao-Yuan Yang, Danielle Eisenbud, Anmol Gulati, Ellie Talius, Eric Ni, Sahra Ghalebikesabi, Edouard Yvinec, Alaa Saade, Thatcher Ulrich, Lorenzo Blanco, Dan A. Calian, Muhuan Huang, Aäron van den Oord, Naman Goyal, Terry Chen, Praynaa Rawlani, Christian Schallhart, Swachhand Lokhande, Xianghong Luo, Jyn Shan, Ceslee Montgomery, Victoria Krakovna, Federico Piccinini, Omer Barak, Jingyu Cui, Yiling Jia, Mikhail Dektiarev, Alexey Kolganov, Shiyu Huang, Zhe Chen, Xingyu Wang, Jessica Austin, Peter de Boursac, Evgeny Sluzhaev, Frank Ding, Huijian Li, Surya Bhupatiraju, Mohit Agarwal, Sławek Kwasiborski, Paramjit Sandhu, Patrick Siegler, Ahmet Iscen, Eyal Ben-David, Shiraz Butt, Miltos Allamanis, Seth Benjamin, Robert Busa-Fekete, Felix Hernandez-Campos, Sasha Goldshtein, Matt Dibb, Weiyang Zhang, Annie Marsden, Carey Radebaugh, Stephen Roller, Abhishek Nayyar, Jacob Austin, Tayfun Terzi, Bhargav Kanagal Shamanna, Pete Shaw, Aayush Singh, Florian Luisier, Artur Mendonça, Vaibhav Aggarwal, Larisa Markeeva, Claudio Fantacci, Sergey Brin, HyunJeong Choe, Guanyu Wang, Hartwig Adam, Avigail Dabush, Tatsuya Kiyono, Eyal Marcus, Jeremy Cole, Theophane Weber, Hongrae Lee, Ronny Huang, Alex Muzio, Leandro Kieliger, Maigo Le, Courtney Biles, Long Le, Archit Sharma, Chengrun Yang, Avery Lamp, Dave Dopson, Nate Hurley, Katrina, Xu, Zhihao Shan, Shuang Song, Jiewen Tan, Alexandre Senges, George Zhang, Chong You, Yennie Jun, David Raposo, Susanna Ricco, Xuan Yang, Weijie Chen, Prakhar Gupta, Arthur Szlam, Kevin Villela, Chun-Sung Ferng, Daniel Kasenberg, Chen Liang, Rui Zhu, Arunachalam Narayanaswamy, Florence Perot, Paul Pucciarelli, Anna Shekhawat, Alexey Stern, Rishikesh Ingale, Stefani Karp, Sanaz Bahargam, Adrian Goedeckemeyer, Jie Han, Sicheng Li, Andrea Tacchetti, Dian Yu, Abhishek Chakladar, Zhiying Zhang, Mona El Mahdy, Xu Gao, Dale Johnson, Samrat Phatale, AJ Piergiovanni, Hyeontaek Lim, Clement Farabet, Carl Lebsack, Theo Guidroz, John Blitzer, Nico Duduta, David Madras, Steve Li, Daniel von Dincklage, Xin Li, Mahdis Mahdieh, George Tucker, Ganesh Jawahar, Owen Xiao, Danny Tarlow, Robert Geirhos, Noam Velan, Daniel Vlasic, Kalesha Bullard, SK Park, Nishesh Gupta, Kellie Webster, Ayal Hitron, Jieming Mao, Julian Eisenschlos, Laurel Prince, Nina D'Souza, Kelvin Zheng, Sara Nasso, Gabriela Botea, Carl Doersch, Caglar Unlu, Chris Alberti, Alexey Svyatkovskiy, Ankita Goel, Krzysztof Choromanski, Pan-Pan Jiang, Richard Nguyen, Four Flynn, Daria Ćurko, Peter Chen, Nicholas Roth, Kieran Milan, Caleb Habtegebriel, Shashi Narayan, Michael Moffitt, Jake Marcus, Thomas Anthony, Brendan McMahan, Gowoon Cheon, Ruibo Liu, Megan Barnes, Lukasz Lew, Rebeca Santamaria-Fernandez, Mayank Upadhyay, Arjun Akula, Arnar Mar Hrafnkelsson, Alvaro Caceres, Andrew Bunner, Michal Sokolik, Subha Puttagunta, Lawrence Moore, Berivan Isik, Weilun Chen, Jay Hartford, Lawrence Chan, Pradeep Shenoy, Dan Holtmann-Rice, Jane Park, Fabio Viola, Alex Salcianu, Sujeevan Rajayogam, Ian Stewart-Binks, Zelin Wu, Richard Everett, Xi Xiong, Pierre-Antoine Manzagol, Gary Leung, Carl Saroufim, Bo Pang, Dawid Wegner, George Papamakarios, Jennimaria Palomaki, Helena Pankov, Guangda Lai, Guilherme Tubone, Shubin Zhao, Theofilos Strinopoulos, Seth Neel, Mingqiu Wang, Joe Kelley, Li Li, Pingmei Xu, Anitha Vijayakumar, Andrea D'olimpio, Omer Levy, Massimo Nicosia, Grigory Rozhdestvenskiy, Ni Lao, Sirui Xie, Yash Katariya, Jon Simon, Sanjiv Kumar, Florian Hartmann, Michael Kilgore, Jinhyuk Lee, Aroma Mahendru, Roman Ring, Tom Hennigan, Fiona Lang, Colin Cherry, David Steiner, Dawsen Hwang, Ray Smith, Pidong Wang, Jeremy Chen, Ming-Hsuan Yang, Sam Kwei, Philippe Schlattner, Donnie Kim, Ganesh Poomal Girirajan, Nikola Momchev, Ayushi Agarwal, Xingyi Zhou, Ilkin Safarli, Zachary Garrett, AJ Pierigiovanni, Sarthak Jauhari, Alif Raditya Rochman, Shikhar Vashishth, Quan Yuan, Christof Angermueller, Jon Blanton, Xinying Song, Nitesh Bharadwaj Gundavarapu, Thi Avrahami, Maxine Deines, Subhrajit Roy, Manish Gupta, Christopher Semturs, Shobha Vasudevan, Aditya Srikanth Veerubhotla, Shriya Sharma, Josh Jacob, Zhen Yang, Andreas Terzis, Dan Karliner, Auriel Wright, Tania Rojas-Esponda, Ashley Brown, Abhijit Guha Roy, Pawan Dogra, Andrei Kapishnikov, Peter Young, Wendy Kan, Vinodh Kumar Rajendran, Maria Ivanova, Salil Deshmukh, Chia-Hua Ho, Mike Kwong, Stav Ginzburg, Annie Louis, KP Sawhney, Slav Petrov, Jing Xie, Yunfei Bai, Georgi Stoyanov, Alex Fabrikant, Rajesh Jayaram, Yuqi Li, Joe Heyward, Justin Gilmer, Yaqing Wang, Radu Soricut, Luyang Liu, Qingnan Duan, Jamie Hayes, Maura O'Brien, Gaurav Singh Tomar, Sivan Eiger, Bahar Fatemi, Jeffrey Hui, Catarina Barros, Adaeze Chukwuka, Alena Butryna, Saksham Thakur, Austin Huang, Zhufeng Pan, Haotian Tang, Serkan Cabi, Tulsee Doshi, Michiel Bakker, Sumit Bagri, Ruy Ley-Wild, Adam Lelkes, Jennie Lees, Patrick Kane, David Greene, Shimu Wu, Jörg Bornschein, Gabriela Surita, Sarah Hodkinson, Fangtao Li, Chris Hidey, Sébastien Pereira, Sean Ammirati, Phillip Lippe, Adam Kraft, Pu Han, Sebastian Gerlach, Zifeng Wang, Liviu Panait, Feng Han, Brian Farris, Yingying Bi, Hannah DeBalsi, Miaosen Wang, Gladys Tyen, James Cohan, Susan Zhang, Jarred Barber, Da-Woon Chung, Jaeyoun Kim, Markus Kunesch, Steven Pecht, Nami Akazawa, Abe Friesen, James Lyon, Ali Eslami, Junru Wu, Jie Tan, Yue Song, Ravi Kumar, Chris Welty, Ilia Akolzin, Gena Gibson, Sean Augenstein, Arjun Pillai, Nancy Yuen, Du Phan, Xin Wang, Iain Barr, Heiga Zen, Nan Hua, Casper Liu, Jilei, Wang, Tanuj Bhatia, Hao Xu, Oded Elyada, Pushmeet Kohli, Mirek Olšák, Ke Chen, Azalia Mirhoseini, Noam Shazeer, Shoshana Jakobovits, Maggie Tran, Nolan Ramsden, Tarun Bharti, Fred Alcober, Yunjie Li, Shilpa Shetty, Jing Chen, Dmitry Kalashnikov, Megha Nawhal, Sercan Arik, Hanwen Chen, Michiel Blokzijl, Shubham Gupta, James Rubin, Rigel Swavely, Sophie Bridgers, Ian Gemp, Chen Su, Arun Suggala, Juliette Pluto, Mary Cassin, Alain Vaucher, Kaiyang Ji, Jiahao Cai, Andrew Audibert, Animesh Sinha, David Tian, Efrat Farkash, Amy Hua, Jilin Chen, Duc-Hieu Tran, Edward Loper, Nicole Brichtova, Lara McConnaughey, Ballie Sandhu, Robert Leland, Doug DeCarlo, Andrew Over, James Huang, Xing Wu, Connie Fan, Eric Li, Yun Lei, Deepak Sharma, Cosmin Paduraru, Luo Yu, Matko Bošnjak, Phuong Dao, Min Choi, Sneha Kudugunta, Jakub Adamek, Carlos Guía, Ali Khodaei, Jie Feng, Wenjun Zeng, David Welling, Sandeep Tata, Christina Butterfield, Andrey Vlasov, Seliem El-Sayed, Swaroop Mishra, Tara Sainath, Shentao Yang, RJ Skerry-Ryan, Jeremy Shar, Robert Berry, Arunkumar Rajendran, Arun Kandoor, Andrea Burns, Deepali Jain, Tom Stone, Wonpyo Park, Shibo Wang, Albin Cassirer, Guohui Wang, Hayato Kobayashi, Sergey Rogulenko, Vineetha Govindaraj, Mikołaj Rybiński, Nadav Olmert, Colin Evans, Po-Sen Huang, Kelvin Xu, Premal Shah, Terry Thurk, Caitlin Sikora, Mu Cai, Jin Xie, Elahe Dabir, Saloni Shah, Norbert Kalb, Carrie Zhang, Shruthi Prabhakara, Amit Sabne, Artiom Myaskovsky, Vikas Raunak, Blanca Huergo, Behnam Neyshabur, Jon Clark, Ye Zhang, Shankar Krishnan, Eden Cohen, Dinesh Tewari, James Lottes, Yumeya Yamamori, Hui, Li, Mohamed Elhawaty, Ada Maksutaj Oflazer, Adrià Recasens, Sheryl Luo, Duy Nguyen, Taylor Bos, Kalyan Andra, Ana Salazar, Ed Chi, Jeongwoo Ko, Matt Ginsberg, Anders Andreassen, Anian Ruoss, Todor Davchev, Elnaz Davoodi, Chenxi Liu, Min Kim, Santiago Ontanon, Chi Ming To, Dawei Jia, Rosemary Ke, Jing Wang, Anna Korsun, Moran Ambar, Ilya Kornakov, Irene Giannoumis, Toni Creswell, Denny Zhou, Yi Su, Ishaan Watts, Aleksandr Zaks, Evgenii Eltyshev, Ziqiang Feng, Sidharth Mudgal, Alex Kaskasoli, Juliette Love, Kingshuk Dasgupta, Sam Shleifer, Richard Green, Sungyong Seo, Chansoo Lee, Dale Webster, Prakash Shroff, Ganna Raboshchuk, Isabel Leal, James Manyika, Sofia Erell, Daniel Murphy, Zhisheng Xiao, Anton Bulyenov, Julian Walker, Mark Collier, Matej Kastelic, Nelson George, Sushant Prakash, Sailesh Sidhwani, Alexey Frolov, Steven Hansen, Petko Georgiev, Tiberiu Sosea, Chris Apps, Aishwarya Kamath, David Reid, Emma Cooney, Charlotte Magister, Oriana Riva, Alec Go, Pu-Chin Chen, Sebastian Krause, Nir Levine, Marco Fornoni, Ilya Figotin, Nick Roy, Parsa Mahmoudieh, Vladimir Magay, Mukundan Madhavan, Jin Miao, Jianmo Ni, Yasuhisa Fujii, Ian Chou, George Scrivener, Zak Tsai, Siobhan Mcloughlin, Jeremy Selier, Sandra Lefdal, Jeffrey Zhao, Abhijit Karmarkar, Kushal Chauhan, Shivanker Goel, Zhaoyi Zhang, Vihan Jain, Parisa Haghani, Mostafa Dehghani, Jacob Scott, Erin Farnese, Anastasija Ilić, Steven Baker, Julia Pawar, Li Zhong, Josh Camp, Yoel Zeldes, Shravya Shetty, Anand Iyer, Vít Listík, Jiaxian Guo, Luming Tang, Mark Geller, Simon Bucher, Yifan Ding, Hongzhi Shi, Carrie Muir, Dominik Grewe, Ramy Eskander, Octavio Ponce, Boqing Gong, Derek Gasaway, Samira Khan, Umang Gupta, Angelos Filos, Weicheng Kuo, Klemen Kloboves, Jennifer Beattie, Christian Wright, Leon Li, Alicia Jin, Sandeep Mariserla, Miteyan Patel, Jens Heitkaemper, Dilip Krishnan, Vivek Sharma, David Bieber, Christian Frank, John Lambert, Paul Caron, Martin Polacek, Mai Giménez, Himadri Choudhury, Xing Yu, Sasan Tavakkol, Arun Ahuja, Franz Och, Rodolphe Jenatton, Wojtek Skut, Bryan Richter, David Gaddy, Andy Ly, Misha Bilenko, Megh Umekar, Ethan Liang, Martin Sevenich, Mandar Joshi, Hassan Mansoor, Rebecca Lin, Sumit Sanghai, Abhimanyu Singh, Xiaowei Li, Sudheendra Vijayanarasimhan, Zaheer Abbas, Yonatan Bitton, Hansa Srinivasan, Manish Reddy Vuyyuru, Alexander Frömmgen, Yanhua Sun, Ralph Leith, Alfonso Castaño, DJ Strouse, Le Yan, Austin Kyker, Satish Kambala, Mary Jasarevic, Thibault Sellam, Chao Jia, Alexander Pritzel, Raghavender R, Huizhong Chen, Natalie Clay, Sudeep Gandhe, Sean Kirmani, Sayna Ebrahimi, Hannah Kirkwood, Jonathan Mallinson, Chao Wang, Adnan Ozturel, Kuo Lin, Shyam Upadhyay, Vincent Cohen-Addad, Sean Purser-haskell, Yichong Xu, Ebrahim Songhori, Babi Seal, Alberto Magni, Almog Gueta, Tingting Zou, Guru Guruganesh, Thais Kagohara, Hung Nguyen, Khalid Salama, Alejandro Cruzado Ruiz, Justin Frye, Zhenkai Zhu, Matthias Lochbrunner, Simon Osindero, Wentao Yuan, Lisa Lee, Aman Prasad, Lam Nguyen Thiet, Daniele Calandriello, Victor Stone, Qixuan Feng, Han Ke, Maria Voitovich, Geta Sampemane, Lewis Chiang, Ling Wu, Alexander Bykovsky, Matt Young, Luke Vilnis, Ishita Dasgupta, Aditya Chawla, Qin Cao, Bowen Liang, Daniel Toyama, Szabolcs Payrits, Anca Stefanoiu, Dimitrios Vytiniotis, Ankesh Anand, Tianxiao Shen, Blagoj Mitrevski, Michael Tschannen, Sreenivas Gollapudi, Aishwarya P S, José Leal, Zhe Shen, Han Fu, Wei Wang, Arvind Kannan, Doron Kukliansky, Sergey Yaroshenko, Svetlana Grant, Umesh Telang, David Wood, Alexandra Chronopoulou, Alexandru Ţifrea, Tao Zhou, Tony, Nguy\~ên, Muge Ersoy, Anima Singh, Meiyan Xie, Emanuel Taropa, Woohyun Han, Eirikur Agustsson, Andrei Sozanschi, Hui Peng, Alex Chen, Yoel Drori, Efren Robles, Yang Gao, Xerxes Dotiwalla, Ying Chen, Anudhyan Boral, Alexei Bendebury, John Nham, Chris Tar, Luis Castro, Jiepu Jiang, Canoee Liu, Felix Halim, Jinoo Baek, Andy Wan, Jeremiah Liu, Yuan Cao, Shengyang Dai, Trilok Acharya, Ruoxi Sun, Fuzhao Xue, Saket Joshi, Morgane Lustman, Yongqin Xian, Rishabh Joshi, Deep Karkhanis, Nora Kassner, Jamie Hall, Xiangzhuo Ding, Gan Song, Gang Li, Chen Zhu, Yana Kulizhskaya, Bin Ni, Alexey Vlaskin, Solomon Demmessie, Lucio Dery, Salah Zaiem, Yanping Huang, Cindy Fan, Felix Gimeno, Ananth Balashankar, Koji Kojima, Hagai Taitelbaum, Maya Meng, Dero Gharibian, Sahil Singla, Wei Chen, Ambrose Slone, Guanjie Chen, Sujee Rajayogam, Max Schumacher, Suyog Kotecha, Rory Blevins, Qifei Wang, Mor Hazan Taege, Alex Morris, Xin Liu, Fayaz Jamil, Richard Zhang, Pratik Joshi, Ben Ingram, Tyler Liechty, Ahmed Eleryan, Scott Baird, Alex Grills, Gagan Bansal, Shan Han, Kiran Yalasangi, Shawn Xu, Majd Al Merey, Isabel Gao, Felix Weissenberger, Igor Karpov, Robert Riachi, Ankit Anand, Gautam Prasad, Kay Lamerigts, Reid Hayes, Jamie Rogers, Mandy Guo, Ashish Shenoy, Qiong, Hu, Kyle He, Yuchen Liu, Polina Zablotskaia, Sagar Gubbi, Yifan Chang, Jay Pavagadhi, Kristian Kjems, Archita Vadali, Diego Machado, Yeqing Li, Renshen Wang, Dipankar Ghosh, Aahil Mehta, Dana Alon, George Polovets, Alessio Tonioni, Nate Kushman, Joel D'sa, Lin Zhuo, Allen Wu, Rohin Shah, John Youssef, Jiayu Ye, Justin Snyder, Karel Lenc, Senaka Buthpitiya, Matthew Tung, Jichuan Chang, Tao Chen, David Saxton, Jenny Lee, Lydia Lihui Zhang, James Qin, Prabakar Radhakrishnan, Maxwell Chen, Piotr Ambroszczyk, Metin Toksoz-Exley, Yan Zhong, Nitzan Katz, Brendan O'Donoghue, Tamara von Glehn, Adi Gerzi Rosenthal, Aga Świetlik, Xiaokai Zhao, Nick Fernando, Jinliang Wei, Jieru Mei, Sergei Vassilvitskii, Diego Cedillo, Pranjal Awasthi, Hui Zheng, Koray Kavukcuoglu, Itay Laish, Joseph Pagadora, Marc Brockschmidt, Christopher A. Choquette-Choo, Arunkumar Byravan, Yifeng Lu, Xu Chen, Mia Chen, Kenton Lee, Rama Pasumarthi, Sijal Bhatnagar, Aditya Shah, Qiyin Wu, Zhuoyuan Chen, Zack Nado, Bartek Perz, Zixuan Jiang, David Kao, Ganesh Mallya, Nino Vieillard, Lantao Mei, Sertan Girgin, Mandy Jordan, Yeongil Ko, Alekh Agarwal, Yaxin Liu, Yasemin Altun, Raoul de Liedekerke, Anastasios Kementsietsidis, Daiyi Peng, Dangyi Liu, Utku Evci, Peter Humphreys, Austin Tarango, Xiang Deng, Yoad Lewenberg, Kevin Aydin, Chengda Wu, Bhavishya Mittal, Tsendsuren Munkhdalai, Kleopatra Chatziprimou, Rodrigo Benenson, Uri First, Xiao Ma, Jinning Li, Armand Joulin, Hamish Tomlinson, Tingnan Zhang, Milad Nasr, Zhi Hong, Michaël Sander, Lisa Anne Hendricks, Anuj Sharma, Andrew Bolt, Eszter Vértes, Jiri Simsa, Tomer Levinboim, Olcan Sercinoglu, Divyansh Shukla, Austin Wu, Craig Swanson, Danny Vainstein, Fan Bu, Bo Wang, Ryan Julian, Charles Yoon, Sergei Lebedev, Antonious Girgis, Bernd Bandemer, David Du, Todd Wang, Xi Chen, Ying Xiao, Peggy Lu, Natalie Ha, Vlad Ionescu, Simon Rowe, Josip Matak, Federico Lebron, Andreas Steiner, Lalit Jain, Manaal Faruqui, Nicolas Lacasse, Georgie Evans, Neesha Subramaniam, Dean Reich, Giulia Vezzani, Aditya Pandey, Joe Stanton, Tianhao Zhou, Liam McCafferty, Henry Griffiths, Verena Rieser, Soheil Hassas Yeganeh, Eleftheria Briakou, Lu Huang, Zichuan Wei, Liangchen Luo, Erik Jue, Gabby Wang, Victor Cotruta, Myriam Khan, Jongbin Park, Qiuchen Guo, Peiran Li, Rong Rong, Diego Antognini, Anastasia Petrushkina, Chetan Tekur, Eli Collins, Parul Bhatia, Chester Kwak, Wenhu Chen, Arvind Neelakantan, Immanuel Odisho, Sheng Peng, Vincent Nallatamby, Vaibhav Tulsyan, Fabian Pedregosa, Peng Xu, Raymond Lin, Yulong Wang, Emma Wang, Sholto Douglas, Reut Tsarfaty, Elena Gribovskaya, Renga Aravamudhan, Manu Agarwal, Mara Finkelstein, Qiao Zhang, Elizabeth Cole, Phil Crone, Sarmishta Velury, Anil Das, Chris Sauer, Luyao Xu, Danfeng Qin, Chenjie Gu, Dror Marcus, CJ Zheng, Wouter Van Gansbeke, Sobhan Miryoosefi, Haitian Sun, YaGuang Li, Charlie Chen, Jae Yoo, Pavel Dubov, Alex Tomala, Adams Yu, Paweł Wesołowski, Alok Gunjan, Eddie Cao, Jiaming Luo, Nikhil Sethi, Arkadiusz Socala, Laura Graesser, Tomas Kocisky, Arturo BC, Minmin Chen, Edward Lee, Sophie Wang, Weize Kong, Qiantong Xu, Nilesh Tripuraneni, Yiming Li, Xinxin Yu, Allen Porter, Paul Voigtlaender, Biao Zhang, Arpi Vezer, Sarah York, Qing Wei, Geoffrey Cideron, Mark Kurzeja, Seungyeon Kim, Benny Li, Angéline Pouget, Hyo Lee, Kaspar Daugaard, Yang Li, Dave Uthus, Aditya Siddhant, Paul Cavallaro, Sriram Ganapathy, Maulik Shah, Rolf Jagerman, Jeff Stanway, Piermaria Mendolicchio, Li Xiao, Kayi Lee, Tara Thompson, Shubham Milind Phal, Jason Chase, Sun Jae Lee, Adrian N Reyes, Disha Shrivastava, Zhen Qin, Roykrong Sukkerd, Seth Odoom, Lior Madmoni, John Aslanides, Jonathan Herzig, Elena Pochernina, Sheng Zhang, Parker Barnes, Daisuke Ikeda, Qiujia Li, Shuo-yiin Chang, Shakir Mohamed, Jim Sproch, Richard Powell, Bidisha Samanta, Domagoj Ćevid, Anton Kovsharov, Shrestha Basu Mallick, Srinivas Tadepalli, Anne Zheng, Kareem Ayoub, Andreas Noever, Christian Reisswig, Zhuo Xu, Junhyuk Oh, Martin Matysiak, Tim Blyth, Shereen Ashraf, Julien Amelot, Boone Severson, Michele Bevilacqua, Motoki Sano, Ethan Dyer, Ofir Roval, Anu Sinha, Yin Zhong, Sagi Perel, Tea Sabolić, Johannes Mauerer, Willi Gierke, Mauro Verzetti, Rodrigo Cabrera, Alvin Abdagic, Steven Hemingray, Austin Stone, Jong Lee, Farooq Ahmad, Karthik Raman, Lior Shani, Jonathan Lai, Orhan Firat, Nathan Waters, Eric Ge, Mo Shomrat, Himanshu Gupta, Rajeev Aggarwal, Tom Hudson, Bill Jia, Simon Baumgartner, Palak Jain, Joe Kovac, Junehyuk Jung, Ante Žužul, Will Truong, Morteza Zadimoghaddam, Songyou Peng, Marco Liang, Rachel Sterneck, Balaji Lakshminarayanan, Machel Reid, Oliver Woodman, Tong Zhou, Jianling Wang, Vincent Coriou, Arjun Narayanan, Jay Hoover, Yenai Ma, Apoorv Jindal, Clayton Sanford, Doug Reid, Swaroop Ramaswamy, Alex Kurakin, Roland Zimmermann, Yana Lunts, Dragos Dena, Zalán Borsos, Vered Cohen, Shujian Zhang, Will Grathwohl, Robert Dadashi, Morgan Redshaw, Joshua Kessinger, Julian Odell, Silvano Bonacina, Zihang Dai, Grace Chen, Ayush Dubey, Pablo Sprechmann, Mantas Pajarskas, Wenxuan Zhou, Niharika Ahuja, Tara Thomas, Martin Nikoltchev, Matija Kecman, Bharath Mankalale, Andrey Ryabtsev, Jennifer She, Christian Walder, Jiaming Shen, Lu Li, Carolina Parada, Sheena Panthaplackel, Okwan Kwon, Matt Lawlor, Utsav Prabhu, Yannick Schroecker, Marc'aurelio Ranzato, Pete Blois, Iurii Kemaev, Ting Yu, Dmitry, Lepikhin, Hao Xiong, Sahand Sharifzadeh, Oleaser Johnson, Jeremiah Willcock, Rui Yao, Greg Farquhar, Sujoy Basu, Hidetoshi Shimokawa, Nina Anderson, Haiguang Li, Khiem Pham, Yizhong Liang, Sebastian Borgeaud, Alexandre Moufarek, Hideto Kazawa, Blair Kutzman, Marcin Sieniek, Sara Smoot, Ruth Wang, Natalie Axelsson, Nova Fallen, Prasha Sundaram, Yuexiang Zhai, Varun Godbole, Petros Maniatis, Alek Wang, Ilia Shumailov, Santhosh Thangaraj, Remi Crocker, Nikita Gupta, Gang Wu, Phil Chen, Gellért Weisz, Celine Smith, Mojtaba Seyedhosseini, Boya Fang, Xiyang Luo, Roey Yogev, Zeynep Cankara, Andrew Hard, Helen Ran, Rahul Sukthankar, George Necula, Gaël Liu, Honglong Cai, Praseem Banzal, Daniel Keysers, Sanjay Ghemawat, Connie Tao, Emma Dunleavy, Aditi Chaudhary, Wei Li, Maciej Mikuła, Chen-Yu Lee, Tiziana Refice, Krishna Somandepalli, Alexandre Fréchette, Dan Bahir, John Karro, Keith Rush, Sarah Perrin, Bill Rosgen, Xiaomeng Yang, Clara Huiyi Hu, Mahmoud Alnahlawi, Justin Mao-Jones, Roopal Garg, Hoang Nguyen, Bat-Orgil Batsaikhan, Iñaki Iturrate, Anselm Levskaya, Avi Singh, Ashyana Kachra, Tony Lu, Denis Petek, Zheng Xu, Mark Graham, Lukas Zilka, Yael Karov, Marija Kostelac, Fangyu Liu, Yaohui Guo, Weiyue Wang, Bernd Bohnet, Emily Pitler, Tony Bruguier, Keisuke Kinoshita, Chrysovalantis Anastasiou, Nilpa Jha, Ting Liu, Jerome Connor, Phil Wallis, Philip Pham, Eric Bailey, Shixin Li, Heng-Tze Cheng, Sally Ma, Haiqiong Li, Akanksha Maurya, Kate Olszewska, Manfred Warmuth, Christy Koh, Dominik Paulus, Siddhartha Reddy Jonnalagadda, Enrique Piqueras, Ali Elqursh, Geoff Brown, Hadar Shemtov, Loren Maggiore, Fei Xia, Ryan Foley, Beka Westberg, George van den Driessche, Livio Baldini Soares, Arjun Kar, Michael Quinn, Siqi Zuo, Jialin Wu, Kyle Kastner, Anna Bortsova, Aijun Bai, Ales Mikhalap, Luowei Zhou, Jennifer Brennan, Vinay Ramasesh, Honglei Zhuang, John Maggs, Johan Schalkwyk, Yuntao Xu, Hui Huang, Andrew Howard, Sasha Brown, Linting Xue, Gloria Shen, Brian Albert, Neha Jha, Daniel Zheng, Varvara Krayvanova, Spurthi Amba Hombaiah, Olivier Lacombe, Gautam Vasudevan, Dan Graur, Tian Xie, Meet Gandhi, Bangju Wang, Dustin Zelle, Harman Singh, Dahun Kim, Sébastien Cevey, Victor Ungureanu, Natasha Noy, Fei Liu, Annie Xie, Fangxiaoyu Feng, Katerina Tsihlas, Daniel Formoso, Neera Vats, Quentin Wellens, Yinan Wang, Niket Kumar Bhumihar, Samrat Ghosh, Matt Hoffman, Tom Lieber, Oran Lang, Kush Bhatia, Tom Paine, Aroonalok Pyne, Ronny Votel, Madeleine Clare Elish, Benoit Schillings, Alex Panagopoulos, Haichuan Yang, Adam Raveret, Zohar Yahav, Shuang Liu, Warren Chen, Dalia El Badawy, Nishant Agrawal, Mohammed Badawi, Mahdi Mirzazadeh, Carla Bromberg, Fan Ye, Chang Liu, Tatiana Sholokhova, George-Cristian Muraru, Gargi Balasubramaniam, Jonathan Malmaud, Alen Carin, Danilo Martins, Irina Jurenka, Pankil Botadra, Dave Lacey, Richa Singh, Mariano Schain, Dan Zheng, Isabelle Guyon, Victor Lavrenko, Seungji Lee, Xiang Zhou, Demis Hassabis, Jeshwanth Challagundla, Derek Cheng, Nikhil Mehta, Matthew Mauger, Michela Paganini, Pushkar Mishra, Kate Lee, Zhang Li, Lexi Baugher, Ondrej Skopek, Max Chang, Amir Zait, Gaurav Menghani, Lizzetth Bellot, Guangxing Han, Jean-Michel Sarr, Sharat Chikkerur, Himanshu Sahni, Rohan Anil, Arun Narayanan, Chandu Thekkath, Daniele Pighin, Hana Strejček, Marko Velic, Fred Bertsch, Manuel Tragut, Keran Rong, Alicia Parrish, Kai Bailey, Jiho Park, Isabela Albuquerque, Abhishek Bapna, Rajesh Venkataraman, Alec Kosik, Johannes Griesser, Zhiwei Deng, Alek Andreev, Qingyun Dou, Kevin Hui, Fanny Wei, Xiaobin Yu, Lei Shu, Avia Aharon, David Barker, Badih Ghazi, Sebastian Flennerhag, Chris Breaux, Yuchuan Liu, Matthew Bilotti, Josh Woodward, Uri Alon, Stephanie Winkler, Tzu-Kuo Huang, Kostas Andriopoulos, João Gabriel Oliveira, Penporn Koanantakool, Berkin Akin, Michael Wunder, Cicero Nogueira dos Santos, Mohammad Hossein Bateni, Lin Yang, Dan Horgan, Beer Changpinyo, Keyvan Amiri, Min Ma, Dayeong Lee, Lihao Liang, Anirudh Baddepudi, Tejasi Latkar, Raia Hadsell, Jun Xu, Hairong Mu, Michael Han, Aedan Pope, Snchit Grover, Frank Kim, Ankit Bhagatwala, Guan Sun, Yamini Bansal, Amir Globerson, Alireza Nazari, Samira Daruki, Hagen Soltau, Jane Labanowski, Laurent El Shafey, Matt Harvey, Yanif Ahmad, Elan Rosenfeld, William Kong, Etienne Pot, Yi-Xuan Tan, Aurora Wei, Victoria Langston, Marcel Prasetya, Petar Veličković, Richard Killam, Robin Strudel, Darren Ni, Zhenhai Zhu, Aaron Archer, Kavya Kopparapu, Lynn Nguyen, Emilio Parisotto, Hussain Masoom, Sravanti Addepalli, Jordan Grimstad, Hexiang Hu, Joss Moore, Avinatan Hassidim, Le Hou, Mukund Raghavachari, Jared Lichtarge, Adam R. Brown, Hilal Dib, Natalia Ponomareva, Justin Fu, Yujing Zhang, Altaf Rahman, Joana Iljazi, Edouard Leurent, Gabriel Dulac-Arnold, Cosmo Du, Chulayuth Asawaroengchai, Larry Jin, Ela Gruzewska, Ziwei Ji, Benigno Uria, Daniel De Freitas, Paul Barham, Lauren Beltrone, Víctor Campos, Jun Yan, Neel Kovelamudi, Arthur Nguyen, Elinor Davies, Zhichun Wu, Zoltan Egyed, Kristina Toutanova, Nithya Attaluri, Hongliang Fei, Peter Stys, Siddhartha Brahma, Martin Izzard, Siva Velusamy, Scott Lundberg, Vincent Zhuang, Kevin Sequeira, Adam Santoro, Ehsan Amid, Ophir Aharoni, Shuai Ye, Mukund Sundararajan, Lijun Yu, Yu-Cheng Ling, Stephen Spencer, Hugo Song, Josip Djolonga, Christo Kirov, Sonal Gupta, Alessandro Bissacco, Clemens Meyer, Mukul Bhutani, Andrew Dai, Weiyi Wang, Siqi Liu, Ashwin Sreevatsa, Qijun Tan, Maria Wang, Lucy Kim, Yicheng Wang, Alex Irpan, Yang Xiao, Stanislav Fort, Yifan He, Alex Gurney, Bryan Gale, Yue Ma, Monica Roy, Viorica Patraucean, Taylan Bilal, Golnaz Ghiasi, Anahita Hosseini, Melvin Johnson, Zhuowan Li, Yi Tay, Benjamin Beyret, Katie Millican, Josef Broder, Mayank Lunayach, Danny Swisher, Eugen Vušak, David Parkinson, MH Tessler, Adi Mayrav Gilady, Richard Song, Allan Dafoe, Yves Raimond, Masa Yamaguchi, Itay Karo, Elizabeth Nielsen, Kevin Kilgour, Mike Dusenberry, Rajiv Mathews, Jiho Choi, Siyuan Qiao, Harsh Mehta, Sahitya Potluri, Chris Knutsen, Jialu Liu, Tat Tan, Kuntal Sengupta, Keerthana Gopalakrishnan, Abodunrinwa Toki, Mencher Chiang, Mike Burrows, Grace Vesom, Zafarali Ahmed, Ilia Labzovsky, Siddharth Vashishtha, Preeti Singh, Ankur Sharma, Ada Ma, Jinyu Xie, Pranav Talluri, Hannah Forbes-Pollard, Aarush Selvan, Joel Wee, Loic Matthey, Tom Funkhouser, Parthasarathy Gopavarapu, Lev Proleev, Cheng Li, Matt Thomas, Kashyap Kolipaka, Zhipeng Jia, Ashwin Kakarla, Srinivas Sunkara, Joan Puigcerver, Suraj Satishkumar Sheth, Emily Graves, Chen Wang, Sadh MNM Khan, Kai Kang, Shyamal Buch, Fred Zhang, Omkar Savant, David Soergel, Kevin Lee, Linda Friso, Xuanyi Dong, Rahul Arya, Shreyas Chandrakaladharan, Connor Schenck, Greg Billock, Tejas Iyer, Anton Bakalov, Leslie Baker, Alex Ruiz, Angad Chandorkar, Trieu Trinh, Matt Miecnikowski, Yanqi Zhou, Yangsibo Huang, Jiazhong Nie, Ali Shah, Ashish Thapliyal, Sam Haves, Lun Wang, Uri Shaham, Patrick Morris-Suzuki, Soroush Radpour, Leonard Berrada, Thomas Strohmann, Chaochao Yan, Jingwei Shen, Sonam Goenka, Tris Warkentin, Petar Dević, Dan Belov, Albert Webson, Madhavi Yenugula, Puranjay Datta, Jerry Chang, Nimesh Ghelani, Aviral Kumar, Vincent Perot, Jessica Lo, Yang Song, Herman Schmit, Jianmin Chen, Vasilisa Bashlovkina, Xiaoyue Pan, Diana Mincu, Paul Roit, Isabel Edkins, Andy Davis, Yujia Li, Ben Horn, Xinjian Li, Pradeep Kumar S, Eric Doi, Wanzheng Zhu, Sri Gayatri Sundara Padmanabhan, Siddharth Verma, Jasmine Liu, Heng Chen, Mihajlo Velimirović, Malcolm Reynolds, Priyanka Agrawal, Nick Sukhanov, Abhinit Modi, Siddharth Goyal, John Palowitch, Nima Khajehnouri, Wing Lowe, David Klinghoffer, Sharon Silver, Vinh Tran, Candice Schumann, Francesco Piccinno, Xi Liu, Mario Lučić, Xiaochen Yang, Sandeep Kumar, Ajay Kannan, Ragha Kotikalapudi, Mudit Bansal, Fabian Fuchs, Javad Hosseini, Abdelrahman Abdelhamed, Dawn Bloxwich, Tianhe Yu, Ruoxin Sang, Gregory Thornton, Karan Gill, Yuchi Liu, Virat Shejwalkar, Jason Lin, Zhipeng Yan, Kehang Han, Thomas Buschmann, Michael Pliskin, Zhi Xing, Susheel Tatineni, Junlin Zhang, Sissie Hsiao, Gavin Buttimore, Marcus Wu, Zefei Li, Geza Kovacs, Legg Yeung, Tao Huang, Aaron Cohen, Bethanie Brownfield, Averi Nowak, Mikel Rodriguez, Tianze Shi, Hado van Hasselt, Kevin Cen, Deepanway Ghoshal, Kushal Majmundar, Weiren Yu, Warren, Chen, Danila Sinopalnikov, Hao Zhang, Vlado Galić, Di Lu, Zeyu Zheng, Maggie Song, Gary Wang, Gui Citovsky, Swapnil Gawde, Isaac Galatzer-Levy, David Silver, Ivana Balazevic, Dipanjan Das, Kingshuk Majumder, Yale Cong, Praneet Dutta, Dustin Tran, Hui Wan, Junwei Yuan, Daniel Eppens, Alanna Walton, Been Kim, Harry Ragan, James Cobon-Kerr, Lu Liu, Weijun Wang, Bryce Petrini, Jack Rae, Rakesh Shivanna, Yan Xiong, Chace Lee, Pauline Coquinot, Yiming Gu, Lisa Patel, Blake Hechtman, Aviel Boag, Orion Jankowski, Alex Wertheim, Alex Lee, Paul Covington, Hila Noga, Sam Sobell, Shanthal Vasanth, William Bono, Chirag Nagpal, Wei Fan, Xavier Garcia, Kedar Soparkar, Aybuke Turker, Nathan Howard, Sachit Menon, Yuankai Chen, Vikas Verma, Vladimir Pchelin, Harish Rajamani, Valentin Dalibard, Ana Ramalho, Yang Guo, Kartikeya Badola, Seojin Bang, Nathalie Rauschmayr, Julia Proskurnia, Sudeep Dasari, Xinyun Chen, Mikhail Sushkov, Anja Hauth, Pauline Sho, Abhinav Singh, Bilva Chandra, Allie Culp, Max Dylla, Olivier Bachem, James Besley, Heri Zhao, Timothy Lillicrap, Wei Wei, Wael Al Jishi, Ning Niu, Alban Rrustemi, Raphaël Lopez Kaufman, Ryan Poplin, Jewel Zhao, Minh Truong, Shikhar Bharadwaj, Ester Hlavnova, Eli Stickgold, Cordelia Schmid, Georgi Stephanov, Zhaoqi Leng, Frederick Liu, Léonard Hussenot, Shenil Dodhia, Juliana Vicente Franco, Lesley Katzen, Abhanshu Sharma, Sarah Cogan, Zuguang Yang, Aniket Ray, Sergi Caelles, Shen Yan, Ravin Kumar, Daniel Gillick, Renee Wong, Joshua Ainslie, Jonathan Hoech, Séb Arnold, Dan Abolafia, Anca Dragan, Ben Hora, Grace Hu, Alexey Guseynov, Yang Lu, Chas Leichner, Jinmeng Rao, Abhimanyu Goyal, Nagabhushan Baddi, Daniel Hernandez Diaz, Tim McConnell, Max Bain, Jake Abernethy, Qiqi Yan, Rylan Schaeffer, Paul Vicol, Will Thompson, Montse Gonzalez Arenas, Mathias Bellaiche, Pablo Barrio, Stefan Zinke, Riccardo Patana, Pulkit Mehta, JK Kearns, Avraham Ruderman, Scott Pollom, David D'Ambrosio, Cath Hope, Yang Yu, Andrea Gesmundo, Kuang-Huei Lee, Aviv Rosenberg, Yiqian Zhou, Yaoyiran Li, Drew Garmon, Yonghui Wu, Safeen Huda, Gil Fidel, Martin Baeuml, Jian Li, Phoebe Kirk, Rhys May, Tao Tu, Sara Mc Carthy, Toshiyuki Fukuzawa, Miranda Aperghis, Chih-Kuan Yeh, Toshihiro Yoshino, Bo Li, Austin Myers, Kaisheng Yao, Ben Limonchik, Changwan Ryu, Rohun Saxena, Alex Goldin, Ruizhe Zhao, Rocky Rhodes, Tao Zhu, Divya Tyam, Heidi Howard, Nathan Byrd, Hongxu Ma, Yan Wu, Ryan Mullins, Qingze Wang, Aida Amini, Sebastien Baur, Yiran Mao, Subhashini Venugopalan, Will Song, Wen Ding, Paul Collins, Sashank Reddi, Megan Shum, Andrei Rusu, Luisa Zintgraf, Kelvin Chan, Sheela Goenka, Mathieu Blondel, Michael Collins, Renke Pan, Marissa Giustina, Nikolai Chinaev, Christian Schuler, Ce Zheng, Jonas Valfridsson, Alyssa Loo, Alex Yakubovich, Jamie Smith, Tao Jiang, Rich Munoz, Gabriel Barcik, Rishabh Bansal, Mingyao Yang, Yilun Du, Pablo Duque, Mary Phuong, Alexandra Belias, Kunal Lad, Zeyu Liu, Tal Schuster, Karthik Duddu, Jieru Hu, Paige Kunkle, Matthew Watson, Jackson Tolins, Josh Smith, Denis Teplyashin, Garrett Bingham, Marvin Ritter, Marco Andreetto, Divya Pitta, Mohak Patel, Shashank Viswanadha, Trevor Strohman, Catalin Ionescu, Jincheng Luo, Yogesh Kalley, Jeremy Wiesner, Dan Deutsch, Derek Lockhart, Peter Choy, Rumen Dangovski, Chawin Sitawarin, Cat Graves, Tanya Lando, Joost van Amersfoort, Ndidi Elue, Zhouyuan Huo, Pooya Moradi, Jean Tarbouriech, Henryk Michalewski, Wenting Ye, Eunyoung Kim, Alex Druinsky, Florent Altché, Xinyi Chen, Artur Dwornik, Da-Cheng Juan, Rivka Moroshko, Horia Toma, Jarrod Kahn, Hai Qian, Maximilian Sieb, Irene Cai, Roman Goldenberg, Praneeth Netrapalli, Sindhu Raghuram, Yuan Gong, Lijie Fan, Evan Palmer, Yossi Matias, Valentin Gabeur, Shreya Pathak, Tom Ouyang, Don Metzler, Geoff Bacon, Srinivasan Venkatachary, Sridhar Thiagarajan, Alex Cullum, Eran Ofek, Vytenis Sakenas, Mohamed Hammad, Cesar Magalhaes, Mayank Daswani, Oscar Chang, Ashok Popat, Ruichao Li, Komal Jalan, Yanhan Hou, Josh Lipschultz, Antoine He, Wenhao Jia, Pier Giuseppe Sessa, Prateek Kolhar, William Wong, Sumeet Singh, Lukas Haas, Jay Whang, Hanna Klimczak-Plucińska, Georges Rotival, Grace Chung, Yiqing Hua, Anfal Siddiqui, Nicolas Serrano, Dongkai Chen, Billy Porter, Libin Bai, Keshav Shivam, Sho Arora, Partha Talukdar, Tom Cobley, Sangnie Bhardwaj, Evgeny Gladchenko, Simon Green, Kelvin Guu, Felix Fischer, Xiao Wu, Eric Wang, Achintya Singhal, Tatiana Matejovicova, James Martens, Hongji Li, Roma Patel, Elizabeth Kemp, Jiaqi Pan, Lily Wang, Blake JianHang Chen, Jean-Baptiste Alayrac, Navneet Potti, Erika Gemzer, Eugene Ie, Kay McKinney, Takaaki Saeki, Edward Chou, Pascal Lamblin, SQ Mah, Zach Fisher, Martin Chadwick, Jon Stritar, Obaid Sarvana, Andrew Hogue, Artem Shtefan, Hadi Hashemi, Yang Xu, Jindong Gu, Sharad Vikram, Chung-Ching Chang, Sabela Ramos, Logan Kilpatrick, Weijuan Xi, Jenny Brennan, Yinghao Sun, Abhishek Jindal, Ionel Gog, Dawn Chen, Felix Wu, Jason Lee, Sudhindra Kopalle, Srinadh Bhojanapalli, Oriol Vinyals, Natan Potikha, Burcu Karagol Ayan, Yuan Yuan, Michael Riley, Piotr Stanczyk, Sergey Kishchenko, Bing Wang, Dan Garrette, Antoine Yang, Vlad Feinberg, CJ Carey, Javad Azizi, Viral Shah, Erica Moreira, Chongyang Shi, Josh Feldman, Elizabeth Salesky, Thomas Lampe, Aneesh Pappu, Duhyeon Kim, Jonas Adler, Avi Caciularu, Brian Walker, Yunhan Xu, Yochai Blau, Dylan Scandinaro, Terry Huang, Sam El-Husseini, Abhishek Sinha, Lijie Ren, Taylor Tobin, Patrik Sundberg, Tim Sohn, Vikas Yadav, Mimi Ly, Emily Xue, Jing Xiong, Afzal Shama Soudagar, Sneha Mondal, Nikhil Khadke, Qingchun Ren, Ben Vargas, Stan Bileschi, Sarah Chakera, Cindy Wang, Boyu Wang, Yoni Halpern, Joe Jiang, Vikas Sindhwani, Petre Petrov, Pranavaraj Ponnuramu, Sanket Vaibhav Mehta, Yu Watanabe, Betty Chan, Matheus Wisniewski, Trang Pham, Jingwei Zhang, Conglong Li, Dario de Cesare, Art Khurshudov, Alex Vasiloff, Melissa Tan, Zoe Ashwood, Bobak Shahriari, Maryam Majzoubi, Garrett Tanzer, Olga Kozlova, Robin Alazard, James Lee-Thorp, Nguyet Minh Phu, Isaac Tian, Junwhan Ahn, Andy Crawford, Lauren Lax, Yuan, Shangguan, Iftekhar Naim, David Ross, Oleksandr Ferludin, Tongfei Guo, Andrea Banino, Hubert Soyer, Xiaoen Ju, Dominika Rogozińska, Ishaan Malhi, Marcella Valentine, Daniel Balle, Apoorv Kulshreshtha, Maciej Kula, Yiwen Song, Sophia Austin, John Schultz, Roy Hirsch, Arthur Douillard, Apoorv Reddy, Michael Fink, Summer Yue, Khyatti Gupta, Adam Zhang, Norman Rink, Daniel McDuff, Lei Meng, András György, Yasaman Razeghi, Ricky Liang, Kazuki Osawa, Aviel Atias, Matan Eyal, Tyrone Hill, Nikolai Grigorev, Zhengdong Wang, Nitish Kulkarni, Rachel Soh, Ivan Lobov, Zachary Charles, Sid Lall, Kazuma Hashimoto, Ido Kessler, Victor Gomes, Zelda Mariet, Danny Driess, Alessandro Agostini, Canfer Akbulut, Jingcao Hu, Marissa Ikonomidis, Emily Caveness, Kartik Audhkhasi, Saurabh Agrawal, Ioana Bica, Evan Senter, Jayaram Mudigonda, Kelly Chen, Jingchen Ye, Xuanhui Wang, James Svensson, Philipp Fränken, Josh Newlan, Li Lao, Eva Schnider, Sami Alabed, Joseph Kready, Jesse Emond, Afief Halumi, Tim Zaman, Chengxi Ye, Naina Raisinghani, Vilobh Meshram, Bo Chang, Ankit Singh Rawat, Axel Stjerngren, Sergey Levi, Rui Wang, Xiangzhu Long, Mitchelle Rasquinha, Steven Hand, Aditi Mavalankar, Lauren Agubuzu, Sudeshna Roy, Junquan Chen, Jarek Wilkiewicz, Hao Zhou, Michal Jastrzebski, Qiong Hu, Agustin Dal Lago, Ramya Sree Boppana, Wei-Jen Ko, Jennifer Prendki, Yao Su, Zhi Li, Eliza Rutherford, Girish Ramchandra Rao, Ramona Comanescu, Adrià Puigdomènech, Qihang Chen, Dessie Petrova, Christine Chan, Vedrana Milutinovic, Felipe Tiengo Ferreira, Chin-Yi Cheng, Ming Zhang, Tapomay Dey, Sherry Yang, Ramesh Sampath, Quoc Le, Howard Zhou, Chu-Cheng Lin, Hoi Lam, Christine Kaeser-Chen, Kai Hui, Dean Hirsch, Tom Eccles, Basil Mustafa, Shruti Rijhwani, Morgane Rivière, Yuanzhong Xu, Junjie Wang, Xinyang Geng, Xiance Si, Arjun Khare, Cheolmin Kim, Vahab Mirrokni, Kamyu Lee, Khuslen Baatarsukh, Nathaniel Braun, Lisa Wang, Pallavi LV, Richard Tanburn, Yuvein, Zhu, Fangda Li, Setareh Ariafar, Dan Goldberg, Ken Burke, Daniil Mirylenka, Meiqi Guo, Olaf Ronneberger, Hadas Natalie Vogel, Liqun Cheng, Nishita Shetty, Johnson Jia, Thomas Jimma, Corey Fry, Ted Xiao, Martin Sundermeyer, Ryan Burnell, Yannis Assael, Mario Pinto, JD Chen, Rohit Sathyanarayana, Donghyun Cho, Jing Lu, Rishabh Agarwal, Sugato Basu, Lucas Gonzalez, Dhruv Shah, Meng Wei, Dre Mahaarachchi, Rohan Agrawal, Tero Rissa, Yani Donchev, Ramiro Leal-Cavazos, Adrian Hutter, Markus Mircea, Alon Jacovi, Faruk Ahmed, Jiageng Zhang, Shuguang Hu, Bo-Juen Chen, Jonni Kanerva, Guillaume Desjardins, Andrew Lee, Nikos Parotsidis, Asier Mujika, Tobias Weyand, Jasper Snoek, Jo Chick, Kai Chen, Paul Chang, Ethan Mahintorabi, Zi Wang, Tolly Powell, Orgad Keller, Abhirut Gupta, Claire Sha, Kanav Garg, Nicolas Heess, Ágoston Weisz, Cassidy Hardin, Bartek Wydrowski, Ben Coleman, Karina Zainullina, Pankaj Joshi, Alessandro Epasto, Terry Spitz, Binbin Xiong, Kai Zhao, Arseniy Klimovskiy, Ivy Zheng, Johan Ferret, Itay Yona, Waleed Khawaja, Jean-Baptiste Lespiau, Maxim Krikun, Siamak Shakeri, Timothee Cour, Bonnie Li, Igor Krivokon, Dan Suh, Alex Hofer, Jad Al Abdallah, Nikita Putikhin, Oscar Akerlund, Silvio Lattanzi, Anurag Kumar, Shane Settle, Himanshu Srivastava, Folawiyo Campbell-Ajala, Edouard Rosseel, Mihai Dorin Istin, Nishanth Dikkala, Anand Rao, Nick Young, Kate Lin, Dhruva Bhaswar, Yiming Wang, Jaume Sanchez Elias, Kritika Muralidharan, James Keeling, Dayou Du, Siddharth Gopal, Gregory Dibb, Charles Blundell, Manolis Delakis, Jacky Liang, Marco Tulio Ribeiro, Georgi Karadzhov, Guillermo Garrido, Ankur Bapna, Jiawei Cao, Adam Sadovsky, Pouya Tafti, Arthur Guez, Coline Devin, Yixian Di, Jinwei Xing, Chuqiao, Xu, Hanzhao Lin, Chun-Te Chu, Sameera Ponda, Wesley Helmholz, Fan Yang, Yue Gao, Sara Javanmardi, Wael Farhan, Alex Ramirez, Ricardo Figueira, Khe Chai Sim, Yuval Bahat, Ashwin Vaswani, Liangzhe Yuan, Gufeng Zhang, Leland Rechis, Hanjun Dai, Tayo Oguntebi, Alexandra Cordell, Eugénie Rives, Kaan Tekelioglu, Naveen Kumar, Bing Zhang, Aurick Zhou, Nikolay Savinov, Andrew Leach, Alex Tudor, Sanjay Ganapathy, Yanyan Zheng, Mirko Rossini, Vera Axelrod, Arnaud Autef, Yukun Zhu, Zheng Zheng, Mingda Zhang, Baochen Sun, Jie Ren, Nenad Tomasev, Nithish Kannan, Amer Sinha, Charles Chen, Louis O'Bryan, Alex Pak, Aditya Kusupati, Weel Yang, Deepak Ramachandran, Patrick Griffin, Seokhwan Kim, Philipp Neubeck, Craig Schiff, Tammo Spalink, Mingyang Ling, Arun Nair, Ga-Young Joung, Linda Deng, Avishkar Bhoopchand, Lora Aroyo, Tom Duerig, Jordan Griffith, Gabe Barth-Maron, Jake Ades, Alex Haig, Ankur Taly, Yunting Song, Paul Michel, Dave Orr, Dean Weesner, Corentin Tallec, Carrie Grimes Bostock, Paul Niemczyk, Andy Twigg, Mudit Verma, Rohith Vallu, Henry Wang, Marco Gelmi, Kiranbir Sodhia, Aleksandr Chuklin, Omer Goldman, Jasmine George, Liang Bai, Kelvin Zhang, Petar Sirkovic, Efrat Nehoran, Golan Pundak, Jiaqi Mu, Alice Chen, Alex Greve, Paulo Zacchello, David Amos, Heming Ge, Eric Noland, Colton Bishop, Jeffrey Dudek, Youhei Namiki, Elena Buchatskaya, Jing Li, Dorsa Sadigh, Masha Samsikova, Dan Malkin, Damien Vincent, Robert David, Rob Willoughby, Phoenix Meadowlark, Shawn Gao, Yan Li, Raj Apte, Amit Jhindal, Stein Xudong Lin, Alex Polozov, Zhicheng Wang, Tomas Mery, Anirudh GP, Varun Yerram, Sage Stevens, Tianqi Liu, Noah Fiedel, Charles Sutton, Matthew Johnson, Xiaodan Song, Kate Baumli, Nir Shabat, Muqthar Mohammad, Hao Liu, Marco Selvi, Yichao Zhou, Mehdi Hafezi Manshadi, Chu-ling Ko, Anthony Chen, Michael Bendersky, Jorge Gonzalez Mendez, Nisarg Kothari, Amir Zandieh, Yiling Huang, Daniel Andor, Ellie Pavlick, Idan Brusilovsky, Jitendra Harlalka, Sally Goldman, Andrew Lampinen, Guowang Li, Asahi Ushio, Somit Gupta, Lei Zhang, Chuyuan Kelly Fu, Madhavi Sewak, Timo Denk, Jed Borovik, Brendan Jou, Avital Zipori, Prateek Jain, Junwen Bai, Thang Luong, Jonathan Tompson, Alice Li, Li Liu, George Powell, Jiajun Shen, Alex Feng, Grishma Chole, Da Yu, Yinlam Chow, Tongxin Yin, Eric Malmi, Kefan Xiao, Yash Pande, Shachi Paul, Niccolò Dal Santo, Adil Dostmohamed, Sergio Guadarrama, Aaron Phillips, Thanumalayan Sankaranarayana Pillai, Gal Yona, Amin Ghafouri, Preethi Lahoti, Benjamin Lee, Dhruv Madeka, Eren Sezener, Simon Tokumine, Adrian Collister, Nicola De Cao, Richard Shin, Uday Kalra, Parker Beak, Emily Nottage, Ryo Nakashima, Ivan Jurin, Vikash Sehwag, Meenu Gaba, Junhao Zeng, Kevin R. McKee, Fernando Pereira, Tamar Yakar, Amayika Panda, Arka Dhar, Peilin Zhong, Daniel Sohn, Mark Brand, Lars Lowe Sjoesund, Viral Carpenter, Sharon Lin, Shantanu Thakoor, Marcus Wainwright, Ashwin Chaugule, Pranesh Srinivasan, Muye Zhu, Bernett Orlando, Jack Weber, Ayzaan Wahid, Gilles Baechler, Apurv Suman, Jovana Mitrović, Gabe Taubman, Honglin Yu, Helen King, Josh Dillon, Cathy Yip, Dhriti Varma, Tomas Izo, Levent Bolelli, Borja De Balle Pigem, Julia Di Trapani, Fotis Iliopoulos, Adam Paszke, Nishant Ranka, Joe Zou, Francesco Pongetti, Jed McGiffin, Alex Siegman, Rich Galt, Ross Hemsley, Goran Žužić, Victor Carbune, Tao Li, Myle Ott, Félix de Chaumont Quitry, David Vilar Torres, Yuri Chervonyi, Tomy Tsai, Prem Eruvbetine, Samuel Yang, Matthew Denton, Jake Walker, Slavica Andačić, Idan Heimlich Shtacher, Vittal Premachandran, Harshal Tushar Lehri, Cip Baetu, Damion Yates, Lampros Lamprou, Mariko Iinuma, Ioana Mihailescu, Ben Albrecht, Shachi Dave, Susie Sargsyan, Bryan Perozzi, Lucas Manning, Chiyuan Zhang, Denis Vnukov, Igor Mordatch, Raia Hadsell Wolfgang Macherey, Ryan Kappedal, Jim Stephan, Aditya Tripathi, Klaus Macherey, Jun Qian, Abhishek Bhowmick, Shekoofeh Azizi, Rémi Leblond, Shiva Mohan Reddy Garlapati, Timothy Knight, Matthew Wiethoff, Wei-Chih Hung, Anelia Angelova, Georgios Evangelopoulos, Pawel Janus, Dimitris Paparas, Matthew Rahtz, Ken Caluwaerts, Vivek Sampathkumar, Daniel Jarrett, Shadi Noghabi, Antoine Miech, Chak Yeung, Geoff Clark, Henry Prior, Fei Zheng, Jean Pouget-Abadie, Indro Bhattacharya, Kalpesh Krishna, Will Bishop, Zhe Yuan, Yunxiao Deng, Ashutosh Sathe, Kacper Krasowiak, Ciprian Chelba, Cho-Jui Hsieh, Kiran Vodrahalli, Buhuang Liu, Thomas Köppe, Amr Khalifa, Lubo Litchev, Pichi Charoenpanit, Reed Roberts, Sachin Yadav, Yasumasa Onoe, Desi Ivanov, Megha Mohabey, Vighnesh Birodkar, Nemanja Rakićević, Pierre Sermanet, Vaibhav Mehta, Krishan Subudhi, Travis Choma, Will Ng, Luheng He, Kathie Wang, Tasos Kementsietsidis, Shane Gu, Mansi Gupta, Andrew Nystrom, Mehran Kazemi, Timothy Chung, Nacho Cano, Nikhil Dhawan, Yufei Wang, Jiawei Xia, Trevor Yacovone, Eric Jia, Mingqing Chen, Simeon Ivanov, Ashrith Sheshan, Sid Dalmia, Paweł Stradomski, Pengcheng Yin, Salem Haykal, Congchao Wang, Dennis Duan, Neslihan Bulut, Greg Kochanski, Liam MacDermed, Namrata Godbole, Shitao Weng, Jingjing Chen, Rachana Fellinger, Ramin Mehran, Daniel Suo, Hisham Husain, Tong He, Kaushal Patel, Joshua Howland, Randall Parker, Kelvin Nguyen, Sharath Maddineni, Chris Rawles, Mina Khan, Shlomi Cohen-Ganor, Amol Mandhane, Xinyi Wu, Chenkai Kuang, Iulia Comşa, Ramya Ganeshan, Hanie Sedghi, Adam Bloniarz, Nuo Wang Pierse, Anton Briukhov, Petr Mitrichev, Anita Gergely, Serena Zhan, Allan Zhou, Nikita Saxena, Eva Lu, Josef Dean, Ashish Gupta, Nicolas Perez-Nieves, Renjie Wu, Cory McLean, Wei Liang, Disha Jindal, Anton Tsitsulin, Wenhao Yu, Kaiz Alarakyia, Tom Schaul, Piyush Patil, Peter Sung, Elijah Peake, Hongkun Yu, Feryal Behbahani, JD Co-Reyes, Alan Ansell, Sean Sun, Clara Barbu, Jonathan Lee, Seb Noury, James Allingham, Bilal Piot, Mohit Sharma, Christopher Yew, Ivan Korotkov, Bibo Xu, Demetra Brady, Goran Petrovic, Shibl Mourad, Claire Cui, Aditya Gupta, Parker Schuh, Saarthak Khanna, Anna Goldie, Abhinav Arora, Vadim Zubov, Amy Stuart, Mark Epstein, Yun Zhu, Jianqiao Liu, Yury Stuken, Ziyue Wang, Karolis Misiunas, Dee Guo, Ashleah Gill, Ale Hartman, Zaid Nabulsi, Aurko Roy, Aleksandra Faust, Jason Riesa, Ben Withbroe, Mengchao Wang, Marco Tagliasacchi, Andreea Marzoca, James Noraky, Serge Toropov, Malika Mehrotra, Bahram Raad, Sanja Deur, Steve Xu, Marianne Monteiro, Zhongru Wu, Yi Luan, Sam Ritter, Nick Li, Håvard Garnes, Yanzhang He, Martin Zlocha, Jifan Zhu, Matteo Hessel, Will Wu, Spandana Raj Babbula, Chizu Kawamoto, Yuanzhen Li, Mehadi Hassen, Yan Wang, Brian Wieder, James Freedman, Yin Zhang, Xinyi Bai, Tianli Yu, David Reitter, XiangHai Sheng, Mateo Wirth, Aditya Kini, Dima Damen, Mingcen Gao, Rachel Hornung, Michael Voznesensky, Brian Roark, Adhi Kuncoro, Yuxiang Zhou, Rushin Shah, Anthony Brohan, Kuangyuan Chen, James Wendt, David Rim, Paul Kishan Rubenstein, Jonathan Halcrow, Michelle Liu, Ty Geri, Yunhsuan Sung, Jane Shapiro, Shaan Bijwadia, Chris Duvarney, Christina Sorokin, Paul Natsev, Reeve Ingle, Pramod Gupta, Young Maeng, Ndaba Ndebele, Kexin Zhu, Valentin Anklin, Katherine Lee, Yuan Liu, Yaroslav Akulov, Shaleen Gupta, Guolong Su, Flavien Prost, Tianlin Liu, Vitaly Kovalev, Pol Moreno, Martin Scholz, Sam Redmond, Zongwei Zhou, Alex Castro-Ros, André Susano Pinto, Dia Kharrat, Michal Yarom, Rachel Saputro, Jannis Bulian, Ben Caine, Ji Liu, Abbas Abdolmaleki, Shariq Iqbal, Tautvydas Misiunas, Mikhail Sirotenko, Shefali Garg, Guy Bensky, Huan Gui, Xuezhi Wang, Raphael Koster, Mike Bernico, Da Huang, Romal Thoppilan, Trevor Cohn, Ben Golan, Wenlei Zhou, Andrew Rosenberg, Markus Freitag, Tynan Gangwani, Vincent Tsang, Anand Shukla, Xiaoqi Ren, Minh Giang, Chi Zou, Andre Elisseeff, Charline Le Lan, Dheeru Dua, Shuba Lall, Pranav Shyam, Frankie Garcia, Sarah Nguyen, Michael Guzman, AJ Maschinot, Marcello Maggioni, Ming-Wei Chang, Karol Gregor, Lotte Weerts, Kumaran Venkatesan, Bogdan Damoc, Leon Liu, Jan Wassenberg, Lewis Ho, Becca Roelofs, Majid Hadian, François-Xavier Aubet, Yu Liang, Sami Lachgar, Danny Karmon, Yong Cheng, Amelio Vázquez-Reina, Angie Chen, Zhuyun Dai, Andy Brock, Shubham Agrawal, Chenxi Pang, Peter Garst, Mariella Sanchez-Vargas, Ivor Rendulic, Aditya Ayyar, Andrija Ražnatović, Olivia Ma, Roopali Vij, Neha Sharma, Ashwin Balakrishna, Bingyuan Liu, Ian Mackinnon, Sorin Baltateanu, Petra Poklukar, Gabriel Ibagon, Colin Ji, Hongyang Jiao, Isaac Noble, Wojciech Stokowiec, Zhihao Li, Jeff Dean, David Lindner, Mark Omernick, Kristen Chiafullo, Mason Dimarco, Vitor Rodrigues, Vittorio Selo, Garrett Honke, Xintian, Wu, Wei He, Adam Hillier, Anhad Mohananey, Vihari Piratla, Chang Ye, Chase Malik, Sebastian Riedel, Samuel Albanie, Zi Yang, Kenny Vassigh, Maria Bauza, Sheng Li, Yiqing Tao, Nevan Wichers, Andrii Maksai, Abe Ittycheriah, Ross Mcilroy, Bryan Seybold, Noah Goodman, Romina Datta, Steven M. Hernandez, Tian Shi, Yony Kochinski, Anna Bulanova, Ken Franko, Mikita Sazanovich, Nicholas FitzGerald, Praneeth Kacham, Shubha Srinivas Raghvendra, Vincent Hellendoorn, Alexander Grushetsky, Julian Salazar, Angeliki Lazaridou, Jason Chang, Jan-Thorsten Peter, Sushant Kafle, Yann Dauphin, Abhishek Rao, Filippo Graziano, Izhak Shafran, Yuguo Liao, Tianli Ding, Geng Yan, Grace Chu, Zhao Fu, Vincent Roulet, Gabriel Rasskin, Duncan Williams, Shahar Drath, Alex Mossin, Raphael Hoffmann, Jordi Orbay, Francesco Bertolini, Hila Sheftel, Justin Chiu, Siyang Xue, Yuheng Kuang, Ferjad Naeem, Swaroop Nath, Nana Nti, Phil Culliton, Kashyap Krishnakumar, Michael Isard, Pei Sun, Ayan Chakrabarti, Nathan Clement, Regev Cohen, Arissa Wongpanich, GS Oh, Ashwin Murthy, Hao Zheng, Jessica Hamrick, Oskar Bunyan, Suhas Ganesh, Nitish Gupta, Roy Frostig, John Wieting, Yury Malkov, Pierre Marcenac, Zhixin, Lai, Xiaodan Tang, Mohammad Saleh, Fedir Zubach, Chinmay Kulkarni, Huanjie Zhou, Vicky Zayats, Nan Ding, Anshuman Tripathi, Arijit Pramanik, Patrik Zochbauer, Harish Ganapathy, Vedant Misra, Zach Behrman, Hugo Vallet, Mingyang Zhang, Mukund Sridhar, Ye Jin, Mohammad Babaeizadeh, Siim Põder, Megha Goel, Divya Jain, Tajwar Nasir, Shubham Mittal, Tim Dozat, Diego Ardila, Aliaksei Severyn, Fabio Pardo, Sammy Jerome, Siyang Qin, Louis Rouillard, Amir Yazdanbakhsh, Zizhao Zhang, Shivani Agrawal, Kaushik Shivakumar, Caden Lu, Praveen Kallakuri, Rachita Chhaparia, Kanishka Rao, Charles Kwong, Asya Fadeeva, Shitij Nigam, Yan Virin, Yuan Zhang, Balaji Venkatraman, Beliz Gunel, Marc Wilson, Huiyu Wang, Abhinav Gupta, Xiaowei Xu, Adrien Ali Taïga, Kareem Mohamed, Doug Fritz, Daniel Rodriguez, Zoubin Ghahramani, Harry Askham, Lior Belenki, James Zhao, Rahul Gupta, Krzysztof Jastrzębski, Takahiro Kosakai, Kaan Katircioglu, Jon Schneider, Rina Panigrahy, Konstantinos Bousmalis, Peter Grabowski, Prajit Ramachandran, Chaitra Hegde, Mihaela Rosca, Angelo Scorza Scarpati, Kyriakos Axiotis, Ying Xu, Zach Gleicher, Assaf Hurwitz Michaely, Mandar Sharma, Sanil Jain, Christoph Hirnschall, Tal Marian, Xuhui Jia, Kevin Mather, Kilol Gupta, Linhai Qiu, Nigamaa Nayakanti, Lucian Ionita, Steven Zheng, Lucia Loher, Kurt Shuster, Igor Petrovski, Roshan Sharma, Rahma Chaabouni, Angel Yeh, James An, Arushi Gupta, Steven Schwarcz, Seher Ellis, Sam Conway-Rahman, Javier Snaider, Alex Zhai, James Atwood, Daniel Golovin, Liqian Peng, Te I, Vivian Xia, Salvatore Scellato, Mahan Malihi, Arthur Bražinskas, Vlad-Doru Ion, Younghoon Jun, James Swirhun, Soroosh Mariooryad, Jiao Sun, Steve Chien, Rey Coaguila, Ariel Brand, Yi Gao, Tom Kwiatkowski, Roee Aharoni, Cheng-Chun Lee, Mislav Žanić, Yichi Zhang, Dan Ethier, Vitaly Nikolaev, Pranav Nair, Yoav Ben Shalom, Hen Fitoussi, Jai Gupta, Hongbin Liu, Dee Cattle, Tolga Bolukbasi, Ben Murdoch, Fantine Huot, Yin Li, Chris Hahn</p><p><b>Upvotes:</b> 57</p><p><b>Summary:</b> In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our most capable model yet, achieving SoTA performance on frontier coding and reasoning benchmarks. In addition to its incredible coding and reasoning skills, Gemini 2.5 Pro is a thinking model that excels at multimodal understanding and it is now able to process up to 3 hours of video content. Its unique combination of long context, multimodal and reasoning capabilities can be combined to unlock new agentic workflows. Gemini 2.5 Flash provides excellent reasoning abilities at a fraction of the compute and latency requirements and Gemini 2.0 Flash and Flash-Lite provide high performance at low latency and cost. Taken together, the Gemini 2.X model generation spans the full Pareto frontier of model capability vs cost, allowing users to explore the boundaries of what is possible with complex agentic problem solving.</p> - https://arxiv.org/abs/2507.06261 - Mon, 07 Jul 2025 17:36:04 +0000 + DeepPHY: Benchmarking Agentic VLMs on Physical Reasoning + https://arxiv.org/abs/2508.05405 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.05405.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xinrun Xu, Pi Bu, Ye Wang, Börje F. Karlsson, Ziming Wang, Tengtao Song, Qi Zhu, Jun Song, Zhiming Ding, Bo Zheng</p><p><b>Upvotes:</b> 63</p><p><b>Summary:</b> Although Vision Language Models (VLMs) exhibit strong perceptual abilities and impressive visual reasoning, they struggle with attention to detail and precise action planning in complex, dynamic environments, leading to subpar performance. Real-world tasks typically require complex interactions, advanced spatial reasoning, long-term planning, and continuous strategy refinement, usually necessitating understanding the physics rules of the target scenario. However, evaluating these capabilities in real-world scenarios is often prohibitively expensive. To bridge this gap, we introduce DeepPHY, a novel benchmark framework designed to systematically evaluate VLMs' understanding and reasoning about fundamental physical principles through a series of challenging simulated environments. DeepPHY integrates multiple physical reasoning environments of varying difficulty levels and incorporates fine-grained evaluation metrics. Our evaluation finds that even state-of-the-art VLMs struggle to translate descriptive physical knowledge into precise, predictive control.</p> + https://arxiv.org/abs/2508.05405 + Thu, 07 Aug 2025 13:58:19 +0000 - StreamVLN: Streaming Vision-and-Language Navigation via SlowFast Context Modeling - https://arxiv.org/abs/2507.05240 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.05240.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Meng Wei, Chenyang Wan, Xiqian Yu, Tai Wang, Yuqiang Yang, Xiaohan Mao, Chenming Zhu, Wenzhe Cai, Hanqing Wang, Yilun Chen, Xihui Liu, Jiangmiao Pang</p><p><b>Upvotes:</b> 45</p><p><b>Summary:</b> Vision-and-Language Navigation (VLN) in real-world settings requires agents to process continuous visual streams and generate actions with low latency grounded in language instructions. While Video-based Large Language Models (Video-LLMs) have driven recent progress, current VLN methods based on Video-LLM often face trade-offs among fine-grained visual understanding, long-term context modeling and computational efficiency. We introduce StreamVLN, a streaming VLN framework that employs a hybrid slow-fast context modeling strategy to support multi-modal reasoning over interleaved vision, language and action inputs. The fast-streaming dialogue context facilitates responsive action generation through a sliding-window of active dialogues, while the slow-updating memory context compresses historical visual states using a 3D-aware token pruning strategy. With this slow-fast design, StreamVLN achieves coherent multi-turn dialogue through efficient KV cache reuse, supporting long video streams with bounded context size and inference cost. Experiments on VLN-CE benchmarks demonstrate state-of-the-art performance with stable low latency, ensuring robustness and efficiency in real-world deployment. The project page is: https://streamvln.github.io/{https://streamvln.github.io/}.</p> - https://arxiv.org/abs/2507.05240 - Mon, 07 Jul 2025 17:49:41 +0000 + On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification + https://arxiv.org/abs/2508.05629 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.05629.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yongliang Wu, Yizhou Zhou, Zhou Ziheng, Yingzhe Peng, Xinyu Ye, Xinting Hu, Wenbo Zhu, Lu Qi, Ming-Hsuan Yang, Xu Yang</p><p><b>Upvotes:</b> 167</p><p><b>Summary:</b> We present a simple yet theoretically motivated improvement to Supervised Fine-Tuning (SFT) for the Large Language Model (LLM), addressing its limited generalization compared to reinforcement learning (RL). Through mathematical analysis, we reveal that standard SFT gradients implicitly encode a problematic reward structure that may severely restrict the generalization capabilities of model. To rectify this, we propose Dynamic Fine-Tuning (DFT), stabilizing gradient updates for each token by dynamically rescaling the objective function with the probability of this token. Remarkably, this single-line code change significantly outperforms standard SFT across multiple challenging benchmarks and base models, demonstrating greatly improved generalization. Additionally, our approach shows competitive results in offline RL settings, offering an effective yet simpler alternative. This work bridges theoretical insight and practical solutions, substantially advancing SFT performance. The code will be available at https://github.com/yongliang-wu/DFT.</p> + https://arxiv.org/abs/2508.05629 + Thu, 07 Aug 2025 17:59:04 +0000 - Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoning - https://arxiv.org/abs/2507.05255 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.05255.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yana Wei, Liang Zhao, Jianjian Sun, Kangheng Lin, Jisheng Yin, Jingcheng Hu, Yinmin Zhang, En Yu, Haoran Lv, Zejia Weng, Jia Wang, Chunrui Han, Yuang Peng, Qi Han, Zheng Ge, Xiangyu Zhang, Daxin Jiang, Vishal M. Patel</p><p><b>Upvotes:</b> 68</p><p><b>Summary:</b> The remarkable reasoning capability of large language models (LLMs) stems from cognitive behaviors that emerge through reinforcement with verifiable rewards. This work investigates how to transfer this principle to Multimodal LLMs (MLLMs) to unlock advanced visual reasoning. We introduce a two-stage paradigm built on Qwen2.5-VL-7B: a massive linguistic cold-start fine-tuning, followed by multimodal reinforcement learning (RL) spanning nearly 1,000 steps, surpassing all previous open-source efforts in scale. This pioneering work reveals three fundamental insights: 1) Behavior transfer emerges surprisingly early in cold start due to linguistic mental imagery. 2) Cold start broadly memorizes visual behaviors, while RL critically discerns and scales up effective patterns. 3) Transfer strategically favors high-utility behaviors such as visual reflection. Our resulting model, Open-Vision-Reasoner (OVR), achieves state-of-the-art performance on a suite of reasoning benchmarks, including 95.3% on MATH500, 51.8% on MathVision and 54.6% on MathVerse. We release our model, data, and training dynamics to catalyze the development of more capable, behavior-aligned multimodal reasoners.</p> - https://arxiv.org/abs/2507.05255 - Mon, 07 Jul 2025 17:59:03 +0000 + Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation + https://arxiv.org/abs/2508.05635 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.05635.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yue Liao, Pengfei Zhou, Siyuan Huang, Donglin Yang, Shengcong Chen, Yuxin Jiang, Yue Hu, Jingbin Cai, Si Liu, Jianlan Luo, Liliang Chen, Shuicheng Yan, Maoqing Yao, Guanghui Ren</p><p><b>Upvotes:</b> 72</p><p><b>Summary:</b> We introduce Genie Envisioner (GE), a unified world foundation platform for robotic manipulation that integrates policy learning, evaluation, and simulation within a single video-generative framework. At its core, GE-Base is a large-scale, instruction-conditioned video diffusion model that captures the spatial, temporal, and semantic dynamics of real-world robotic interactions in a structured latent space. Built upon this foundation, GE-Act maps latent representations to executable action trajectories through a lightweight, flow-matching decoder, enabling precise and generalizable policy inference across diverse embodiments with minimal supervision. To support scalable evaluation and training, GE-Sim serves as an action-conditioned neural simulator, producing high-fidelity rollouts for closed-loop policy development. The platform is further equipped with EWMBench, a standardized benchmark suite measuring visual fidelity, physical consistency, and instruction-action alignment. Together, these components establish Genie Envisioner as a scalable and practical foundation for instruction-driven, general-purpose embodied intelligence. All code, models, and benchmarks will be released publicly.</p> + https://arxiv.org/abs/2508.05635 + Thu, 07 Aug 2025 17:59:44 +0000 - SingLoRA: Low Rank Adaptation Using a Single Matrix - https://arxiv.org/abs/2507.05566 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.05566.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> David Bensaïd, Noam Rotstein, Roy Velich, Daniel Bensaïd, Ron Kimmel</p><p><b>Upvotes:</b> 108</p><p><b>Summary:</b> Low-Rank Adaptation (LoRA) has significantly advanced parameter-efficient fine-tuning of large pretrained models. LoRA augments the pre-trained weights of a model by adding the product of two smaller matrices that together form a low-rank matrix update. Recent research has shown that scale disparities between these two matrices often cause unstable training dynamics, leading to suboptimal performance. In this paper, we propose SingLoRA, which reformulates low-rank adaptation by learning the weights update as a decomposition of a single low-rank matrix multiplied by its transpose. This simple design inherently removes inter-matrix scale conflicts, ensuring stable optimization, and roughly halves the parameter count. We analyze SingLoRA within the infinite-width neural network framework, showing that it guarantees stable feature learning by construction. Extensive experiments on multiple tasks validate these benefits. In common sense reasoning, fine-tuning LLama 7B on MNLI with SingLoRA achieves 91.3% accuracy - surpassing LoRA (89.1%) and LoRA+ (90.2%) - while using only 60% of their parameter budget. In image generation, fine-tuning Stable Diffusion with SingLoRA significantly improves image fidelity on DreamBooth, achieving a DINO similarity score of 0.151, compared to scores of 0.148 and 0.143 for DoRA and LoRA, respectively.</p> - https://arxiv.org/abs/2507.05566 - Tue, 08 Jul 2025 01:11:30 +0000 + WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agent + https://arxiv.org/abs/2508.05748 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.05748.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xinyu Geng, Peng Xia, Zhen Zhang, Xinyu Wang, Qiuchen Wang, Ruixue Ding, Chenxi Wang, Jialong Wu, Yida Zhao, Kuan Li, Yong Jiang, Pengjun Xie, Fei Huang, Jingren Zhou</p><p><b>Upvotes:</b> 121</p><p><b>Summary:</b> Web agents such as Deep Research have demonstrated superhuman cognitive abilities, capable of solving highly challenging information-seeking problems. However, most research remains primarily text-centric, overlooking visual information in the real world. This makes multimodal Deep Research highly challenging, as such agents require much stronger reasoning abilities in perception, logic, knowledge, and the use of more sophisticated tools compared to text-based agents. To address this limitation, we introduce WebWatcher, a multi-modal Agent for Deep Research equipped with enhanced visual-language reasoning capabilities. It leverages high-quality synthetic multimodal trajectories for efficient cold start training, utilizes various tools for deep reasoning, and further enhances generalization through reinforcement learning. To better evaluate the capabilities of multimodal agents, we propose BrowseComp-VL, a benchmark with BrowseComp-style that requires complex information retrieval involving both visual and textual information. Experimental results show that WebWatcher significantly outperforms proprietary baseline, RAG workflow and open-source agents in four challenging VQA benchmarks, which paves the way for solving complex multimodal information-seeking tasks.</p> + https://arxiv.org/abs/2508.05748 + Thu, 07 Aug 2025 18:03:50 +0000 - T-LoRA: Single Image Diffusion Model Customization Without Overfitting - https://arxiv.org/abs/2507.05964 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.05964.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Vera Soboleva, Aibek Alanov, Andrey Kuznetsov, Konstantin Sobolev</p><p><b>Upvotes:</b> 113</p><p><b>Summary:</b> While diffusion model fine-tuning offers a powerful approach for customizing pre-trained models to generate specific objects, it frequently suffers from overfitting when training samples are limited, compromising both generalization capability and output diversity. This paper tackles the challenging yet most impactful task of adapting a diffusion model using just a single concept image, as single-image customization holds the greatest practical potential. We introduce T-LoRA, a Timestep-Dependent Low-Rank Adaptation framework specifically designed for diffusion model personalization. In our work we show that higher diffusion timesteps are more prone to overfitting than lower ones, necessitating a timestep-sensitive fine-tuning strategy. T-LoRA incorporates two key innovations: (1) a dynamic fine-tuning strategy that adjusts rank-constrained updates based on diffusion timesteps, and (2) a weight parametrization technique that ensures independence between adapter components through orthogonal initialization. Extensive experiments show that T-LoRA and its individual components outperform standard LoRA and other diffusion model personalization techniques. They achieve a superior balance between concept fidelity and text alignment, highlighting the potential of T-LoRA in data-limited and resource-constrained scenarios. Code is available at https://github.com/ControlGenAI/T-LoRA.</p> - https://arxiv.org/abs/2507.05964 - Tue, 08 Jul 2025 13:14:10 +0000 + Memp: Exploring Agent Procedural Memory + https://arxiv.org/abs/2508.06433 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.06433.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Runnan Fang, Yuan Liang, Xiaobin Wang, Jialong Wu, Shuofei Qiao, Pengjun Xie, Fei Huang, Huajun Chen, Ningyu Zhang</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> Large Language Models (LLMs) based agents excel at diverse tasks, yet they suffer from brittle procedural memory that is manually engineered or entangled in static parameters. In this work, we investigate strategies to endow agents with a learnable, updatable, and lifelong procedural memory. We propose Memp that distills past agent trajectories into both fine-grained, step-by-step instructions and higher-level, script-like abstractions, and explore the impact of different strategies for Build, Retrieval, and Update of procedural memory. Coupled with a dynamic regimen that continuously updates, corrects, and deprecates its contents, this repository evolves in lockstep with new experience. Empirical evaluation on TravelPlanner and ALFWorld shows that as the memory repository is refined, agents achieve steadily higher success rates and greater efficiency on analogous tasks. Moreover, procedural memory built from a stronger model retains its value: migrating the procedural memory to a weaker model yields substantial performance gains.</p> + https://arxiv.org/abs/2508.06433 + Fri, 08 Aug 2025 16:20:56 +0000 - OmniPart: Part-Aware 3D Generation with Semantic Decoupling and Structural Cohesion - https://arxiv.org/abs/2507.06165 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.06165.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yunhan Yang, Yufan Zhou, Yuan-Chen Guo, Zi-Xin Zou, Yukun Huang, Ying-Tian Liu, Hao Xu, Ding Liang, Yan-Pei Cao, Xihui Liu</p><p><b>Upvotes:</b> 54</p><p><b>Summary:</b> The creation of 3D assets with explicit, editable part structures is crucial for advancing interactive applications, yet most generative methods produce only monolithic shapes, limiting their utility. We introduce OmniPart, a novel framework for part-aware 3D object generation designed to achieve high semantic decoupling among components while maintaining robust structural cohesion. OmniPart uniquely decouples this complex task into two synergistic stages: (1) an autoregressive structure planning module generates a controllable, variable-length sequence of 3D part bounding boxes, critically guided by flexible 2D part masks that allow for intuitive control over part decomposition without requiring direct correspondences or semantic labels; and (2) a spatially-conditioned rectified flow model, efficiently adapted from a pre-trained holistic 3D generator, synthesizes all 3D parts simultaneously and consistently within the planned layout. Our approach supports user-defined part granularity, precise localization, and enables diverse downstream applications. Extensive experiments demonstrate that OmniPart achieves state-of-the-art performance, paving the way for more interpretable, editable, and versatile 3D content.</p> - https://arxiv.org/abs/2507.06165 - Tue, 08 Jul 2025 16:46:15 +0000 + GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models + https://arxiv.org/abs/2508.06471 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.06471.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> GLM-4. 5 Team, Aohan Zeng, Xin Lv, Qinkai Zheng, Zhenyu Hou, Bin Chen, Chengxing Xie, Cunxiang Wang, Da Yin, Hao Zeng, Jiajie Zhang, Kedong Wang, Lucen Zhong, Mingdao Liu, Rui Lu, Shulin Cao, Xiaohan Zhang, Xuancheng Huang, Yao Wei, Yean Cheng, Yifan An, Yilin Niu, Yuanhao Wen, Yushi Bai, Zhengxiao Du, Zihan Wang, Zilin Zhu, Bohan Zhang, Bosi Wen, Bowen Wu, Bowen Xu, Can Huang, Casey Zhao, Changpeng Cai, Chao Yu, Chen Li, Chendi Ge, Chenghua Huang, Chenhui Zhang, Chenxi Xu, Chenzheng Zhu, Chuang Li, Congfeng Yin, Daoyan Lin, Dayong Yang, Dazhi Jiang, Ding Ai, Erle Zhu, Fei Wang, Gengzheng Pan, Guo Wang, Hailong Sun, Haitao Li, Haiyang Li, Haiyi Hu, Hanyu Zhang, Hao Peng, Hao Tai, Haoke Zhang, Haoran Wang, Haoyu Yang, He Liu, He Zhao, Hongwei Liu, Hongxi Yan, Huan Liu, Huilong Chen, Ji Li, Jiajing Zhao, Jiamin Ren, Jian Jiao, Jiani Zhao, Jianyang Yan, Jiaqi Wang, Jiayi Gui, Jiayue Zhao, Jie Liu, Jijie Li, Jing Li, Jing Lu, Jingsen Wang, Jingwei Yuan, Jingxuan Li, Jingzhao Du, Jinhua Du, Jinxin Liu, Junkai Zhi, Junli Gao, Ke Wang, Lekang Yang, Liang Xu, Lin Fan, Lindong Wu, Lintao Ding, Lu Wang, Man Zhang, Minghao Li, Minghuan Xu, Mingming Zhao, Mingshu Zhai, Pengfan Du, Qian Dong, Shangde Lei, Shangqing Tu, Shangtong Yang, Shaoyou Lu, Shijie Li, Shuang Li, Shuang-Li, Shuxun Yang, Sibo Yi, Tianshu Yu, Wei Tian, Weihan Wang, Wenbo Yu, Weng Lam Tam, Wenjie Liang, Wentao Liu, Xiao Wang, Xiaohan Jia, Xiaotao Gu, Xiaoying Ling, Xin Wang, Xing Fan, Xingru Pan, Xinyuan Zhang, Xinze Zhang, Xiuqing Fu, Xunkai Zhang, Yabo Xu, Yandong Wu, Yida Lu, Yidong Wang, Yilin Zhou, Yiming Pan, Ying Zhang, Yingli Wang, Yingru Li, Yinpei Su, Yipeng Geng, Yitong Zhu, Yongkun Yang, Yuhang Li, Yuhao Wu, Yujiang Li, Yunan Liu, Yunqing Wang, Yuntao Li, Yuxuan Zhang, Zezhen Liu, Zhen Yang, Zhengda Zhou, Zhongpei Qiao, Zhuoer Feng, Zhuorui Liu, Zichen Zhang, Zihan Wang, Zijun Yao, Zikang Wang, Ziqiang Liu, Ziwei Chai, Zixuan Li, Zuodong Zhao, Wenguang Chen, Jidong Zhai, Bin Xu, Minlie Huang, Hongning Wang, Juanzi Li, Yuxiao Dong, Jie Tang</p><p><b>Upvotes:</b> 168</p><p><b>Summary:</b> We present GLM-4.5, an open-source Mixture-of-Experts (MoE) large language model with 355B total parameters and 32B activated parameters, featuring a hybrid reasoning method that supports both thinking and direct response modes. Through multi-stage training on 23T tokens and comprehensive post-training with expert model iteration and reinforcement learning, GLM-4.5 achieves strong performance across agentic, reasoning, and coding (ARC) tasks, scoring 70.1% on TAU-Bench, 91.0% on AIME 24, and 64.2% on SWE-bench Verified. With much fewer parameters than several competitors, GLM-4.5 ranks 3rd overall among all evaluated models and 2nd on agentic benchmarks. We release both GLM-4.5 (355B parameters) and a compact version, GLM-4.5-Air (106B parameters), to advance research in reasoning and agentic AI systems. Code, models, and more information are available at https://github.com/zai-org/GLM-4.5.</p> + https://arxiv.org/abs/2508.06471 + Fri, 08 Aug 2025 17:21:06 +0000 - Skywork-R1V3 Technical Report - https://arxiv.org/abs/2507.06167 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.06167.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wei Shen, Jiangbo Pei, Yi Peng, Xuchen Song, Yang Liu, Jian Peng, Haofeng Sun, Yunzhuo Hao, Peiyu Wang, Yahui Zhou</p><p><b>Upvotes:</b> 66</p><p><b>Summary:</b> We introduce Skywork-R1V3, an advanced, open-source vision-language model (VLM) that pioneers a new approach to visual reasoning. Its key innovation lies in effectively transferring reasoning skills from text-only Large Language Models (LLMs) to visual tasks. The strong performance of Skywork-R1V3 primarily stems from our elaborate post-training RL framework, which effectively activates and enhances the model's reasoning ability, without the need for additional continue pre-training. Through this framework, we further uncover the fundamental role of the connector module in achieving robust cross-modal alignment for multimodal reasoning models. In addition, we introduce a unique indicator of reasoning capability, the entropy of critical reasoning tokens, which has proven highly effective for checkpoint selection during RL training. Skywork-R1V3 achieves state-of-the-art results on MMMU, significantly improving from 64.3% to 76.0%. This performance matches entry-level human capabilities. Remarkably, our RL-powered post-training approach enables even the 38B parameter model to rival top closed-source VLMs. The implementation successfully transfers mathematical reasoning to other subject-related reasoning tasks. We also include an analysis of curriculum learning and reinforcement finetuning strategies, along with a broader discussion on multimodal reasoning. Skywork-R1V3 represents a significant leap in multimodal reasoning, showcasing RL as a powerful engine for advancing open-source VLM capabilities.</p> - https://arxiv.org/abs/2507.06167 - Tue, 08 Jul 2025 16:47:16 +0000 + BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent + https://arxiv.org/abs/2508.06600 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.06600.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zijian Chen, Xueguang Ma, Shengyao Zhuang, Ping Nie, Kai Zou, Andrew Liu, Joshua Green, Kshama Patel, Ruoxi Meng, Mingyi Su, Sahel Sharifymoghaddam, Yanxi Li, Haoran Hong, Xinyu Shi, Xuye Liu, Nandan Thakur, Crystina Zhang, Luyu Gao, Wenhu Chen, Jimmy Lin</p><p><b>Upvotes:</b> 36</p><p><b>Summary:</b> Deep-Research agents, which integrate large language models (LLMs) with search tools, have shown success in improving the effectiveness of handling complex queries that require iterative search planning and reasoning over search results. Evaluations on current benchmarks like BrowseComp relies on black-box live web search APIs, have notable limitations in (1) fairness: dynamic and opaque web APIs hinder fair comparisons and reproducibility of deep research methods; (2) transparency: lack of control over the document corpus makes it difficult to isolate retriever contributions. In other words, the current evaluations may compare a complete deep research system at a given time, but they do not foster well-controlled experiments to provide insights into the capability of underlying deep research LLMs. To address these challenges, we introduce BrowseComp-Plus, a benchmark derived from BrowseComp, employing a fixed, carefully curated corpus. Each query in BrowseComp-Plus includes human-verified supporting documents and mined challenging negatives, enabling controlled experimentation. The benchmark is shown to be effective in distinguishing the performance of deep research systems. For instance, the open-source model Search-R1, when paired with the BM25 retriever, achieves 3.86% accuracy, whereas the GPT-5 achieves 55.9%. Integrating the GPT-5 with the Qwen3-Embedding-8B retriever further enhances its accuracy to 70.1% with fewer search calls. This benchmark allows comprehensive evaluation and disentangled analysis of deep research agents and retrieval methods, fostering insights into retrieval effectiveness, citation accuracy, and context engineering in Deep-Research system.</p> + https://arxiv.org/abs/2508.06600 + Fri, 08 Aug 2025 17:55:11 +0000 - CriticLean: Critic-Guided Reinforcement Learning for Mathematical Formalization - https://arxiv.org/abs/2507.06181 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.06181.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhongyuan Peng, Yifan Yao, Kaijing Ma, Shuyue Guo, Yizhe Li, Yichi Zhang, Chenchen Zhang, Yifan Zhang, Zhouliang Yu, Luming Li, Minghao Liu, Yihang Xia, Jiawei Shen, Yuchen Wu, Yixin Cao, Zhaoxiang Zhang, Wenhao Huang, Jiaheng Liu, Ge Zhang</p><p><b>Upvotes:</b> 39</p><p><b>Summary:</b> Translating natural language mathematical statements into formal, executable code is a fundamental challenge in automated theorem proving. While prior work has focused on generation and compilation success, little attention has been paid to the critic phase-the evaluation of whether generated formalizations truly capture the semantic intent of the original problem. In this paper, we introduce CriticLean, a novel critic-guided reinforcement learning framework that elevates the role of the critic from a passive validator to an active learning component. Specifically, first, we propose the CriticLeanGPT, trained via supervised fine-tuning and reinforcement learning, to rigorously assess the semantic fidelity of Lean 4 formalizations. Then, we introduce CriticLeanBench, a benchmark designed to measure models' ability to distinguish semantically correct from incorrect formalizations, and demonstrate that our trained CriticLeanGPT models can significantly outperform strong open- and closed-source baselines. Building on the CriticLean framework, we construct FineLeanCorpus, a dataset comprising over 285K problems that exhibits rich domain diversity, broad difficulty coverage, and high correctness based on human evaluation. Overall, our findings highlight that optimizing the critic phase is essential for producing reliable formalizations, and we hope our CriticLean will provide valuable insights for future advances in formal mathematical reasoning.</p> - https://arxiv.org/abs/2507.06181 - Tue, 08 Jul 2025 17:03:39 +0000 + ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability + https://arxiv.org/abs/2508.07050 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.07050.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wenhan Liu, Xinyu Ma, Weiwei Sun, Yutao Zhu, Yuchen Li, Dawei Yin, Zhicheng Dou</p><p><b>Upvotes:</b> 114</p><p><b>Summary:</b> Large Language Model (LLM) based listwise ranking has shown superior performance in many passage ranking tasks. With the development of Large Reasoning Models, many studies have demonstrated that step-by-step reasoning during test-time helps improve listwise ranking performance. However, due to the scarcity of reasoning-intensive training data, existing rerankers perform poorly in many complex ranking scenarios and the ranking ability of reasoning-intensive rerankers remains largely underdeveloped. In this paper, we first propose an automated reasoning-intensive training data synthesis framework, which sources training queries and passages from diverse domains and applies DeepSeek-R1 to generate high-quality training labels. A self-consistency data filtering mechanism is designed to ensure the data quality. To empower the listwise reranker with strong reasoning ability, we further propose a two-stage post-training approach, which includes a cold-start supervised fine-tuning (SFT) stage for reasoning pattern learning and a reinforcement learning (RL) stage for further ranking ability enhancement. During the RL stage, based on the nature of listwise ranking, we design a multi-view ranking reward, which is more effective than a ranking metric-based reward. Extensive experiments demonstrate that our trained reasoning-intensive reranker ReasonRank outperforms existing baselines significantly and also achieves much lower latency than pointwise reranker Rank1. Through further experiments, our ReasonRank has achieved state-of-the-art (SOTA) performance 40.6 on the BRIGHT leaderboard\footnote{https://brightbenchmark.github.io/.} Our codes are available at https://github.com/8421BCD/ReasonRank.</p> + https://arxiv.org/abs/2508.07050 + Sat, 09 Aug 2025 17:26:18 +0000 - A Survey on Latent Reasoning - https://arxiv.org/abs/2507.06203 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.06203.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Rui-Jie Zhu, Tianhao Peng, Tianhao Cheng, Xingwei Qu, Jinfa Huang, Dawei Zhu, Hao Wang, Kaiwen Xue, Xuanliang Zhang, Yong Shan, Tianle Cai, Taylor Kergan, Assel Kembay, Andrew Smith, Chenghua Lin, Binh Nguyen, Yuqi Pan, Yuhong Chou, Zefan Cai, Zhenhe Wu, Yongchi Zhao, Tianyu Liu, Jian Yang, Wangchunshu Zhou, Chujie Zheng, Chongxuan Li, Yuyin Zhou, Zhoujun Li, Zhaoxiang Zhang, Jiaheng Liu, Ge Zhang, Wenhao Huang, Jason Eshraghian</p><p><b>Upvotes:</b> 85</p><p><b>Summary:</b> Large Language Models (LLMs) have demonstrated impressive reasoning capabilities, especially when guided by explicit chain-of-thought (CoT) reasoning that verbalizes intermediate steps. While CoT improves both interpretability and accuracy, its dependence on natural language reasoning limits the model's expressive bandwidth. Latent reasoning tackles this bottleneck by performing multi-step inference entirely in the model's continuous hidden state, eliminating token-level supervision. To advance latent reasoning research, this survey provides a comprehensive overview of the emerging field of latent reasoning. We begin by examining the foundational role of neural network layers as the computational substrate for reasoning, highlighting how hierarchical representations support complex transformations. Next, we explore diverse latent reasoning methodologies, including activation-based recurrence, hidden state propagation, and fine-tuning strategies that compress or internalize explicit reasoning traces. Finally, we discuss advanced paradigms such as infinite-depth latent reasoning via masked diffusion models, which enable globally consistent and reversible reasoning processes. By unifying these perspectives, we aim to clarify the conceptual landscape of latent reasoning and chart future directions for research at the frontier of LLM cognition. An associated GitHub repository collecting the latest papers and repos is available at: https://github.com/multimodal-art-projection/LatentCoT-Horizon/.</p> - https://arxiv.org/abs/2507.06203 - Tue, 08 Jul 2025 17:29:07 +0000 + A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems + https://arxiv.org/abs/2508.07407 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.07407.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jinyuan Fang, Yanwen Peng, Xi Zhang, Yingxu Wang, Xinhao Yi, Guibin Zhang, Yi Xu, Bin Wu, Siwei Liu, Zihao Li, Zhaochun Ren, Nikos Aletras, Xi Wang, Han Zhou, Zaiqiao Meng</p><p><b>Upvotes:</b> 88</p><p><b>Summary:</b> Recent advances in large language models have sparked growing interest in AI agents capable of solving complex, real-world tasks. However, most existing agent systems rely on manually crafted configurations that remain static after deployment, limiting their ability to adapt to dynamic and evolving environments. To this end, recent research has explored agent evolution techniques that aim to automatically enhance agent systems based on interaction data and environmental feedback. This emerging direction lays the foundation for self-evolving AI agents, which bridge the static capabilities of foundation models with the continuous adaptability required by lifelong agentic systems. In this survey, we provide a comprehensive review of existing techniques for self-evolving agentic systems. Specifically, we first introduce a unified conceptual framework that abstracts the feedback loop underlying the design of self-evolving agentic systems. The framework highlights four key components: System Inputs, Agent System, Environment, and Optimisers, serving as a foundation for understanding and comparing different strategies. Based on this framework, we systematically review a wide range of self-evolving techniques that target different components of the agent system. We also investigate domain-specific evolution strategies developed for specialised fields such as biomedicine, programming, and finance, where optimisation objectives are tightly coupled with domain constraints. In addition, we provide a dedicated discussion on the evaluation, safety, and ethical considerations for self-evolving agentic systems, which are critical to ensuring their effectiveness and reliability. This survey aims to provide researchers and practitioners with a systematic understanding of self-evolving AI agents, laying the foundation for the development of more adaptive, autonomous, and lifelong agentic systems.</p> + https://arxiv.org/abs/2508.07407 + Sun, 10 Aug 2025 16:07:32 +0000 - Perception-Aware Policy Optimization for Multimodal Reasoning - https://arxiv.org/abs/2507.06448 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.06448.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhenhailong Wang, Xuehang Guo, Sofia Stoica, Haiyang Xu, Hongru Wang, Hyeonjeong Ha, Xiusi Chen, Yangyi Chen, Ming Yan, Fei Huang, Heng Ji</p><p><b>Upvotes:</b> 44</p><p><b>Summary:</b> Reinforcement Learning with Verifiable Rewards (RLVR) has proven to be a highly effective strategy for endowing Large Language Models (LLMs) with robust multi-step reasoning abilities. However, its design and optimizations remain tailored to purely textual domains, resulting in suboptimal performance when applied to multimodal reasoning tasks. In particular, we observe that a major source of error in current multimodal reasoning lies in the perception of visual inputs. To address this bottleneck, we propose Perception-Aware Policy Optimization (PAPO), a simple yet effective extension of GRPO that encourages the model to learn to perceive while learning to reason, entirely from internal supervision signals. Notably, PAPO does not rely on additional data curation, external reward models, or proprietary models. Specifically, we introduce the Implicit Perception Loss in the form of a KL divergence term to the GRPO objective, which, despite its simplicity, yields significant overall improvements (4.4%) on diverse multimodal benchmarks. The improvements are more pronounced, approaching 8.0%, on tasks with high vision dependency. We also observe a substantial reduction (30.5%) in perception errors, indicating improved perceptual capabilities with PAPO. We conduct comprehensive analysis of PAPO and identify a unique loss hacking issue, which we rigorously analyze and mitigate through a Double Entropy Loss. Overall, our work introduces a deeper integration of perception-aware supervision into RLVR learning objectives and lays the groundwork for a new RL framework that encourages visually grounded reasoning. Project page: https://mikewangwzhl.github.io/PAPO.</p> - https://arxiv.org/abs/2507.06448 - Tue, 08 Jul 2025 23:22:34 +0000 + CharacterShot: Controllable and Consistent 4D Character Animation + https://arxiv.org/abs/2508.07409 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.07409.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junyao Gao, Jiaxing Li, Wenran Liu, Yanhong Zeng, Fei Shen, Kai Chen, Yanan Sun, Cairong Zhao</p><p><b>Upvotes:</b> 38</p><p><b>Summary:</b> In this paper, we propose CharacterShot, a controllable and consistent 4D character animation framework that enables any individual designer to create dynamic 3D characters (i.e., 4D character animation) from a single reference character image and a 2D pose sequence. We begin by pretraining a powerful 2D character animation model based on a cutting-edge DiT-based image-to-video model, which allows for any 2D pose sequnce as controllable signal. We then lift the animation model from 2D to 3D through introducing dual-attention module together with camera prior to generate multi-view videos with spatial-temporal and spatial-view consistency. Finally, we employ a novel neighbor-constrained 4D gaussian splatting optimization on these multi-view videos, resulting in continuous and stable 4D character representations. Moreover, to improve character-centric performance, we construct a large-scale dataset Character4D, containing 13,115 unique characters with diverse appearances and motions, rendered from multiple viewpoints. Extensive experiments on our newly constructed benchmark, CharacterBench, demonstrate that our approach outperforms current state-of-the-art methods. Code, models, and datasets will be publicly available at https://github.com/Jeoyal/CharacterShot.</p> + https://arxiv.org/abs/2508.07409 + Sun, 10 Aug 2025 16:15:04 +0000 - LangSplatV2: High-dimensional 3D Language Gaussian Splatting with 450+ FPS - https://arxiv.org/abs/2507.07136 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.07136.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wanhua Li, Yujie Zhao, Minghan Qin, Yang Liu, Yuanhao Cai, Chuang Gan, Hanspeter Pfister</p><p><b>Upvotes:</b> 35</p><p><b>Summary:</b> In this paper, we introduce LangSplatV2, which achieves high-dimensional feature splatting at 476.2 FPS and 3D open-vocabulary text querying at 384.6 FPS for high-resolution images, providing a 42 times speedup and a 47 times boost over LangSplat respectively, along with improved query accuracy. LangSplat employs Gaussian Splatting to embed 2D CLIP language features into 3D, significantly enhancing speed and learning a precise 3D language field with SAM semantics. Such advancements in 3D language fields are crucial for applications that require language interaction within complex scenes. However, LangSplat does not yet achieve real-time inference performance (8.2 FPS), even with advanced A100 GPUs, severely limiting its broader application. In this paper, we first conduct a detailed time analysis of LangSplat, identifying the heavyweight decoder as the primary speed bottleneck. Our solution, LangSplatV2 assumes that each Gaussian acts as a sparse code within a global dictionary, leading to the learning of a 3D sparse coefficient field that entirely eliminates the need for a heavyweight decoder. By leveraging this sparsity, we further propose an efficient sparse coefficient splatting method with CUDA optimization, rendering high-dimensional feature maps at high quality while incurring only the time cost of splatting an ultra-low-dimensional feature. Our experimental results demonstrate that LangSplatV2 not only achieves better or competitive query accuracy but is also significantly faster. Codes and demos are available at our project page: https://langsplat-v2.github.io.</p> - https://arxiv.org/abs/2507.07136 - Wed, 09 Jul 2025 00:19:58 +0000 + Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization + https://arxiv.org/abs/2508.07629 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.07629.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhenpeng Su, Leiyu Pan, Xue Bai, Dening Liu, Guanting Dong, Jiaming Huang, Wenping Hu, Guorui Zhou</p><p><b>Upvotes:</b> 39</p><p><b>Summary:</b> We present Klear-Reasoner, a model with long reasoning capabilities that demonstrates careful deliberation during problem solving, achieving outstanding performance across multiple benchmarks. Although there are already many excellent works related to inference models in the current community, there are still many problems with reproducing high-performance inference models due to incomplete disclosure of training details. This report provides an in-depth analysis of the reasoning model, covering the entire post-training workflow from data preparation and long Chain-of-Thought supervised fine-tuning (long CoT SFT) to reinforcement learning (RL), along with detailed ablation studies for each experimental component. For SFT data, our experiments show that a small number of high-quality data sources are more effective than a large number of diverse data sources, and that difficult samples can achieve better results without accuracy filtering. In addition, we investigate two key issues with current clipping mechanisms in RL: Clipping suppresses critical exploration signals and ignores suboptimal trajectories. To address these challenges, we propose Gradient-Preserving clipping Policy Optimization (GPPO) that gently backpropagates gradients from clipped tokens. GPPO not only enhances the model's exploration capacity but also improves its efficiency in learning from negative samples. Klear-Reasoner exhibits exceptional reasoning abilities in mathematics and programming, scoring 90.5\% on AIME 2024, 83.2\% on AIME 2025, 66.0\% on LiveCodeBench V5 and 58.1\% on LiveCodeBench V6.</p> + https://arxiv.org/abs/2508.07629 + Mon, 11 Aug 2025 05:17:51 +0000 - Go to Zero: Towards Zero-shot Motion Generation with Million-scale Data - https://arxiv.org/abs/2507.07095 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.07095.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ke Fan, Shunlin Lu, Minyue Dai, Runyi Yu, Lixing Xiao, Zhiyang Dou, Junting Dong, Lizhuang Ma, Jingbo Wang</p><p><b>Upvotes:</b> 53</p><p><b>Summary:</b> Generating diverse and natural human motion sequences based on textual descriptions constitutes a fundamental and challenging research area within the domains of computer vision, graphics, and robotics. Despite significant advancements in this field, current methodologies often face challenges regarding zero-shot generalization capabilities, largely attributable to the limited size of training datasets. Moreover, the lack of a comprehensive evaluation framework impedes the advancement of this task by failing to identify directions for improvement. In this work, we aim to push text-to-motion into a new era, that is, to achieve the generalization ability of zero-shot. To this end, firstly, we develop an efficient annotation pipeline and introduce MotionMillion-the largest human motion dataset to date, featuring over 2,000 hours and 2 million high-quality motion sequences. Additionally, we propose MotionMillion-Eval, the most comprehensive benchmark for evaluating zero-shot motion generation. Leveraging a scalable architecture, we scale our model to 7B parameters and validate its performance on MotionMillion-Eval. Our results demonstrate strong generalization to out-of-domain and complex compositional motions, marking a significant step toward zero-shot human motion generation. The code is available at https://github.com/VankouF/MotionMillion-Codes.</p> - https://arxiv.org/abs/2507.07095 - Wed, 09 Jul 2025 17:52:04 +0000 + Stand-In: A Lightweight and Plug-and-Play Identity Control for Video Generation + https://arxiv.org/abs/2508.07901 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.07901.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bowen Xue, Qixin Yan, Wenjing Wang, Hao Liu, Chen Li</p><p><b>Upvotes:</b> 39</p><p><b>Summary:</b> Generating high-fidelity human videos that match user-specified identities is important yet challenging in the field of generative AI. Existing methods often rely on an excessive number of training parameters and lack compatibility with other AIGC tools. In this paper, we propose Stand-In, a lightweight and plug-and-play framework for identity preservation in video generation. Specifically, we introduce a conditional image branch into the pre-trained video generation model. Identity control is achieved through restricted self-attentions with conditional position mapping, and can be learned quickly with only 2000 pairs. Despite incorporating and training just sim1\% additional parameters, our framework achieves excellent results in video quality and identity preservation, outperforming other full-parameter training methods. Moreover, our framework can be seamlessly integrated for other tasks, such as subject-driven video generation, pose-referenced video generation, stylization, and face swapping.</p> + https://arxiv.org/abs/2508.07901 + Mon, 11 Aug 2025 12:17:38 +0000 - Vision-Language-Vision Auto-Encoder: Scalable Knowledge Distillation from Diffusion Models - https://arxiv.org/abs/2507.07104 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.07104.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tiezheng Zhang, Yitong Li, Yu-cheng Chou, Jieneng Chen, Alan Yuille, Chen Wei, Junfei Xiao</p><p><b>Upvotes:</b> 44</p><p><b>Summary:</b> Building state-of-the-art Vision-Language Models (VLMs) with strong captioning capabilities typically necessitates training on billions of high-quality image-text pairs, requiring millions of GPU hours. This paper introduces the Vision-Language-Vision (VLV) auto-encoder framework, which strategically leverages key pretrained components: a vision encoder, the decoder of a Text-to-Image (T2I) diffusion model, and subsequently, a Large Language Model (LLM). Specifically, we establish an information bottleneck by regularizing the language representation space, achieved through freezing the pretrained T2I diffusion decoder. Our VLV pipeline effectively distills knowledge from the text-conditioned diffusion model using continuous embeddings, demonstrating comprehensive semantic understanding via high-quality reconstructions. Furthermore, by fine-tuning a pretrained LLM to decode the intermediate language representations into detailed descriptions, we construct a state-of-the-art (SoTA) captioner comparable to leading models like GPT-4o and Gemini 2.0 Flash. Our method demonstrates exceptional cost-efficiency and significantly reduces data requirements; by primarily utilizing single-modal images for training and maximizing the utility of existing pretrained models (image encoder, T2I diffusion model, and LLM), it circumvents the need for massive paired image-text datasets, keeping the total training expenditure under $1,000 USD.</p> - https://arxiv.org/abs/2507.07104 - Wed, 09 Jul 2025 17:59:04 +0000 + MolmoAct: Action Reasoning Models that can Reason in Space + https://arxiv.org/abs/2508.07917 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.07917.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jason Lee, Jiafei Duan, Haoquan Fang, Yuquan Deng, Shuo Liu, Boyang Li, Bohan Fang, Jieyu Zhang, Yi Ru Wang, Sangho Lee, Winson Han, Wilbert Pumacay, Angelica Wu, Rose Hendrix, Karen Farley, Eli VanderBilt, Ali Farhadi, Dieter Fox, Ranjay Krishna</p><p><b>Upvotes:</b> 40</p><p><b>Summary:</b> Reasoning is central to purposeful action, yet most robotic foundation models map perception and instructions directly to control, which limits adaptability, generalization, and semantic grounding. We introduce Action Reasoning Models (ARMs), a class of vision-language-action models that integrate perception, planning, and control through a structured three-stage pipeline. Our model, MolmoAct, encodes observations and instructions into depth-aware perception tokens, generates mid-level spatial plans as editable trajectory traces, and predicts precise low-level actions, enabling explainable and steerable behavior. MolmoAct-7B-D achieves strong performance across simulation and real-world settings: 70.5% zero-shot accuracy on SimplerEnv Visual Matching tasks, surpassing closed-source Pi-0 and GR00T N1; 86.6% average success on LIBERO, including an additional 6.3% gain over ThinkAct on long-horizon tasks; and in real-world fine-tuning, an additional 10% (single-arm) and an additional 22.7% (bimanual) task progression over Pi-0-FAST. It also outperforms baselines by an additional 23.3% on out-of-distribution generalization and achieves top human-preference scores for open-ended instruction following and trajectory steering. Furthermore, we release, for the first time, the MolmoAct Dataset -- a mid-training robot dataset comprising over 10,000 high quality robot trajectories across diverse scenarios and tasks. Training with this dataset yields an average 5.5% improvement in general performance over the base model. We release all model weights, training code, our collected dataset, and our action reasoning dataset, establishing MolmoAct as both a state-of-the-art robotics foundation model and an open blueprint for building ARMs that transform perception into purposeful action through structured reasoning. Blogpost: https://allenai.org/blog/molmoact</p> + https://arxiv.org/abs/2508.07917 + Mon, 11 Aug 2025 12:32:45 +0000 - 4KAgent: Agentic Any Image to 4K Super-Resolution - https://arxiv.org/abs/2507.07105 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.07105.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yushen Zuo, Qi Zheng, Mingyang Wu, Xinrui Jiang, Renjie Li, Jian Wang, Yide Zhang, Gengchen Mai, Lihong V. Wang, James Zou, Xiaoyu Wang, Ming-Hsuan Yang, Zhengzhong Tu</p><p><b>Upvotes:</b> 96</p><p><b>Summary:</b> We present 4KAgent, a unified agentic super-resolution generalist system designed to universally upscale any image to 4K resolution (and even higher, if applied iteratively). Our system can transform images from extremely low resolutions with severe degradations, for example, highly distorted inputs at 256x256, into crystal-clear, photorealistic 4K outputs. 4KAgent comprises three core components: (1) Profiling, a module that customizes the 4KAgent pipeline based on bespoke use cases; (2) A Perception Agent, which leverages vision-language models alongside image quality assessment experts to analyze the input image and make a tailored restoration plan; and (3) A Restoration Agent, which executes the plan, following a recursive execution-reflection paradigm, guided by a quality-driven mixture-of-expert policy to select the optimal output for each step. Additionally, 4KAgent embeds a specialized face restoration pipeline, significantly enhancing facial details in portrait and selfie photos. We rigorously evaluate our 4KAgent across 11 distinct task categories encompassing a total of 26 diverse benchmarks, setting new state-of-the-art on a broad spectrum of imaging domains. Our evaluations cover natural images, portrait photos, AI-generated content, satellite imagery, fluorescence microscopy, and medical imaging like fundoscopy, ultrasound, and X-ray, demonstrating superior performance in terms of both perceptual (e.g., NIQE, MUSIQ) and fidelity (e.g., PSNR) metrics. By establishing a novel agentic paradigm for low-level vision tasks, we aim to catalyze broader interest and innovation within vision-centric autonomous agents across diverse research communities. We will release all the code, models, and results at: https://4kagent.github.io.</p> - https://arxiv.org/abs/2507.07105 - Wed, 09 Jul 2025 17:59:19 +0000 + Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL + https://arxiv.org/abs/2508.07976 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.07976.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiaxuan Gao, Wei Fu, Minyang Xie, Shusheng Xu, Chuyi He, Zhiyu Mei, Banghua Zhu, Yi Wu</p><p><b>Upvotes:</b> 48</p><p><b>Summary:</b> Recent advancements in LLM-based agents have demonstrated remarkable capabilities in handling complex, knowledge-intensive tasks by integrating external tools. Among diverse choices of tools, search tools play a pivotal role in accessing vast external knowledge. However, open-source agents still fall short of achieving expert-level Search Intelligence, the ability to resolve ambiguous queries, generate precise searches, analyze results, and conduct thorough exploration. Existing approaches fall short in scalability, efficiency, and data quality. For example, small turn limits in existing online RL methods, e.g. <=10, restrict complex strategy learning. This paper introduces ASearcher, an open-source project for large-scale RL training of search agents. Our key contributions include: (1) Scalable fully asynchronous RL training that enables long-horizon search while maintaining high training efficiency. (2) A prompt-based LLM agent that autonomously synthesizes high-quality and challenging QAs, creating a large-scale QA dataset. Through RL training, our prompt-based QwQ-32B agent achieves substantial improvements, with 46.7% and 20.8% Avg@4 gains on xBench and GAIA, respectively. Notably, our agent exhibits extreme long-horizon search, with tool calls exceeding 40 turns and output tokens exceeding 150k during training time. With a simple agent design and no external LLMs, ASearcher-Web-QwQ achieves Avg@4 scores of 42.1 on xBench and 52.8 on GAIA, surpassing existing open-source 32B agents. We open-source our models, training data, and codes in https://github.com/inclusionAI/ASearcher.</p> + https://arxiv.org/abs/2508.07976 + Mon, 11 Aug 2025 13:36:57 +0000 - MIRIX: Multi-Agent Memory System for LLM-Based Agents - https://arxiv.org/abs/2507.07957 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.07957.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yu Wang, Xi Chen</p><p><b>Upvotes:</b> 60</p><p><b>Summary:</b> Although memory capabilities of AI agents are gaining increasing attention, existing solutions remain fundamentally limited. Most rely on flat, narrowly scoped memory components, constraining their ability to personalize, abstract, and reliably recall user-specific information over time. To this end, we introduce MIRIX, a modular, multi-agent memory system that redefines the future of AI memory by solving the field's most critical challenge: enabling language models to truly remember. Unlike prior approaches, MIRIX transcends text to embrace rich visual and multimodal experiences, making memory genuinely useful in real-world scenarios. MIRIX consists of six distinct, carefully structured memory types: Core, Episodic, Semantic, Procedural, Resource Memory, and Knowledge Vault, coupled with a multi-agent framework that dynamically controls and coordinates updates and retrieval. This design enables agents to persist, reason over, and accurately retrieve diverse, long-term user data at scale. We validate MIRIX in two demanding settings. First, on ScreenshotVQA, a challenging multimodal benchmark comprising nearly 20,000 high-resolution computer screenshots per sequence, requiring deep contextual understanding and where no existing memory systems can be applied, MIRIX achieves 35% higher accuracy than the RAG baseline while reducing storage requirements by 99.9%. Second, on LOCOMO, a long-form conversation benchmark with single-modal textual input, MIRIX attains state-of-the-art performance of 85.4%, far surpassing existing baselines. These results show that MIRIX sets a new performance standard for memory-augmented LLM agents. To allow users to experience our memory system, we provide a packaged application powered by MIRIX. It monitors the screen in real time, builds a personalized memory base, and offers intuitive visualization and secure local storage to ensure privacy.</p> - https://arxiv.org/abs/2507.07957 - Thu, 10 Jul 2025 17:40:11 +0000 + Omni-Effects: Unified and Spatially-Controllable Visual Effects Generation + https://arxiv.org/abs/2508.07981 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.07981.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fangyuan Mao, Aiming Hao, Jintao Chen, Dongxia Liu, Xiaokun Feng, Jiashu Zhu, Meiqi Wu, Chubin Chen, Jiahong Wu, Xiangxiang Chu</p><p><b>Upvotes:</b> 58</p><p><b>Summary:</b> Visual effects (VFX) are essential visual enhancements fundamental to modern cinematic production. Although video generation models offer cost-efficient solutions for VFX production, current methods are constrained by per-effect LoRA training, which limits generation to single effects. This fundamental limitation impedes applications that require spatially controllable composite effects, i.e., the concurrent generation of multiple effects at designated locations. However, integrating diverse effects into a unified framework faces major challenges: interference from effect variations and spatial uncontrollability during multi-VFX joint training. To tackle these challenges, we propose Omni-Effects, a first unified framework capable of generating prompt-guided effects and spatially controllable composite effects. The core of our framework comprises two key innovations: (1) LoRA-based Mixture of Experts (LoRA-MoE), which employs a group of expert LoRAs, integrating diverse effects within a unified model while effectively mitigating cross-task interference. (2) Spatial-Aware Prompt (SAP) incorporates spatial mask information into the text token, enabling precise spatial control. Furthermore, we introduce an Independent-Information Flow (IIF) module integrated within the SAP, isolating the control signals corresponding to individual effects to prevent any unwanted blending. To facilitate this research, we construct a comprehensive VFX dataset Omni-VFX via a novel data collection pipeline combining image editing and First-Last Frame-to-Video (FLF2V) synthesis, and introduce a dedicated VFX evaluation framework for validating model performance. Extensive experiments demonstrate that Omni-Effects achieves precise spatial control and diverse effect generation, enabling users to specify both the category and location of desired effects.</p> + https://arxiv.org/abs/2508.07981 + Mon, 11 Aug 2025 13:41:24 +0000 - Scaling RL to Long Videos - https://arxiv.org/abs/2507.07966 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.07966.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yukang Chen, Wei Huang, Baifeng Shi, Qinghao Hu, Hanrong Ye, Ligeng Zhu, Zhijian Liu, Pavlo Molchanov, Jan Kautz, Xiaojuan Qi, Sifei Liu, Hongxu Yin, Yao Lu, Song Han</p><p><b>Upvotes:</b> 151</p><p><b>Summary:</b> We introduce a full-stack framework that scales up reasoning in vision-language models (VLMs) to long videos, leveraging reinforcement learning. We address the unique challenges of long video reasoning by integrating three critical components: (1) a large-scale dataset, LongVideo-Reason, comprising 52K long video QA pairs with high-quality reasoning annotations across diverse domains such as sports, games, and vlogs; (2) a two-stage training pipeline that extends VLMs with chain-of-thought supervised fine-tuning (CoT-SFT) and reinforcement learning (RL); and (3) a training infrastructure for long video RL, named Multi-modal Reinforcement Sequence Parallelism (MR-SP), which incorporates sequence parallelism and a vLLM-based engine tailored for long video, using cached video embeddings for efficient rollout and prefilling. In experiments, LongVILA-R1-7B achieves strong performance on long video QA benchmarks such as VideoMME. It also outperforms Video-R1-7B and even matches Gemini-1.5-Pro across temporal reasoning, goal and purpose reasoning, spatial reasoning, and plot reasoning on our LongVideo-Reason-eval benchmark. Notably, our MR-SP system achieves up to 2.1x speedup on long video RL training. LongVILA-R1 demonstrates consistent performance gains as the number of input video frames scales. LongVILA-R1 marks a firm step towards long video reasoning in VLMs. In addition, we release our training system for public availability that supports RL training on various modalities (video, text, and audio), various models (VILA and Qwen series), and even image and video generation models. On a single A100 node (8 GPUs), it supports RL training on hour-long videos (e.g., 3,600 frames / around 256k tokens).</p> - https://arxiv.org/abs/2507.07966 - Thu, 10 Jul 2025 17:47:40 +0000 + WideSearch: Benchmarking Agentic Broad Info-Seeking + https://arxiv.org/abs/2508.07999 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.07999.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ryan Wong, Jiawei Wang, Junjie Zhao, Li Chen, Yan Gao, Long Zhang, Xuan Zhou, Zuo Wang, Kai Xiang, Ge Zhang, Wenhao Huang, Yang Wang, Ke Wang</p><p><b>Upvotes:</b> 105</p><p><b>Summary:</b> From professional research to everyday planning, many tasks are bottlenecked by wide-scale information seeking, which is more repetitive than cognitively complex. With the rapid development of Large Language Models (LLMs), automated search agents powered by LLMs offer a promising solution to liberate humans from this tedious work. However, the capability of these agents to perform such "wide-context" collection reliably and completely remains largely unevaluated due to a lack of suitable benchmarks. To bridge this gap, we introduce WideSearch, a new benchmark engineered to evaluate agent reliability on these large-scale collection tasks. The benchmark features 200 manually curated questions (100 in English, 100 in Chinese) from over 15 diverse domains, grounded in real user queries. Each task requires agents to collect large-scale atomic information, which could be verified one by one objectively, and arrange it into a well-organized output. A rigorous five-stage quality control pipeline ensures the difficulty, completeness, and verifiability of the dataset. We benchmark over 10 state-of-the-art agentic search systems, including single-agent, multi-agent frameworks, and end-to-end commercial systems. Most systems achieve overall success rates near 0\%, with the best performer reaching just 5\%. However, given sufficient time, cross-validation by multiple human testers can achieve a near 100\% success rate. These results demonstrate that present search agents have critical deficiencies in large-scale information seeking, underscoring urgent areas for future research and development in agentic search. Our dataset, evaluation pipeline, and benchmark results have been publicly released at https://widesearch-seed.github.io/</p> + https://arxiv.org/abs/2508.07999 + Mon, 11 Aug 2025 14:03:09 +0000 - OST-Bench: Evaluating the Capabilities of MLLMs in Online Spatio-temporal Scene Understanding - https://arxiv.org/abs/2507.07984 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.07984.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> JingLi Lin, Chenming Zhu, Runsen Xu, Xiaohan Mao, Xihui Liu, Tai Wang, Jiangmiao Pang</p><p><b>Upvotes:</b> 39</p><p><b>Summary:</b> Recent advances in multimodal large language models (MLLMs) have shown remarkable capabilities in integrating vision and language for complex reasoning. While most existing benchmarks evaluate models under offline settings with a fixed set of pre-recorded inputs, we introduce OST-Bench, a benchmark designed to evaluate Online Spatio-Temporal understanding from the perspective of an agent actively exploring a scene. The Online aspect emphasizes the need to process and reason over incrementally acquired observations, while the Spatio-Temporal component requires integrating current visual inputs with historical memory to support dynamic spatial reasoning. OST-Bench better reflects the challenges of real-world embodied perception. Built on an efficient data collection pipeline, OST-Bench consists of 1.4k scenes and 10k question-answer pairs collected from ScanNet, Matterport3D, and ARKitScenes. We evaluate several leading MLLMs on OST-Bench and observe that they fall short on tasks requiring complex spatio-temporal reasoning. Under the online setting, their accuracy declines as the exploration horizon extends and the memory grows. Through further experimental analysis, we identify common error patterns across models and find that both complex clue-based spatial reasoning demands and long-term memory retrieval requirements significantly drop model performance along two separate axes, highlighting the core challenges that must be addressed to improve online embodied reasoning. To foster further research and development in the field, our codes, dataset, and benchmark are available. Our project page is: https://rbler1234.github.io/OSTBench.github.io/</p> - https://arxiv.org/abs/2507.07984 - Thu, 10 Jul 2025 17:56:07 +0000 + Matrix-3D: Omnidirectional Explorable 3D World Generation + https://arxiv.org/abs/2508.08086 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.08086.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhongqi Yang, Wenhang Ge, Yuqi Li, Jiaqi Chen, Haoyuan Li, Mengyin An, Fei Kang, Hua Xue, Baixin Xu, Yuyang Yin, Eric Li, Yang Liu, Yikai Wang, Hao-Xiang Guo, Yahui Zhou</p><p><b>Upvotes:</b> 70</p><p><b>Summary:</b> Explorable 3D world generation from a single image or text prompt forms a cornerstone of spatial intelligence. Recent works utilize video model to achieve wide-scope and generalizable 3D world generation. However, existing approaches often suffer from a limited scope in the generated scenes. In this work, we propose Matrix-3D, a framework that utilize panoramic representation for wide-coverage omnidirectional explorable 3D world generation that combines conditional video generation and panoramic 3D reconstruction. We first train a trajectory-guided panoramic video diffusion model that employs scene mesh renders as condition, to enable high-quality and geometrically consistent scene video generation. To lift the panorama scene video to 3D world, we propose two separate methods: (1) a feed-forward large panorama reconstruction model for rapid 3D scene reconstruction and (2) an optimization-based pipeline for accurate and detailed 3D scene reconstruction. To facilitate effective training, we also introduce the Matrix-Pano dataset, the first large-scale synthetic collection comprising 116K high-quality static panoramic video sequences with depth and trajectory annotations. Extensive experiments demonstrate that our proposed framework achieves state-of-the-art performance in panoramic video generation and 3D world generation. See more in https://matrix-3d.github.io.</p> + https://arxiv.org/abs/2508.08086 + Mon, 11 Aug 2025 15:29:57 +0000 - Multi-Granular Spatio-Temporal Token Merging for Training-Free Acceleration of Video LLMs - https://arxiv.org/abs/2507.07990 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.07990.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jeongseok Hyun, Sukjun Hwang, Su Ho Han, Taeoh Kim, Inwoong Lee, Dongyoon Wee, Joon-Young Lee, Seon Joo Kim, Minho Shim</p><p><b>Upvotes:</b> 44</p><p><b>Summary:</b> Video large language models (LLMs) achieve strong video understanding by leveraging a large number of spatio-temporal tokens, but suffer from quadratic computational scaling with token count. To address this, we propose a training-free spatio-temporal token merging method, named STTM. Our key insight is to exploit local spatial and temporal redundancy in video data which has been overlooked in prior work. STTM first transforms each frame into multi-granular spatial tokens using a coarse-to-fine search over a quadtree structure, then performs directed pairwise merging across the temporal dimension. This decomposed merging approach outperforms existing token reduction methods across six video QA benchmarks. Notably, STTM achieves a 2times speed-up with only a 0.5% accuracy drop under a 50% token budget, and a 3times speed-up with just a 2% drop under a 30% budget. Moreover, STTM is query-agnostic, allowing KV cache reuse across different questions for the same video. The project page is available at https://www.jshyun.me/projects/sttm.</p> - https://arxiv.org/abs/2507.07990 - Thu, 10 Jul 2025 17:59:02 +0000 + Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning + https://arxiv.org/abs/2508.08221 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.08221.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zihe Liu, Jiashun Liu, Yancheng He, Weixun Wang, Jiaheng Liu, Ling Pan, Xinyu Hu, Shaopan Xiong, Ju Huang, Jian Hu, Shengyi Huang, Siran Yang, Jiamang Wang, Wenbo Su, Bo Zheng</p><p><b>Upvotes:</b> 42</p><p><b>Summary:</b> Reinforcement learning for LLM reasoning has rapidly emerged as a prominent research area, marked by a significant surge in related studies on both algorithmic innovations and practical applications. Despite this progress, several critical challenges remain, including the absence of standardized guidelines for employing RL techniques and a fragmented understanding of their underlying mechanisms. Additionally, inconsistent experimental settings, variations in training data, and differences in model initialization have led to conflicting conclusions, obscuring the key characteristics of these techniques and creating confusion among practitioners when selecting appropriate techniques. This paper systematically reviews widely adopted RL techniques through rigorous reproductions and isolated evaluations within a unified open-source framework. We analyze the internal mechanisms, applicable scenarios, and core principles of each technique through fine-grained experiments, including datasets of varying difficulty, model sizes, and architectures. Based on these insights, we present clear guidelines for selecting RL techniques tailored to specific setups, and provide a reliable roadmap for practitioners navigating the RL for the LLM domain. Finally, we reveal that a minimalist combination of two techniques can unlock the learning capability of critic-free policies using vanilla PPO loss. The results demonstrate that our simple combination consistently improves performance, surpassing strategies like GRPO and DAPO.</p> + https://arxiv.org/abs/2508.08221 + Mon, 11 Aug 2025 17:39:45 +0000 - Traceable Evidence Enhanced Visual Grounded Reasoning: Evaluation and Methodology - https://arxiv.org/abs/2507.07999 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.07999.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haochen Wang, Xiangtai Li, Zilong Huang, Anran Wang, Jiacong Wang, Tao Zhang, Jiani Zheng, Sule Bai, Zijian Kang, Jiashi Feng, Zhuochen Wang, Zhaoxiang Zhang</p><p><b>Upvotes:</b> 46</p><p><b>Summary:</b> Models like OpenAI-o3 pioneer visual grounded reasoning by dynamically referencing visual regions, just like human "thinking with images". However, no benchmark exists to evaluate these capabilities holistically. To bridge this gap, we propose TreeBench (Traceable Evidence Evaluation Benchmark), a diagnostic benchmark built on three principles: (1) focused visual perception of subtle targets in complex scenes, (2) traceable evidence via bounding box evaluation, and (3) second-order reasoning to test object interactions and spatial hierarchies beyond simple object localization. Prioritizing images with dense objects, we initially sample 1K high-quality images from SA-1B, and incorporate eight LMM experts to manually annotate questions, candidate options, and answers for each image. After three stages of quality control, TreeBench consists of 405 challenging visual question-answering pairs, even the most advanced models struggle with this benchmark, where none of them reach 60% accuracy, e.g., OpenAI-o3 scores only 54.87. Furthermore, we introduce TreeVGR (Traceable Evidence Enhanced Visual Grounded Reasoning), a training paradigm to supervise localization and reasoning jointly with reinforcement learning, enabling accurate localizations and explainable reasoning pathways. Initialized from Qwen2.5-VL-7B, it improves V* Bench (+16.8), MME-RealWorld (+12.6), and TreeBench (+13.4), proving traceability is key to advancing vision-grounded reasoning. The code is available at https://github.com/Haochen-Wang409/TreeVGR.</p> - https://arxiv.org/abs/2507.07999 - Thu, 10 Jul 2025 17:59:58 +0000 + ODYSSEY: Open-World Quadrupeds Exploration and Manipulation for Long-Horizon Tasks + https://arxiv.org/abs/2508.08240 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.08240.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kaijun Wang, Liqin Lu, Mingyu Liu, Jianuo Jiang, Zeju Li, Bolin Zhang, Wancai Zheng, Xinyi Yu, Hao Chen, Chunhua Shen</p><p><b>Upvotes:</b> 43</p><p><b>Summary:</b> Language-guided long-horizon mobile manipulation has long been a grand challenge in embodied semantic reasoning, generalizable manipulation, and adaptive locomotion. Three fundamental limitations hinder progress: First, although large language models have improved spatial reasoning and task planning through semantic priors, existing implementations remain confined to tabletop scenarios, failing to address the constrained perception and limited actuation ranges of mobile platforms. Second, current manipulation strategies exhibit insufficient generalization when confronted with the diverse object configurations encountered in open-world environments. Third, while crucial for practical deployment, the dual requirement of maintaining high platform maneuverability alongside precise end-effector control in unstructured settings remains understudied. In this work, we present ODYSSEY, a unified mobile manipulation framework for agile quadruped robots equipped with manipulators, which seamlessly integrates high-level task planning with low-level whole-body control. To address the challenge of egocentric perception in language-conditioned tasks, we introduce a hierarchical planner powered by a vision-language model, enabling long-horizon instruction decomposition and precise action execution. At the control level, our novel whole-body policy achieves robust coordination across challenging terrains. We further present the first benchmark for long-horizon mobile manipulation, evaluating diverse indoor and outdoor scenarios. Through successful sim-to-real transfer, we demonstrate the system's generalization and robustness in real-world deployments, underscoring the practicality of legged manipulators in unstructured environments. Our work advances the feasibility of generalized robotic assistants capable of complex, dynamic tasks. Our project page: https://kaijwang.github.io/odyssey.github.io/</p> + https://arxiv.org/abs/2508.08240 + Mon, 11 Aug 2025 17:54:31 +0000 - Upsample What Matters: Region-Adaptive Latent Sampling for Accelerated Diffusion Transformers - https://arxiv.org/abs/2507.08422 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.08422.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wongi Jeong, Kyungryeol Lee, Hoigi Seo, Se Young Chun</p><p><b>Upvotes:</b> 35</p><p><b>Summary:</b> Diffusion transformers have emerged as an alternative to U-net-based diffusion models for high-fidelity image and video generation, offering superior scalability. However, their heavy computation remains a major obstacle to real-world deployment. Existing acceleration methods primarily exploit the temporal dimension such as reusing cached features across diffusion timesteps. Here, we propose Region-Adaptive Latent Upsampling (RALU), a training-free framework that accelerates inference along spatial dimension. RALU performs mixed-resolution sampling across three stages: 1) low-resolution denoising latent diffusion to efficiently capture global semantic structure, 2) region-adaptive upsampling on specific regions prone to artifacts at full-resolution, and 3) all latent upsampling at full-resolution for detail refinement. To stabilize generations across resolution transitions, we leverage noise-timestep rescheduling to adapt the noise level across varying resolutions. Our method significantly reduces computation while preserving image quality by achieving up to 7.0times speed-up on FLUX and 3.0times on Stable Diffusion 3 with minimal degradation. Furthermore, RALU is complementary to existing temporal accelerations such as caching methods, thus can be seamlessly integrated to further reduce inference latency without compromising generation quality.</p> - https://arxiv.org/abs/2507.08422 - Fri, 11 Jul 2025 09:07:43 +0000 + Mol-R1: Towards Explicit Long-CoT Reasoning in Molecule Discovery + https://arxiv.org/abs/2508.08401 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.08401.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiatong Li, Weida Wang, Qinggang Zhang, Junxian Li, Di Zhang, Changmeng Zheng, Shufei Zhang, Xiaoyong Wei, Qing Li</p><p><b>Upvotes:</b> 42</p><p><b>Summary:</b> Large language models (LLMs), especially Explicit Long Chain-of-Thought (CoT) reasoning models like DeepSeek-R1 and QWQ, have demonstrated powerful reasoning capabilities, achieving impressive performance in commonsense reasoning and mathematical inference. Despite their effectiveness, Long-CoT reasoning models are often criticized for their limited ability and low efficiency in knowledge-intensive domains such as molecule discovery. Success in this field requires a precise understanding of domain knowledge, including molecular structures and chemical principles, which is challenging due to the inherent complexity of molecular data and the scarcity of high-quality expert annotations. To bridge this gap, we introduce Mol-R1, a novel framework designed to improve explainability and reasoning performance of R1-like Explicit Long-CoT reasoning LLMs in text-based molecule generation. Our approach begins with a high-quality reasoning dataset curated through Prior Regulation via In-context Distillation (PRID), a dedicated distillation strategy to effectively generate paired reasoning traces guided by prior regulations. Building upon this, we introduce MoIA, Molecular Iterative Adaptation, a sophisticated training strategy that iteratively combines Supervised Fine-tuning (SFT) with Reinforced Policy Optimization (RPO), tailored to boost the reasoning performance of R1-like reasoning models for molecule discovery. Finally, we examine the performance of Mol-R1 in the text-based molecule reasoning generation task, showing superior performance against existing baselines.</p> + https://arxiv.org/abs/2508.08401 + Mon, 11 Aug 2025 18:50:05 +0000 - Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Image Generation - https://arxiv.org/abs/2507.08441 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.08441.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Anlin Zheng, Xin Wen, Xuanyang Zhang, Chuofan Ma, Tiancai Wang, Gang Yu, Xiangyu Zhang, Xiaojuan Qi</p><p><b>Upvotes:</b> 59</p><p><b>Summary:</b> Leveraging the powerful representations of pre-trained vision foundation models -- traditionally used for visual comprehension -- we explore a novel direction: building an image tokenizer directly atop such models, a largely underexplored area. Specifically, we employ a frozen vision foundation model as the encoder of our tokenizer. To enhance its effectiveness, we introduce two key components: (1) a region-adaptive quantization framework that reduces redundancy in the pre-trained features on regular 2D grids, and (2) a semantic reconstruction objective that aligns the tokenizer's outputs with the foundation model's representations to preserve semantic fidelity. Based on these designs, our proposed image tokenizer, VFMTok, achieves substantial improvements in image reconstruction and generation quality, while also enhancing token efficiency. It further boosts autoregressive (AR) generation -- achieving a gFID of 2.07 on ImageNet benchmarks, while accelerating model convergence by three times, and enabling high-fidelity class-conditional synthesis without the need for classifier-free guidance (CFG). The code will be released publicly to benefit the community.</p> - https://arxiv.org/abs/2507.08441 - Fri, 11 Jul 2025 09:32:45 +0000 + VertexRegen: Mesh Generation with Continuous Level of Detail + https://arxiv.org/abs/2508.09062 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.09062.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiang Zhang, Yawar Siddiqui, Armen Avetisyan, Chris Xie, Jakob Engel, Henry Howard-Jenkins</p><p><b>Upvotes:</b> 35</p><p><b>Summary:</b> We introduce VertexRegen, a novel mesh generation framework that enables generation at a continuous level of detail. Existing autoregressive methods generate meshes in a partial-to-complete manner and thus intermediate steps of generation represent incomplete structures. VertexRegen takes inspiration from progressive meshes and reformulates the process as the reversal of edge collapse, i.e. vertex split, learned through a generative model. Experimental results demonstrate that VertexRegen produces meshes of comparable quality to state-of-the-art methods while uniquely offering anytime generation with the flexibility to halt at any step to yield valid meshes with varying levels of detail.</p> + https://arxiv.org/abs/2508.09062 + Tue, 12 Aug 2025 16:25:46 +0000 - CLiFT: Compressive Light-Field Tokens for Compute-Efficient and Adaptive Neural Rendering - https://arxiv.org/abs/2507.08776 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.08776.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhengqing Wang, Yuefan Wu, Jiacheng Chen, Fuyang Zhang, Yasutaka Furukawa</p><p><b>Upvotes:</b> 53</p><p><b>Summary:</b> This paper proposes a neural rendering approach that represents a scene as "compressed light-field tokens (CLiFTs)", retaining rich appearance and geometric information of a scene. CLiFT enables compute-efficient rendering by compressed tokens, while being capable of changing the number of tokens to represent a scene or render a novel view with one trained network. Concretely, given a set of images, multi-view encoder tokenizes the images with the camera poses. Latent-space K-means selects a reduced set of rays as cluster centroids using the tokens. The multi-view ``condenser'' compresses the information of all the tokens into the centroid tokens to construct CLiFTs. At test time, given a target view and a compute budget (i.e., the number of CLiFTs), the system collects the specified number of nearby tokens and synthesizes a novel view using a compute-adaptive renderer. Extensive experiments on RealEstate10K and DL3DV datasets quantitatively and qualitatively validate our approach, achieving significant data reduction with comparable rendering quality and the highest overall rendering score, while providing trade-offs of data size, rendering quality, and rendering speed.</p> - https://arxiv.org/abs/2507.08776 - Fri, 11 Jul 2025 17:38:52 +0000 + Complex Logical Instruction Generation + https://arxiv.org/abs/2508.09125 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.09125.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mian Zhang, Shujian Liu, Sixun Dong, Ming Yin, Yebowen Hu, Xun Wang, Steven Ma, Song Wang, Sathish Reddy Indurthi, Haoyun Deng, Zhiyu Zoey Chen, Kaiqiang Song</p><p><b>Upvotes:</b> 38</p><p><b>Summary:</b> Instruction following has catalyzed the recent era of Large Language Models (LLMs) and is the foundational skill underpinning more advanced capabilities such as reasoning and agentic behaviors. As tasks grow more challenging, the logic structures embedded in natural language instructions becomes increasingly intricate. However, how well LLMs perform on such logic-rich instructions remains under-explored. We propose LogicIFGen and LogicIFEval. LogicIFGen is a scalable, automated framework for generating verifiable instructions from code functions, which can naturally express rich logic such as conditionals, nesting, recursion, and function calls. We further curate a collection of complex code functions and use LogicIFGen to construct LogicIFEval, a benchmark comprising 426 verifiable logic-rich instructions. Our experiments demonstrate that current state-of-the-art LLMs still struggle to correctly follow the instructions in LogicIFEval. Most LLMs can only follow fewer than 60% of the instructions, revealing significant deficiencies in the instruction-following ability. Code and Benchmark: https://github.com/mianzhang/LogicIF</p> + https://arxiv.org/abs/2508.09125 + Tue, 12 Aug 2025 17:54:27 +0000 - KV Cache Steering for Inducing Reasoning in Small Language Models - https://arxiv.org/abs/2507.08799 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.08799.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Max Belitsky, Dawid J. Kopiczko, Michael Dorkenwald, M. Jehanzeb Mirza, Cees G. M. Snoek, Yuki M. Asano</p><p><b>Upvotes:</b> 39</p><p><b>Summary:</b> We propose cache steering, a lightweight method for implicit steering of language models via a one-shot intervention applied directly to the key-value cache. To validate its effectiveness, we apply cache steering to induce chain-of-thought reasoning in small language models. Our approach leverages GPT-4o-generated reasoning traces to construct steering vectors that shift model behavior toward more explicit, multi-step reasoning without fine-tuning or prompt modifications. Experimental evaluations on diverse reasoning benchmarks demonstrate that cache steering improves both the qualitative structure of model reasoning and quantitative task performance. Compared to prior activation steering techniques that require continuous interventions, our one-shot cache steering offers substantial advantages in terms of hyperparameter stability, inference-time efficiency, and ease of integration, making it a more robust and practical solution for controlled generation.</p> - https://arxiv.org/abs/2507.08799 - Fri, 11 Jul 2025 17:59:36 +0000 + Time Is a Feature: Exploiting Temporal Dynamics in Diffusion Language Models + https://arxiv.org/abs/2508.09138 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.09138.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wen Wang, Bozhen Fang, Chenchen Jing, Yongliang Shen, Yangyi Shen, Qiuyu Wang, Hao Ouyang, Hao Chen, Chunhua Shen</p><p><b>Upvotes:</b> 36</p><p><b>Summary:</b> Diffusion large language models (dLLMs) generate text through iterative denoising, yet current decoding strategies discard rich intermediate predictions in favor of the final output. Our work here reveals a critical phenomenon, temporal oscillation, where correct answers often emerge in the middle process, but are overwritten in later denoising steps. To address this issue, we introduce two complementary methods that exploit temporal consistency: 1) Temporal Self-Consistency Voting, a training-free, test-time decoding strategy that aggregates predictions across denoising steps to select the most consistent output; and 2) a post-training method termed Temporal Consistency Reinforcement, which uses Temporal Semantic Entropy (TSE), a measure of semantic stability across intermediate predictions, as a reward signal to encourage stable generations. Empirical results across multiple benchmarks demonstrate the effectiveness of our approach. Using the negative TSE reward alone, we observe a remarkable average improvement of 24.7% on the Countdown dataset over an existing dLLM. Combined with the accuracy reward, we achieve absolute gains of 2.0% on GSM8K, 4.3% on MATH500, 6.6% on SVAMP, and 25.3% on Countdown, respectively. Our findings underscore the untapped potential of temporal dynamics in dLLMs and offer two simple yet effective tools to harness them.</p> + https://arxiv.org/abs/2508.09138 + Tue, 12 Aug 2025 17:59:57 +0000 - NeuralOS: Towards Simulating Operating Systems via Neural Generative Models - https://arxiv.org/abs/2507.08800 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.08800.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Luke Rivard, Sun Sun, Hongyu Guo, Wenhu Chen, Yuntian Deng</p><p><b>Upvotes:</b> 75</p><p><b>Summary:</b> We introduce NeuralOS, a neural framework that simulates graphical user interfaces (GUIs) of operating systems by directly predicting screen frames in response to user inputs such as mouse movements, clicks, and keyboard events. NeuralOS combines a recurrent neural network (RNN), which tracks computer state, with a diffusion-based neural renderer that generates screen images. The model is trained on a large-scale dataset of Ubuntu XFCE recordings, which include both randomly generated interactions and realistic interactions produced by AI agents. Experiments show that NeuralOS successfully renders realistic GUI sequences, accurately captures mouse interactions, and reliably predicts state transitions like application launches. Although modeling fine-grained keyboard interactions precisely remains challenging, NeuralOS offers a step toward creating fully adaptive, generative neural interfaces for future human-computer interaction systems.</p> - https://arxiv.org/abs/2507.08800 - Fri, 11 Jul 2025 17:59:40 +0000 + Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory + https://arxiv.org/abs/2508.09736 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.09736.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lin Long, Yichen He, Wentao Ye, Yiyuan Pan, Yuan Lin, Hang Li, Junbo Zhao, Wei Li</p><p><b>Upvotes:</b> 53</p><p><b>Summary:</b> We introduce M3-Agent, a novel multimodal agent framework equipped with long-term memory. Like humans, M3-Agent can process real-time visual and auditory inputs to build and update its long-term memory. Beyond episodic memory, it also develops semantic memory, enabling it to accumulate world knowledge over time. Its memory is organized in an entity-centric, multimodal format, allowing deeper and more consistent understanding of the environment. Given an instruction, M3-Agent autonomously performs multi-turn, iterative reasoning and retrieves relevant information from memory to accomplish the task. To evaluate memory effectiveness and memory-based reasoning in multimodal agents, we develop M3-Bench, a new long-video question answering benchmark. M3-Bench comprises 100 newly recorded real-world videos captured from a robot's perspective (M3-Bench-robot) and 929 web-sourced videos across diverse scenarios (M3-Bench-web). We annotate question-answer pairs designed to test key capabilities essential for agent applications, such as human understanding, general knowledge extraction, and cross-modal reasoning. Experimental results show that M3-Agent, trained via reinforcement learning, outperforms the strongest baseline, a prompting agent using Gemini-1.5-pro and GPT-4o, achieving 6.7%, 7.7%, and 5.3% higher accuracy on M3-Bench-robot, M3-Bench-web and VideoMME-long, respectively. Our work advances the multimodal agents toward more human-like long-term memory and provides insights into their practical design. Model, code and data are available at https://github.com/bytedance-seed/m3-agent</p> + https://arxiv.org/abs/2508.09736 + Wed, 13 Aug 2025 12:03:03 +0000 - Scaling Laws for Optimal Data Mixtures - https://arxiv.org/abs/2507.09404 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.09404.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mustafa Shukor, Louis Bethune, Dan Busbridge, David Grangier, Enrico Fini, Alaaeldin El-Nouby, Pierre Ablin</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> Large foundation models are typically trained on data from multiple domains, with the data mixture--the proportion of each domain used--playing a critical role in model performance. The standard approach to selecting this mixture relies on trial and error, which becomes impractical for large-scale pretraining. We propose a systematic method to determine the optimal data mixture for any target domain using scaling laws. Our approach accurately predicts the loss of a model of size N trained with D tokens and a specific domain weight vector h. We validate the universality of these scaling laws by demonstrating their predictive power in three distinct and large-scale settings: large language model (LLM), native multimodal model (NMM), and large vision models (LVM) pretraining. We further show that these scaling laws can extrapolate to new data mixtures and across scales: their parameters can be accurately estimated using a few small-scale training runs, and used to estimate the performance at larger scales and unseen domain weights. The scaling laws allow to derive the optimal domain weights for any target domain under a given training budget (N,D), providing a principled alternative to costly trial-and-error methods.</p> - https://arxiv.org/abs/2507.09404 - Sat, 12 Jul 2025 21:16:08 +0000 + Speed Always Wins: A Survey on Efficient Architectures for Large Language Models + https://arxiv.org/abs/2508.09834 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.09834.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weigao Sun, Jiaxi Hu, Yucheng Zhou, Jusen Du, Disen Lan, Kexin Wang, Tong Zhu, Xiaoye Qu, Yu Zhang, Xiaoyu Mo, Daizong Liu, Yuxuan Liang, Wenliang Chen, Guoqi Li, Yu Cheng</p><p><b>Upvotes:</b> 51</p><p><b>Summary:</b> Large Language Models (LLMs) have delivered impressive results in language understanding, generation, reasoning, and pushes the ability boundary of multimodal models. Transformer models, as the foundation of modern LLMs, offer a strong baseline with excellent scaling properties. However, the traditional transformer architecture requires substantial computations and poses significant obstacles for large-scale training and practical deployment. In this survey, we offer a systematic examination of innovative LLM architectures that address the inherent limitations of transformers and boost the efficiency. Starting from language modeling, this survey covers the background and technical details of linear and sparse sequence modeling methods, efficient full attention variants, sparse mixture-of-experts, hybrid model architectures incorporating the above techniques, and emerging diffusion LLMs. Additionally, we discuss applications of these techniques to other modalities and consider their wider implications for developing scalable, resource-aware foundation models. By grouping recent studies into the above category, this survey presents a blueprint of modern efficient LLM architectures, and we hope this could help motivate future research toward more efficient, versatile AI systems.</p> + https://arxiv.org/abs/2508.09834 + Wed, 13 Aug 2025 14:13:46 +0000 - Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs - https://arxiv.org/abs/2507.09477 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.09477.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yangning Li, Weizhi Zhang, Yuyao Yang, Wei-Chieh Huang, Yaozu Wu, Junyu Luo, Yuanchen Bei, Henry Peng Zou, Xiao Luo, Yusheng Zhao, Chunkit Chan, Yankai Chen, Zhongfen Deng, Yinghui Li, Hai-Tao Zheng, Dongyuan Li, Renhe Jiang, Ming Zhang, Yangqiu Song, Philip S. Yu</p><p><b>Upvotes:</b> 76</p><p><b>Summary:</b> Retrieval-Augmented Generation (RAG) lifts the factuality of Large Language Models (LLMs) by injecting external knowledge, yet it falls short on problems that demand multi-step inference; conversely, purely reasoning-oriented approaches often hallucinate or mis-ground facts. This survey synthesizes both strands under a unified reasoning-retrieval perspective. We first map how advanced reasoning optimizes each stage of RAG (Reasoning-Enhanced RAG). Then, we show how retrieved knowledge of different type supply missing premises and expand context for complex inference (RAG-Enhanced Reasoning). Finally, we spotlight emerging Synergized RAG-Reasoning frameworks, where (agentic) LLMs iteratively interleave search and reasoning to achieve state-of-the-art performance across knowledge-intensive benchmarks. We categorize methods, datasets, and open challenges, and outline research avenues toward deeper RAG-Reasoning systems that are more effective, multimodally-adaptive, trustworthy, and human-centric. The collection is available at https://github.com/DavidZWZ/Awesome-RAG-Reasoning.</p> - https://arxiv.org/abs/2507.09477 - Sun, 13 Jul 2025 03:29:41 +0000 + PRELUDE: A Benchmark Designed to Require Global Comprehension and Reasoning over Long Contexts + https://arxiv.org/abs/2508.09848 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.09848.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mo Yu, Tsz Ting Chung, Chulun Zhou, Tong Li, Rui Lu, Jiangnan Li, Liyan Xu, Haoshu Lu, Ning Zhang, Jing Li, Jie Zhou</p><p><b>Upvotes:</b> 66</p><p><b>Summary:</b> We introduce PRELUDE, a benchmark for evaluating long-context understanding through the task of determining whether a character's prequel story is consistent with the canonical narrative of the original book. Our task poses a stronger demand for global comprehension and deep reasoning than existing benchmarks -- as the prequels are not part of the original story, assessing their plausibility typically requires searching and integrating information that is only indirectly related. Empirically, 88% of instances require evidence from multiple parts of the narrative. Experimental results highlight the challenge of our task: in-context learning, RAG and in-domain training with state-of-the-art LLMs, and commercial DeepResearch services, lag behind humans by >15%. A further human study reveals that models often produce correct answers with flawed reasoning, leading to an over 30% gap in reasoning accuracy compared to humans. These findings underscore the substantial room for improvement in long-context understanding and reasoning.</p> + https://arxiv.org/abs/2508.09848 + Wed, 13 Aug 2025 14:28:25 +0000 - SpeakerVid-5M: A Large-Scale High-Quality Dataset for Audio-Visual Dyadic Interactive Human Generation - https://arxiv.org/abs/2507.09862 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.09862.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Youliang Zhang, Zhaoyang Li, Duomin Wang, Jiahe Zhang, Deyu Zhou, Zixin Yin, Xili Dai, Gang Yu, Xiu Li</p><p><b>Upvotes:</b> 48</p><p><b>Summary:</b> The rapid development of large-scale models has catalyzed significant breakthroughs in the digital human domain. These advanced methodologies offer high-fidelity solutions for avatar driving and rendering, leading academia to focus on the next major challenge: audio-visual dyadic interactive virtual human. To facilitate research in this emerging area, we present SpeakerVid-5M dataset, the first large-scale, high-quality dataset designed for audio-visual dyadic interactive virtual human generation. Totaling over 8,743 hours, SpeakerVid-5M contains more than 5.2 million video clips of human portraits. It covers diverse scales and interaction types, including monadic talking, listening, and dyadic conversations. Crucially, the dataset is structured along two key dimensions: interaction type and data quality. First, it is categorized into four types (dialogue branch, single branch, listening branch and multi-turn branch) based on the interaction scenario. Second, it is stratified into a large-scale pre-training subset and a curated, high-quality subset for Supervised Fine-Tuning (SFT). This dual structure accommodates a wide array of 2D virtual human tasks. In addition, we provide an autoregressive (AR)-based video chat baseline trained on this data, accompanied by a dedicated set of metrics and test data to serve as a benchmark VidChatBench for future work. Both the dataset and the corresponding data processing code will be publicly released. Project page: https://dorniwang.github.io/SpeakerVid-5M/</p> - https://arxiv.org/abs/2507.09862 - Mon, 14 Jul 2025 02:22:47 +0000 + AWorld: Dynamic Multi-Agent System with Stable Maneuvering for Robust GAIA Problem Solving + https://arxiv.org/abs/2508.09889 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.09889.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhitian Xie, Qintong Wu, Chengyue Yu, Chenyi Zhuang, Jinjie Gu</p><p><b>Upvotes:</b> 32</p><p><b>Summary:</b> The rapid advancement of large language models (LLMs) has empowered intelligent agents to leverage diverse external tools for solving complex real-world problems. However, as agents increasingly depend on multiple tools, they encounter new challenges: extended contexts from disparate sources and noisy or irrelevant tool outputs can undermine system reliability and accuracy. These challenges underscore the necessity for enhanced stability in agent-based systems. To address this, we introduce dynamic supervision and maneuvering mechanisms, constructing a robust and dynamic Multi-Agent System (MAS) architecture within the AWorld framework. In our approach, the Execution Agent invokes the Guard Agent at critical steps to verify and correct the reasoning process, effectively reducing errors arising from noise and bolstering problem-solving robustness. Extensive experiments on the GAIA test dataset reveal that our dynamic maneuvering mechanism significantly improves both the effectiveness and stability of solutions, outperforming single-agent system (SAS) and standard tool-augmented systems. As a result, our dynamic MAS system achieved first place among open-source projects on the prestigious GAIA leaderboard. These findings highlight the practical value of collaborative agent roles in developing more reliable and trustworthy intelligent systems.</p> + https://arxiv.org/abs/2508.09889 + Wed, 13 Aug 2025 15:46:25 +0000 - Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation - https://arxiv.org/abs/2507.10524 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.10524.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sangmin Bae, Yujin Kim, Reza Bayat, Sungnyun Kim, Jiyoun Ha, Tal Schuster, Adam Fisch, Hrayr Harutyunyan, Ziwei Ji, Aaron Courville, Se-Young Yun</p><p><b>Upvotes:</b> 64</p><p><b>Summary:</b> Scaling language models unlocks impressive capabilities, but the accompanying computational and memory demands make both training and deployment expensive. Existing efficiency efforts typically target either parameter sharing or adaptive computation, leaving open the question of how to attain both simultaneously. We introduce Mixture-of-Recursions (MoR), a unified framework that combines the two axes of efficiency inside a single Recursive Transformer. MoR reuses a shared stack of layers across recursion steps to achieve parameter efficiency, while lightweight routers enable adaptive token-level thinking by dynamically assigning different recursion depths to individual tokens. This allows MoR to focus quadratic attention computation only among tokens still active at a given recursion depth, further improving memory access efficiency by selectively caching only their key-value pairs. Beyond these core mechanisms, we also propose a KV sharing variant that reuses KV pairs from the first recursion, specifically designed to decrease prefill latency and memory footprint. Across model scales ranging from 135M to 1.7B parameters, MoR forms a new Pareto frontier: at equal training FLOPs and smaller model sizes, it significantly lowers validation perplexity and improves few-shot accuracy, while delivering higher throughput compared with vanilla and existing recursive baselines. These gains demonstrate that MoR is an effective path towards large-model quality without incurring large-model cost.</p> - https://arxiv.org/abs/2507.10524 - Mon, 14 Jul 2025 17:49:00 +0000 + Story2Board: A Training-Free Approach for Expressive Storyboard Generation + https://arxiv.org/abs/2508.09983 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.09983.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> David Dinkevich, Matan Levy, Omri Avrahami, Dvir Samuel, Dani Lischinski</p><p><b>Upvotes:</b> 66</p><p><b>Summary:</b> We present Story2Board, a training-free framework for expressive storyboard generation from natural language. Existing methods narrowly focus on subject identity, overlooking key aspects of visual storytelling such as spatial composition, background evolution, and narrative pacing. To address this, we introduce a lightweight consistency framework composed of two components: Latent Panel Anchoring, which preserves a shared character reference across panels, and Reciprocal Attention Value Mixing, which softly blends visual features between token pairs with strong reciprocal attention. Together, these mechanisms enhance coherence without architectural changes or fine-tuning, enabling state-of-the-art diffusion models to generate visually diverse yet consistent storyboards. To structure generation, we use an off-the-shelf language model to convert free-form stories into grounded panel-level prompts. To evaluate, we propose the Rich Storyboard Benchmark, a suite of open-domain narratives designed to assess layout diversity and background-grounded storytelling, in addition to consistency. We also introduce a new Scene Diversity metric that quantifies spatial and pose variation across storyboards. Our qualitative and quantitative results, as well as a user study, show that Story2Board produces more dynamic, coherent, and narratively engaging storyboards than existing baselines.</p> + https://arxiv.org/abs/2508.09983 + Wed, 13 Aug 2025 17:56:26 +0000 - Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contamination - https://arxiv.org/abs/2507.10532 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.10532.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mingqi Wu, Zhihao Zhang, Qiaole Dong, Zhiheng Xi, Jun Zhao, Senjie Jin, Xiaoran Fan, Yuhao Zhou, Yanwei Fu, Qin Liu, Songyang Zhang, Qi Zhang</p><p><b>Upvotes:</b> 80</p><p><b>Summary:</b> The reasoning capabilities of large language models (LLMs) have been a longstanding focus of research. Recent works have further enhanced these capabilities using reinforcement learning (RL), with many new methods claiming significant improvements with minimal or no external supervision. Surprisingly, some studies even suggest that random or incorrect reward signals can enhance reasoning performance. However, these breakthroughs are mostly reported on the Qwen2.5 model family and evaluated on well-known benchmarks such as MATH-500, AMC, and AIME, while failing to achieve similar gains on other models like Llama, which warrants further investigation. Our analysis shows that although Qwen2.5 achieves strong mathematical reasoning performance, its pretraining on large-scale web corpora makes it vulnerable to data contamination in popular benchmarks. As a result, results derived from these benchmarks may be unreliable. To address this, we introduce a generator that produces fully synthetic arithmetic problems of arbitrary length and difficulty, yielding a clean dataset we call RandomCalculation. Using these leakage-free datasets, we show that only accurate reward signals consistently improve performance, while noisy or incorrect signals do not. We advocate for evaluating RL methods on uncontaminated benchmarks and across diverse model families to ensure trustworthy conclusions.</p> - https://arxiv.org/abs/2507.10532 - Mon, 14 Jul 2025 17:55:15 +0000 + DINOv3 + https://arxiv.org/abs/2508.10104 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.10104.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Oriane Siméoni, Huy V. Vo, Maximilian Seitzer, Federico Baldassarre, Maxime Oquab, Cijo Jose, Vasil Khalidov, Marc Szafraniec, Seungeun Yi, Michaël Ramamonjisoa, Francisco Massa, Daniel Haziza, Luca Wehrstedt, Jianyuan Wang, Timothée Darcet, Théo Moutakanni, Leonel Sentana, Claire Roberts, Andrea Vedaldi, Jamie Tolan, John Brandt, Camille Couprie, Julien Mairal, Hervé Jégou, Patrick Labatut, Piotr Bojanowski</p><p><b>Upvotes:</b> 221</p><p><b>Summary:</b> Self-supervised learning holds the promise of eliminating the need for manual data annotation, enabling models to scale effortlessly to massive datasets and larger architectures. By not being tailored to specific tasks or domains, this training paradigm has the potential to learn visual representations from diverse sources, ranging from natural to aerial images -- using a single algorithm. This technical report introduces DINOv3, a major milestone toward realizing this vision by leveraging simple yet effective strategies. First, we leverage the benefit of scaling both dataset and model size by careful data preparation, design, and optimization. Second, we introduce a new method called Gram anchoring, which effectively addresses the known yet unsolved issue of dense feature maps degrading during long training schedules. Finally, we apply post-hoc strategies that further enhance our models' flexibility with respect to resolution, model size, and alignment with text. As a result, we present a versatile vision foundation model that outperforms the specialized state of the art across a broad range of settings, without fine-tuning. DINOv3 produces high-quality dense features that achieve outstanding performance on various vision tasks, significantly surpassing previous self- and weakly-supervised foundation models. We also share the DINOv3 suite of vision models, designed to advance the state of the art on a wide spectrum of tasks and data by providing scalable solutions for diverse resource constraints and deployment scenarios.</p> + https://arxiv.org/abs/2508.10104 + Wed, 13 Aug 2025 18:00:55 +0000 - EmbRACE-3K: Embodied Reasoning and Action in Complex Environments - https://arxiv.org/abs/2507.10548 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.10548.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mingxian Lin, Wei Huang, Yitang Li, Chengjie Jiang, Kui Wu, Fangwei Zhong, Shengju Qian, Xin Wang, Xiaojuan Qi</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> Recent advanced vision-language models(VLMs) have demonstrated strong performance on passive, offline image and video understanding tasks. However, their effectiveness in embodied settings, which require online interaction and active scene understanding remains limited. In such scenarios, an agent perceives the environment from a first-person perspective, with each action dynamically shaping subsequent observations. Even state-of-the-art models such as GPT-4o, Claude 3.5 Sonnet, and Gemini 2.5 Pro struggle in open-environment interactions, exhibiting clear limitations in spatial reasoning and long-horizon planning. To address this gap, we introduce EmRACE-3K, a dataset of over 3,000 language-guided tasks situated in diverse, photorealistic environments constructed using Unreal Engine and the UnrealCV-Zoo framework. The tasks encompass a wide range of embodied challenges, including navigation, object manipulation, and multi-stage goal execution. Each task unfolds as a multi-step trajectory, pairing first-person visual observations with high-level instructions, grounded actions, and natural language rationales that express the agent's intent at every step. Using EmRACE-3K, we establish a benchmark to evaluate the embodied reasoning capabilities of VLMs across three key dimensions: Exploration, Dynamic Spatial-Semantic Reasoning, and Multi-stage Goal Execution. In zero-shot settings, all models achieve success rates below 20%, underscoring the challenge posed by our benchmark and the current limitations of VLMs in interactive environments. To demonstrate the utility of EmRACE-3K, we further fine-tune Qwen2.5-VL-7B using supervised learning followed by reinforcement learning. This approach yields substantial improvements across all three challenge categories, highlighting the dataset's effectiveness in enabling the development of embodied reasoning capabilities.</p> - https://arxiv.org/abs/2507.10548 - Mon, 14 Jul 2025 17:59:46 +0000 + XQuant: Breaking the Memory Wall for LLM Inference with KV Cache Rematerialization + https://arxiv.org/abs/2508.10395 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.10395.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Aditya Tomar, Coleman Hooper, Minjae Lee, Haocheng Xi, Rishabh Tiwari, Wonjun Kang, Luca Manolache, Michael W. Mahoney, Kurt Keutzer, Amir Gholami</p><p><b>Upvotes:</b> 40</p><p><b>Summary:</b> Although LLM inference has emerged as a critical workload for many downstream applications, efficiently inferring LLMs is challenging due to the substantial memory footprint and bandwidth requirements. In parallel, compute capabilities have steadily outpaced both memory capacity and bandwidth over the last few decades, a trend that remains evident in modern GPU hardware and exacerbates the challenge of LLM inference. As such, new algorithms are emerging that trade increased computation for reduced memory operations. To that end, we present XQuant, which takes advantage of this trend, enabling an order-of-magnitude reduction in memory consumption through low-bit quantization with substantial accuracy benefits relative to state-of-the-art KV cache quantization methods. We accomplish this by quantizing and caching the layer input activations X, instead of using standard KV caching, and then rematerializing the Keys and Values on-the-fly during inference. This results in an immediate 2times memory savings compared to KV caching. By applying XQuant, we achieve up to sim 7.7times memory savings with <0.1 perplexity degradation compared to the FP16 baseline. Furthermore, our approach leverages the fact that X values are similar across layers. Building on this observation, we introduce XQuant-CL, which exploits the cross-layer similarity in the X embeddings for extreme compression. Across different models, XQuant-CL attains up to 10times memory savings relative to the FP16 baseline with only 0.01 perplexity degradation, and 12.5times memory savings with only 0.1 perplexity degradation. XQuant exploits the rapidly increasing compute capabilities of hardware platforms to eliminate the memory bottleneck, while surpassing state-of-the-art KV cache quantization methods and achieving near-FP16 accuracy across a wide range of models.</p> + https://arxiv.org/abs/2508.10395 + Thu, 14 Aug 2025 06:52:38 +0000 - Robust 3D-Masked Part-level Editing in 3D Gaussian Splatting with Regularized Score Distillation Sampling - https://arxiv.org/abs/2507.11061 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.11061.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hayeon Kim, Ji Ha Jang, Se Young Chun</p><p><b>Upvotes:</b> 37</p><p><b>Summary:</b> Recent advances in 3D neural representations and instance-level editing models have enabled the efficient creation of high-quality 3D content. However, achieving precise local 3D edits remains challenging, especially for Gaussian Splatting, due to inconsistent multi-view 2D part segmentations and inherently ambiguous nature of Score Distillation Sampling (SDS) loss. To address these limitations, we propose RoMaP, a novel local 3D Gaussian editing framework that enables precise and drastic part-level modifications. First, we introduce a robust 3D mask generation module with our 3D-Geometry Aware Label Prediction (3D-GALP), which uses spherical harmonics (SH) coefficients to model view-dependent label variations and soft-label property, yielding accurate and consistent part segmentations across viewpoints. Second, we propose a regularized SDS loss that combines the standard SDS loss with additional regularizers. In particular, an L1 anchor loss is introduced via our Scheduled Latent Mixing and Part (SLaMP) editing method, which generates high-quality part-edited 2D images and confines modifications only to the target region while preserving contextual coherence. Additional regularizers, such as Gaussian prior removal, further improve flexibility by allowing changes beyond the existing context, and robust 3D masking prevents unintended edits. Experimental results demonstrate that our RoMaP achieves state-of-the-art local 3D editing on both reconstructed and generated Gaussian scenes and objects qualitatively and quantitatively, making it possible for more robust and flexible part-level 3D Gaussian editing. Code is available at https://janeyeon.github.io/romap.</p> - https://arxiv.org/abs/2507.11061 - Tue, 15 Jul 2025 07:54:11 +0000 + ComoRAG: A Cognitive-Inspired Memory-Organized RAG for Stateful Long Narrative Reasoning + https://arxiv.org/abs/2508.10419 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.10419.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Juyuan Wang, Rongchen Zhao, Wei Wei, Yufeng Wang, Mo Yu, Jie Zhou, Jin Xu, Liyan Xu</p><p><b>Upvotes:</b> 70</p><p><b>Summary:</b> Narrative comprehension on long stories and novels has been a challenging domain attributed to their intricate plotlines and entangled, often evolving relations among characters and entities. Given the LLM's diminished reasoning over extended context and high computational cost, retrieval-based approaches remain a pivotal role in practice. However, traditional RAG methods can fall short due to their stateless, single-step retrieval process, which often overlooks the dynamic nature of capturing interconnected relations within long-range context. In this work, we propose ComoRAG, holding the principle that narrative reasoning is not a one-shot process, but a dynamic, evolving interplay between new evidence acquisition and past knowledge consolidation, analogous to human cognition when reasoning with memory-related signals in the brain. Specifically, when encountering a reasoning impasse, ComoRAG undergoes iterative reasoning cycles while interacting with a dynamic memory workspace. In each cycle, it generates probing queries to devise new exploratory paths, then integrates the retrieved evidence of new aspects into a global memory pool, thereby supporting the emergence of a coherent context for the query resolution. Across four challenging long-context narrative benchmarks (200K+ tokens), ComoRAG outperforms strong RAG baselines with consistent relative gains up to 11% compared to the strongest baseline. Further analysis reveals that ComoRAG is particularly advantageous for complex queries requiring global comprehension, offering a principled, cognitively motivated paradigm for retrieval-based long context comprehension towards stateful reasoning. Our code is publicly released at https://github.com/EternityJune25/ComoRAG</p> + https://arxiv.org/abs/2508.10419 + Thu, 14 Aug 2025 07:52:09 +0000 - The Devil behind the mask: An emergent safety vulnerability of Diffusion LLMs - https://arxiv.org/abs/2507.11097 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.11097.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zichen Wen, Jiashu Qu, Dongrui Liu, Zhiyuan Liu, Ruixi Wu, Yicun Yang, Xiangqi Jin, Haoyun Xu, Xuyang Liu, Weijia Li, Chaochao Lu, Jing Shao, Conghui He, Linfeng Zhang</p><p><b>Upvotes:</b> 62</p><p><b>Summary:</b> Diffusion-based large language models (dLLMs) have recently emerged as a powerful alternative to autoregressive LLMs, offering faster inference and greater interactivity via parallel decoding and bidirectional modeling. However, despite strong performance in code generation and text infilling, we identify a fundamental safety concern: existing alignment mechanisms fail to safeguard dLLMs against context-aware, masked-input adversarial prompts, exposing novel vulnerabilities. To this end, we present DIJA, the first systematic study and jailbreak attack framework that exploits unique safety weaknesses of dLLMs. Specifically, our proposed DIJA constructs adversarial interleaved mask-text prompts that exploit the text generation mechanisms of dLLMs, i.e., bidirectional modeling and parallel decoding. Bidirectional modeling drives the model to produce contextually consistent outputs for masked spans, even when harmful, while parallel decoding limits model dynamic filtering and rejection sampling of unsafe content. This causes standard alignment mechanisms to fail, enabling harmful completions in alignment-tuned dLLMs, even when harmful behaviors or unsafe instructions are directly exposed in the prompt. Through comprehensive experiments, we demonstrate that DIJA significantly outperforms existing jailbreak methods, exposing a previously overlooked threat surface in dLLM architectures. Notably, our method achieves up to 100% keyword-based ASR on Dream-Instruct, surpassing the strongest prior baseline, ReNeLLM, by up to 78.5% in evaluator-based ASR on JailbreakBench and by 37.7 points in StrongREJECT score, while requiring no rewriting or hiding of harmful content in the jailbreak prompt. Our findings underscore the urgent need for rethinking safety alignment in this emerging class of language models. Code is available at https://github.com/ZichenWen1/DIJA.</p> - https://arxiv.org/abs/2507.11097 - Tue, 15 Jul 2025 08:44:46 +0000 + We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoning + https://arxiv.org/abs/2508.10433 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.10433.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Runqi Qiao, Qiuna Tan, Peiqing Yang, Yanzi Wang, Xiaowan Wang, Enhui Wan, Sitong Zhou, Guanting Dong, Yuchen Zeng, Yida Xu, Jie Wang, Chong Sun, Chen Li, Honggang Zhang</p><p><b>Upvotes:</b> 142</p><p><b>Summary:</b> Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities across various tasks, but still struggle with complex mathematical reasoning. Existing research primarily focuses on dataset construction and method optimization, often overlooking two critical aspects: comprehensive knowledge-driven design and model-centric data space modeling. In this paper, we introduce We-Math 2.0, a unified system that integrates a structured mathematical knowledge system, model-centric data space modeling, and a reinforcement learning (RL)-based training paradigm to comprehensively enhance the mathematical reasoning abilities of MLLMs. The key contributions of We-Math 2.0 are fourfold: (1) MathBook Knowledge System: We construct a five-level hierarchical system encompassing 491 knowledge points and 1,819 fundamental principles. (2) MathBook-Standard & Pro: We develop MathBook-Standard, a dataset that ensures broad conceptual coverage and flexibility through dual expansion. Additionally, we define a three-dimensional difficulty space and generate 7 progressive variants per problem to build MathBook-Pro, a challenging dataset for robust training. (3) MathBook-RL: We propose a two-stage RL framework comprising: (i) Cold-Start Fine-tuning, which aligns the model with knowledge-oriented chain-of-thought reasoning; and (ii) Progressive Alignment RL, leveraging average-reward learning and dynamic data scheduling to achieve progressive alignment across difficulty levels. (4) MathBookEval: We introduce a comprehensive benchmark covering all 491 knowledge points with diverse reasoning step distributions. Experimental results show that MathBook-RL performs competitively with existing baselines on four widely-used benchmarks and achieves strong results on MathBookEval, suggesting promising generalization in mathematical reasoning.</p> + https://arxiv.org/abs/2508.10433 + Thu, 14 Aug 2025 08:15:41 +0000 - EXAONE 4.0: Unified Large Language Models Integrating Non-reasoning and Reasoning Modes - https://arxiv.org/abs/2507.11407 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.11407.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> LG AI Research, Kyunghoon Bae, Eunbi Choi, Kibong Choi, Stanley Jungkyu Choi, Yemuk Choi, Kyubeen Han, Seokhee Hong, Junwon Hwang, Taewan Hwang, Joonwon Jang, Hyojin Jeon, Kijeong Jeon, Gerrard Jeongwon Jo, Hyunjik Jo, Jiyeon Jung, Euisoon Kim, Hyosang Kim, Jihoon Kim, Joonkee Kim, Seonghwan Kim, Soyeon Kim, Sunkyoung Kim, Yireun Kim, Yongil Kim, Youchul Kim, Edward Hwayoung Lee, Gwangho Lee, Haeju Lee, Honglak Lee, Jinsik Lee, Kyungmin Lee, Sangha Park, Young Min Paik, Yongmin Park, Youngyong Park, Sanghyun Seo, Sihoon Yang, Heuiyeen Yeen, Sihyuk Yi, Hyeongu Yun</p><p><b>Upvotes:</b> 51</p><p><b>Summary:</b> This technical report introduces EXAONE 4.0, which integrates a Non-reasoning mode and a Reasoning mode to achieve both the excellent usability of EXAONE 3.5 and the advanced reasoning abilities of EXAONE Deep. To pave the way for the agentic AI era, EXAONE 4.0 incorporates essential features such as agentic tool use, and its multilingual capabilities are extended to support Spanish in addition to English and Korean. The EXAONE 4.0 model series consists of two sizes: a mid-size 32B model optimized for high performance, and a small-size 1.2B model designed for on-device applications. The EXAONE 4.0 demonstrates superior performance compared to open-weight models in its class and remains competitive even against frontier-class models. The models are publicly available for research purposes and can be easily downloaded via https://huggingface.co/LGAI-EXAONE.</p> - https://arxiv.org/abs/2507.11407 - Tue, 15 Jul 2025 15:24:51 +0000 + NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale + https://arxiv.org/abs/2508.10711 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.10711.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> NextStep Team, Chunrui Han, Guopeng Li, Jingwei Wu, Quan Sun, Yan Cai, Yuang Peng, Zheng Ge, Deyu Zhou, Haomiao Tang, Hongyu Zhou, Kenkun Liu, Ailin Huang, Bin Wang, Changxin Miao, Deshan Sun, En Yu, Fukun Yin, Gang Yu, Hao Nie, Haoran Lv, Hanpeng Hu, Jia Wang, Jian Zhou, Jianjian Sun, Kaijun Tan, Kang An, Kangheng Lin, Liang Zhao, Mei Chen, Peng Xing, Rui Wang, Shiyu Liu, Shutao Xia, Tianhao You, Wei Ji, Xianfang Zeng, Xin Han, Xuelin Zhang, Yana Wei, Yanming Xu, Yimin Jiang, Yingming Wang, Yu Zhou, Yucheng Han, Ziyang Meng, Binxing Jiao, Daxin Jiang, Xiangyu Zhang, Yibo Zhu</p><p><b>Upvotes:</b> 139</p><p><b>Summary:</b> Prevailing autoregressive (AR) models for text-to-image generation either rely on heavy, computationally-intensive diffusion models to process continuous image tokens, or employ vector quantization (VQ) to obtain discrete tokens with quantization loss. In this paper, we push the autoregressive paradigm forward with NextStep-1, a 14B autoregressive model paired with a 157M flow matching head, training on discrete text tokens and continuous image tokens with next-token prediction objectives. NextStep-1 achieves state-of-the-art performance for autoregressive models in text-to-image generation tasks, exhibiting strong capabilities in high-fidelity image synthesis. Furthermore, our method shows strong performance in image editing, highlighting the power and versatility of our unified approach. To facilitate open research, we will release our code and models to the community.</p> + https://arxiv.org/abs/2508.10711 + Thu, 14 Aug 2025 14:54:22 +0000 - DrafterBench: Benchmarking Large Language Models for Tasks Automation in Civil Engineering - https://arxiv.org/abs/2507.11527 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.11527.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yinsheng Li, Zhen Dong, Yi Shao</p><p><b>Upvotes:</b> 31</p><p><b>Summary:</b> Large Language Model (LLM) agents have shown great potential for solving real-world problems and promise to be a solution for tasks automation in industry. However, more benchmarks are needed to systematically evaluate automation agents from an industrial perspective, for example, in Civil Engineering. Therefore, we propose DrafterBench for the comprehensive evaluation of LLM agents in the context of technical drawing revision, a representation task in civil engineering. DrafterBench contains twelve types of tasks summarized from real-world drawing files, with 46 customized functions/tools and 1920 tasks in total. DrafterBench is an open-source benchmark to rigorously test AI agents' proficiency in interpreting intricate and long-context instructions, leveraging prior knowledge, and adapting to dynamic instruction quality via implicit policy awareness. The toolkit comprehensively assesses distinct capabilities in structured data comprehension, function execution, instruction following, and critical reasoning. DrafterBench offers detailed analysis of task accuracy and error statistics, aiming to provide deeper insight into agent capabilities and identify improvement targets for integrating LLMs in engineering applications. Our benchmark is available at https://github.com/Eason-Li-AIS/DrafterBench, with the test set hosted at https://huggingface.co/datasets/Eason666/DrafterBench.</p> - https://arxiv.org/abs/2507.11527 - Tue, 15 Jul 2025 17:56:04 +0000 + UI-Venus Technical Report: Building High-performance UI Agents with RFT + https://arxiv.org/abs/2508.10833 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.10833.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhangxuan Gu, Zhengwen Zeng, Zhenyu Xu, Xingran Zhou, Shuheng Shen, Yunfei Liu, Beitong Zhou, Changhua Meng, Tianyu Xia, Weizhi Chen, Yue Wen, Jingya Dou, Fei Tang, Jinzhen Lin, Yulin Liu, Zhenlin Guo, Yichen Gong, Heng Jia, Changlong Gao, Yuan Guo, Yong Deng, Zhenyu Guo, Liang Chen, Weiqiang Wang</p><p><b>Upvotes:</b> 40</p><p><b>Summary:</b> We present UI-Venus, a native UI agent that takes only screenshots as input based on a multimodal large language model. UI-Venus achieves SOTA performance on both UI grounding and navigation tasks using only several hundred thousand high-quality training samples through reinforcement finetune (RFT) based on Qwen2.5-VL. Specifically, the 7B and 72B variants of UI-Venus obtain 94.1% / 50.8% and 95.3% / 61.9% on the standard grounding benchmarks, i.e., Screenspot-V2 / Pro, surpassing the previous SOTA baselines including open-source GTA1 and closed-source UI-TARS-1.5.To show UI-Venus's summary and planing ability, we also evaluate it on the AndroidWorld, an online UI navigation arena, on which our 7B and 72B variants achieve 49.1% and 65.9% success rate, also beating existing models.To achieve this, we introduce carefully designed reward functions for both UI grounding and navigation tasks and corresponding efficient data cleaning strategies.To further boost navigation performance, we propose Self-Evolving Trajectory History Alignment \& Sparse Action Enhancement that refine historical reasoning traces and balances the distribution of sparse but critical actions, leading to more coherent planning and better generalization in complex UI tasks. Our contributions include the publish of SOTA open-source UI agents, comprehensive data cleaning protocols and a novel self-evolving framework for improving navigation performance, which encourage further research and development in the community. Code is available at https://github.com/antgroup/UI-Venus.</p> + https://arxiv.org/abs/2508.10833 + Thu, 14 Aug 2025 16:58:07 +0000 - RiemannLoRA: A Unified Riemannian Framework for Ambiguity-Free LoRA Optimization - https://arxiv.org/abs/2507.12142 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.12142.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Vladimir Bogachev, Vladimir Aletov, Alexander Molozhavenko, Denis Bobkov, Vera Soboleva, Aibek Alanov, Maxim Rakhuba</p><p><b>Upvotes:</b> 35</p><p><b>Summary:</b> Low-Rank Adaptation (LoRA) has become a widely adopted standard for parameter-efficient fine-tuning of large language models (LLMs), significantly reducing memory and computational demands. However, challenges remain, including finding optimal initialization strategies or mitigating overparametrization in low-rank matrix factorization. In this work, we propose a novel approach that addresses both of the challenges simultaneously within a unified framework. Our method treats a set of fixed-rank LoRA matrices as a smooth manifold. Considering adapters as elements on this manifold removes overparametrization, while determining the direction of the fastest loss decrease along the manifold provides initialization. Special care is taken to obtain numerically stable and computationally efficient implementation of our method, using best practices from numerical linear algebra and Riemannian optimization. Experimental results on LLM and diffusion model architectures demonstrate that RiemannLoRA consistently improves both convergence speed and final performance over standard LoRA and its state-of-the-art modifications.</p> - https://arxiv.org/abs/2507.12142 - Wed, 16 Jul 2025 11:17:12 +0000 + SSRL: Self-Search Reinforcement Learning + https://arxiv.org/abs/2508.10874 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.10874.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuchen Fan, Kaiyan Zhang, Heng Zhou, Yuxin Zuo, Yanxu Chen, Yu Fu, Xinwei Long, Xuekai Zhu, Che Jiang, Yuchen Zhang, Li Kang, Gang Chen, Cheng Huang, Zhizhou He, Bingning Wang, Lei Bai, Ning Ding, Bowen Zhou</p><p><b>Upvotes:</b> 90</p><p><b>Summary:</b> We investigate the potential of large language models (LLMs) to serve as efficient simulators for agentic search tasks in reinforcement learning (RL), thereby reducing dependence on costly interactions with external search engines. To this end, we first quantify the intrinsic search capability of LLMs via structured prompting and repeated sampling, which we term Self-Search. Our results reveal that LLMs exhibit strong scaling behavior with respect to the inference budget, achieving high pass@k on question-answering benchmarks, including the challenging BrowseComp task. Building on these observations, we introduce Self-Search RL (SSRL), which enhances LLMs' Self-Search capability through format-based and rule-based rewards. SSRL enables models to iteratively refine their knowledge utilization internally, without requiring access to external tools. Empirical evaluations demonstrate that SSRL-trained policy models provide a cost-effective and stable environment for search-driven RL training, reducing reliance on external search engines and facilitating robust sim-to-real transfer. We draw the following conclusions: 1) LLMs possess world knowledge that can be effectively elicited to achieve high performance; 2) SSRL demonstrates the potential of leveraging internal knowledge to reduce hallucination; 3) SSRL-trained models integrate seamlessly with external search engines without additional effort. Our findings highlight the potential of LLMs to support more scalable RL agent training.</p> + https://arxiv.org/abs/2508.10874 + Thu, 14 Aug 2025 17:46:01 +0000 - SWE-Perf: Can Language Models Optimize Code Performance on Real-World Repositories? - https://arxiv.org/abs/2507.12415 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.12415.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xinyi He, Qian Liu, Mingzhe Du, Lin Yan, Zhijie Fan, Yiming Huang, Zejian Yuan, Zejun Ma</p><p><b>Upvotes:</b> 40</p><p><b>Summary:</b> Code performance optimization is paramount in real-world software engineering and critical for production-level systems. While Large Language Models (LLMs) have demonstrated impressive capabilities in code generation and bug fixing, their proficiency in enhancing code performance at the repository level remains largely unexplored. To address this gap, we introduce SWE-Perf, the first benchmark specifically designed to systematically evaluate LLMs on code performance optimization tasks within authentic repository contexts. SWE-Perf comprises 140 carefully curated instances, each derived from performance-improving pull requests from popular GitHub repositories. Each benchmark instance includes the relevant codebase, target functions, performance-related tests, expert-authored patches, and executable environments. Through a comprehensive evaluation of representative methods that span file-level and repo-level approaches (e.g., Agentless and OpenHands), we reveal a substantial capability gap between existing LLMs and expert-level optimization performance, highlighting critical research opportunities in this emerging field.</p> - https://arxiv.org/abs/2507.12415 - Wed, 16 Jul 2025 17:05:17 +0000 + A Survey on Diffusion Language Models + https://arxiv.org/abs/2508.10875 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.10875.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tianyi Li, Mingda Chen, Bowei Guo, Zhiqiang Shen</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> Diffusion Language Models (DLMs) are rapidly emerging as a powerful and promising alternative to the dominant autoregressive (AR) paradigm. By generating tokens in parallel through an iterative denoising process, DLMs possess inherent advantages in reducing inference latency and capturing bidirectional context, thereby enabling fine-grained control over the generation process. While achieving a several-fold speed-up, recent advancements have allowed DLMs to show performance comparable to their autoregressive counterparts, making them a compelling choice for various natural language processing tasks. In this survey, we provide a holistic overview of the current DLM landscape. We trace its evolution and relationship with other paradigms, such as autoregressive and masked language models, and cover both foundational principles and state-of-the-art models. Our work offers an up-to-date, comprehensive taxonomy and an in-depth analysis of current techniques, from pre-training strategies to advanced post-training methods. Another contribution of this survey is a thorough review of DLM inference strategies and optimizations, including improvements in decoding parallelism, caching mechanisms, and generation quality. We also highlight the latest approaches to multimodal extensions of DLMs and delineate their applications across various practical scenarios. Furthermore, our discussion addresses the limitations and challenges of DLMs, including efficiency, long-sequence handling, and infrastructure requirements, while outlining future research directions to sustain progress in this rapidly evolving field. Project GitHub is available at https://github.com/VILA-Lab/Awesome-DLMs.</p> + https://arxiv.org/abs/2508.10875 + Thu, 14 Aug 2025 17:47:22 +0000 - PhysX: Physical-Grounded 3D Asset Generation - https://arxiv.org/abs/2507.12465 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.12465.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ziang Cao, Zhaoxi Chen, Linag Pan, Ziwei Liu</p><p><b>Upvotes:</b> 41</p><p><b>Summary:</b> 3D modeling is moving from virtual to physical. Existing 3D generation primarily emphasizes geometries and textures while neglecting physical-grounded modeling. Consequently, despite the rapid development of 3D generative models, the synthesized 3D assets often overlook rich and important physical properties, hampering their real-world application in physical domains like simulation and embodied AI. As an initial attempt to address this challenge, we propose PhysX, an end-to-end paradigm for physical-grounded 3D asset generation. 1) To bridge the critical gap in physics-annotated 3D datasets, we present PhysXNet - the first physics-grounded 3D dataset systematically annotated across five foundational dimensions: absolute scale, material, affordance, kinematics, and function description. In particular, we devise a scalable human-in-the-loop annotation pipeline based on vision-language models, which enables efficient creation of physics-first assets from raw 3D assets.2) Furthermore, we propose PhysXGen, a feed-forward framework for physics-grounded image-to-3D asset generation, injecting physical knowledge into the pre-trained 3D structural space. Specifically, PhysXGen employs a dual-branch architecture to explicitly model the latent correlations between 3D structures and physical properties, thereby producing 3D assets with plausible physical predictions while preserving the native geometry quality. Extensive experiments validate the superior performance and promising generalization capability of our framework. All the code, data, and models will be released to facilitate future research in generative physical AI.</p> - https://arxiv.org/abs/2507.12465 - Wed, 16 Jul 2025 17:59:35 +0000 + ToonComposer: Streamlining Cartoon Production with Generative Post-Keyframing + https://arxiv.org/abs/2508.10881 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.10881.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lingen Li, Guangzhi Wang, Zhaoyang Zhang, Yaowei Li, Xiaoyu Li, Qi Dou, Jinwei Gu, Tianfan Xue, Ying Shan</p><p><b>Upvotes:</b> 51</p><p><b>Summary:</b> Traditional cartoon and anime production involves keyframing, inbetweening, and colorization stages, which require intensive manual effort. Despite recent advances in AI, existing methods often handle these stages separately, leading to error accumulation and artifacts. For instance, inbetweening approaches struggle with large motions, while colorization methods require dense per-frame sketches. To address this, we introduce ToonComposer, a generative model that unifies inbetweening and colorization into a single post-keyframing stage. ToonComposer employs a sparse sketch injection mechanism to provide precise control using keyframe sketches. Additionally, it uses a cartoon adaptation method with the spatial low-rank adapter to tailor a modern video foundation model to the cartoon domain while keeping its temporal prior intact. Requiring as few as a single sketch and a colored reference frame, ToonComposer excels with sparse inputs, while also supporting multiple sketches at any temporal location for more precise motion control. This dual capability reduces manual workload and improves flexibility, empowering artists in real-world scenarios. To evaluate our model, we further created PKBench, a benchmark featuring human-drawn sketches that simulate real-world use cases. Our evaluation demonstrates that ToonComposer outperforms existing methods in visual quality, motion consistency, and production efficiency, offering a superior and more flexible solution for AI-assisted cartoon production.</p> + https://arxiv.org/abs/2508.10881 + Thu, 14 Aug 2025 17:50:11 +0000 - AnyCap Project: A Unified Framework, Dataset, and Benchmark for Controllable Omni-modal Captioning - https://arxiv.org/abs/2507.12841 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.12841.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yiming Ren, Zhiqiang Lin, Yu Li, Gao Meng, Weiyun Wang, Junjie Wang, Zicheng Lin, Jifeng Dai, Yujiu Yang, Wenhai Wang, Ruihang Chu</p><p><b>Upvotes:</b> 39</p><p><b>Summary:</b> Controllable captioning is essential for precise multimodal alignment and instruction following, yet existing models often lack fine-grained control and reliable evaluation protocols. To address this gap, we present the AnyCap Project, an integrated solution spanning model, dataset, and evaluation. We introduce AnyCapModel (ACM), a lightweight plug-and-play framework that enhances the controllability of existing foundation models for omni-modal captioning without retraining the base model. ACM reuses the original captions from base models while incorporating user instructions and modality features to generate improved captions. To remedy the data scarcity in controllable multimodal captioning, we build AnyCapDataset (ACD), covering three modalities, 28 user-instruction types, and 300\,k high-quality data entries. We further propose AnyCapEval, a new benchmark that provides more reliable evaluation metrics for controllable captioning by decoupling content accuracy and stylistic fidelity. ACM markedly improves caption quality across a diverse set of base models on AnyCapEval. Notably, ACM-8B raises GPT-4o\'s content scores by 45\% and style scores by 12\%, and it also achieves substantial gains on widely used benchmarks such as MIA-Bench and VidCapBench.</p> - https://arxiv.org/abs/2507.12841 - Thu, 17 Jul 2025 07:04:05 +0000 + BeyondWeb: Lessons from Scaling Synthetic Data for Trillion-scale Pretraining + https://arxiv.org/abs/2508.10975 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.10975.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Pratyush Maini, Vineeth Dorna, Parth Doshi, Aldo Carranza, Fan Pan, Jack Urbanek, Paul Burstein, Alex Fang, Alvin Deng, Amro Abbas, Brett Larsen, Cody Blakeney, Charvi Bannur, Christina Baek, Darren Teh, David Schwab, Haakon Mongstad, Haoli Yin, Josh Wills, Kaleigh Mentzer, Luke Merrick, Ricardo Monti, Rishabh Adiga, Siddharth Joshi, Spandan Das, Zhengping Wang, Bogdan Gaza, Ari Morcos, Matthew Leavitt</p><p><b>Upvotes:</b> 56</p><p><b>Summary:</b> Recent advances in large language model (LLM) pretraining have shown that simply scaling data quantity eventually leads to diminishing returns, hitting a data wall. In response, the use of synthetic data for pretraining has emerged as a promising paradigm for pushing the frontier of performance. Despite this, the factors affecting synthetic data quality remain poorly understood. In this work, we introduce BeyondWeb, a synthetic data generation framework that produces high-quality synthetic data for pretraining. BeyondWeb significantly extends the capabilities of traditional web-scale datasets, outperforming state-of-the-art synthetic pretraining datasets such as Cosmopedia and Nemotron-CC's high-quality synthetic subset (Nemotron-Synth) by up to 5.1 percentage points (pp) and 2.6pp, respectively, when averaged across a suite of 14 benchmark evaluations. It delivers up to 7.7x faster training than open web data and 2.7x faster than Nemotron-Synth. Remarkably, a 3B model trained for 180B tokens on BeyondWeb outperforms an 8B model trained for the same token budget on Cosmopedia. We also present several insights from BeyondWeb on synthetic data for pretraining: what drives its benefits, which data to rephrase and how, and the impact of model size and family on data quality. Overall, our work shows that there's no silver bullet for generating high-quality synthetic pretraining data. The best outcomes require jointly optimizing many factors, a challenging task that requires rigorous science and practical expertise. Naive approaches can yield modest improvements, potentially at great cost, while well-executed methods can yield transformative improvements, as exemplified by BeyondWeb.</p> + https://arxiv.org/abs/2508.10975 + Thu, 14 Aug 2025 17:55:47 +0000 - The Imitation Game: Turing Machine Imitator is Length Generalizable Reasoner - https://arxiv.org/abs/2507.13332 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.13332.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhouqi Hua, Wenwei Zhang, Chengqi Lyu, Yuzhe Gu, Songyang Gao, Kuikun Liu, Kai Chen</p><p><b>Upvotes:</b> 47</p><p><b>Summary:</b> Length generalization, the ability to solve problems of longer sequences than those observed during training, poses a core challenge of Transformer-based large language models (LLM). Although existing studies have predominantly focused on data-driven approaches for arithmetic operations and symbolic manipulation tasks, these approaches tend to be task-specific with limited overall performance. To pursue a more general solution, this paper focuses on a broader case of reasoning problems that are computable, i.e., problems that algorithms can solve, thus can be solved by the Turing Machine. From this perspective, this paper proposes Turing MAchine Imitation Learning (TAIL) to improve the length generalization ability of LLMs. TAIL synthesizes chain-of-thoughts (CoT) data that imitate the execution process of a Turing Machine by computer programs, which linearly expands the reasoning steps into atomic states to alleviate shortcut learning and explicit memory fetch mechanism to reduce the difficulties of dynamic and long-range data access in elementary operations. To validate the reliability and universality of TAIL, we construct a challenging synthetic dataset covering 8 classes of algorithms and 18 tasks. Without bells and whistles, TAIL significantly improves the length generalization ability as well as the performance of Qwen2.5-7B on various tasks using only synthetic data, surpassing previous methods and DeepSeek-R1. The experimental results reveal that the key concepts in the Turing Machine, instead of the thinking styles, are indispensable for TAIL for length generalization, through which the model exhibits read-and-write behaviors consistent with the properties of the Turing Machine in their attention layers. This work provides a promising direction for future research in the learning of LLM reasoning from synthetic data.</p> - https://arxiv.org/abs/2507.13332 - Thu, 17 Jul 2025 17:50:07 +0000 + When Punctuation Matters: A Large-Scale Comparison of Prompt Robustness Methods for LLMs + https://arxiv.org/abs/2508.11383 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.11383.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mikhail Seleznyov, Mikhail Chaichuk, Gleb Ershov, Alexander Panchenko, Elena Tutubalina, Oleg Somov</p><p><b>Upvotes:</b> 39</p><p><b>Summary:</b> Large Language Models (LLMs) are highly sensitive to subtle, non-semantic variations in prompt phrasing and formatting. In this work, we present the first systematic evaluation of 5 methods for improving prompt robustness within a unified experimental framework. We benchmark these techniques on 8 models from Llama, Qwen and Gemma families across 52 tasks from Natural Instructions dataset. Our evaluation covers robustness methods from both fine-tuned and in-context learning paradigms, and tests their generalization against multiple types of distribution shifts. Finally, we extend our analysis to GPT-4.1 and DeepSeek V3 to assess frontier models' current robustness to format perturbations. Our findings offer actionable insights into the relative effectiveness of these robustness methods, enabling practitioners to make informed decisions when aiming for stable and reliable LLM performance in real-world applications. Code: https://github.com/AIRI-Institute/when-punctuation-matters.</p> + https://arxiv.org/abs/2508.11383 + Fri, 15 Aug 2025 10:32:50 +0000 - A Survey of Context Engineering for Large Language Models - https://arxiv.org/abs/2507.13334 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.13334.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lingrui Mei, Jiayu Yao, Yuyao Ge, Yiwei Wang, Baolong Bi, Yujun Cai, Jiazhi Liu, Mingyu Li, Zhong-Zhi Li, Duzhen Zhang, Chenlin Zhou, Jiayi Mao, Tianze Xia, Jiafeng Guo, Shenghua Liu</p><p><b>Upvotes:</b> 221</p><p><b>Summary:</b> The performance of Large Language Models (LLMs) is fundamentally determined by the contextual information provided during inference. This survey introduces Context Engineering, a formal discipline that transcends simple prompt design to encompass the systematic optimization of information payloads for LLMs. We present a comprehensive taxonomy decomposing Context Engineering into its foundational components and the sophisticated implementations that integrate them into intelligent systems. We first examine the foundational components: context retrieval and generation, context processing and context management. We then explore how these components are architecturally integrated to create sophisticated system implementations: retrieval-augmented generation (RAG), memory systems and tool-integrated reasoning, and multi-agent systems. Through this systematic analysis of over 1300 research papers, our survey not only establishes a technical roadmap for the field but also reveals a critical research gap: a fundamental asymmetry exists between model capabilities. While current models, augmented by advanced context engineering, demonstrate remarkable proficiency in understanding complex contexts, they exhibit pronounced limitations in generating equally sophisticated, long-form outputs. Addressing this gap is a defining priority for future research. Ultimately, this survey provides a unified framework for both researchers and engineers advancing context-aware AI.</p> - https://arxiv.org/abs/2507.13334 - Thu, 17 Jul 2025 17:50:36 +0000 + Ovis2.5 Technical Report + https://arxiv.org/abs/2508.11737 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.11737.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shiyin Lu, Yang Li, Yu Xia, Yuwei Hu, Shanshan Zhao, Yanqing Ma, Zhichao Wei, Yinglun Li, Lunhao Duan, Jianshan Zhao, Yuxuan Han, Haijun Li, Wanying Chen, Junke Tang, Chengkun Hou, Zhixing Du, Tianli Zhou, Wenjie Zhang, Huping Ding, Jiahe Li, Wen Li, Gui Hu, Yiliang Gu, Siran Yang, Jiamang Wang, Hailong Sun, Yibo Wang, Hui Sun, Jinlong Huang, Yuping He, Shengze Shi, Weihong Zhang, Guodong Zheng, Junpeng Jiang, Sensen Gao, Yi-Feng Wu, Sijia Chen, Yuhui Chen, Qing-Guo Chen, Zhao Xu, Weihua Luo, Kaifu Zhang</p><p><b>Upvotes:</b> 104</p><p><b>Summary:</b> We present Ovis2.5, a successor to Ovis2 designed for native-resolution visual perception and strong multimodal reasoning. Ovis2.5 integrates a native-resolution vision transformer that processes images at their native, variable resolutions, avoiding the degradation from fixed-resolution tiling and preserving both fine detail and global layout -- crucial for visually dense content like complex charts. To strengthen reasoning, we train the model to move beyond linear chain-of-thought and perform reflection -- including self-checking and revision. This advanced capability is exposed as an optional "thinking mode" at inference time, allowing users to trade latency for enhanced accuracy on difficult inputs. The model is trained via a comprehensive five-phase curriculum that progressively builds its skills. The process begins with foundational visual and multimodal pretraining, advances through large-scale instruction tuning, and culminates in alignment and reasoning enhancement using DPO and GRPO. To scale these upgrades efficiently, we employ multimodal data packing and hybrid parallelism, yielding a significant end-to-end speedup. We release two open-source models: Ovis2.5-9B and Ovis2.5-2B. The latter continues the "small model, big performance" philosophy of Ovis2, making it ideal for resource-constrained, on-device scenarios. On the OpenCompass multimodal leaderboard, Ovis2.5-9B averages 78.3, marking a substantial improvement over its predecessor, Ovis2-8B, and achieving state-of-the-art results among open-source MLLMs in the sub-40B parameter range; Ovis2.5-2B scores 73.9, establishing SOTA for its size. Beyond aggregate scores, Ovis2.5 achieves leading results on STEM benchmarks, exhibits strong capabilities on grounding and video tasks, and achieves open-source SOTA at its scale for complex chart analysis.</p> + https://arxiv.org/abs/2508.11737 + Fri, 15 Aug 2025 17:01:08 +0000 - Diffuman4D: 4D Consistent Human View Synthesis from Sparse-View Videos with Spatio-Temporal Diffusion Models - https://arxiv.org/abs/2507.13344 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.13344.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yudong Jin, Sida Peng, Xuan Wang, Tao Xie, Zhen Xu, Yifan Yang, Yujun Shen, Hujun Bao, Xiaowei Zhou</p><p><b>Upvotes:</b> 52</p><p><b>Summary:</b> This paper addresses the challenge of high-fidelity view synthesis of humans with sparse-view videos as input. Previous methods solve the issue of insufficient observation by leveraging 4D diffusion models to generate videos at novel viewpoints. However, the generated videos from these models often lack spatio-temporal consistency, thus degrading view synthesis quality. In this paper, we propose a novel sliding iterative denoising process to enhance the spatio-temporal consistency of the 4D diffusion model. Specifically, we define a latent grid in which each latent encodes the image, camera pose, and human pose for a certain viewpoint and timestamp, then alternately denoising the latent grid along spatial and temporal dimensions with a sliding window, and finally decode the videos at target viewpoints from the corresponding denoised latents. Through the iterative sliding, information flows sufficiently across the latent grid, allowing the diffusion model to obtain a large receptive field and thus enhance the 4D consistency of the output, while making the GPU memory consumption affordable. The experiments on the DNA-Rendering and ActorsHQ datasets demonstrate that our method is able to synthesize high-quality and consistent novel-view videos and significantly outperforms the existing approaches. See our project page for interactive demos and video results: https://diffuman4d.github.io/ .</p> - https://arxiv.org/abs/2507.13344 - Thu, 17 Jul 2025 17:59:17 +0000 + Thyme: Think Beyond Images + https://arxiv.org/abs/2508.11630 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.11630.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yi-Fan Zhang, Xingyu Lu, Shukang Yin, Chaoyou Fu, Wei Chen, Xiao Hu, Bin Wen, Kaiyu Jiang, Changyi Liu, Tianke Zhang, Haonan Fan, Kaibing Chen, Jiankang Chen, Haojie Ding, Kaiyu Tang, Zhang Zhang, Liang Wang, Fan Yang, Tingting Gao, Guorui Zhou</p><p><b>Upvotes:</b> 77</p><p><b>Summary:</b> Following OpenAI's introduction of the ``thinking with images'' concept, recent efforts have explored stimulating the use of visual information in the reasoning process to enhance model performance in perception and reasoning tasks. However, to the best of our knowledge, no open-source work currently offers a feature set as rich as proprietary models (O3), which can perform diverse image manipulations and simultaneously enhance logical reasoning capabilities through code. In this paper, we make a preliminary attempt in this direction by introducing Thyme (Think Beyond Images), a novel paradigm for enabling MLLMs to transcend existing ``think with images'' approaches by autonomously generating and executing diverse image processing and computational operations via executable code. This approach not only facilitates a rich, on-the-fly set of image manipulations (e.g., cropping, rotation, contrast enhancement) but also allows for mathematical computations, all while maintaining high autonomy in deciding when and how to apply these operations. We activate this capability through a two-stage training strategy: an initial SFT on a curated dataset of 500K samples to teach code generation, followed by a RL phase to refine decision-making. For the RL stage, we manually collect and design high-resolution question-answer pairs to increase the learning difficulty, and we propose GRPO-ATS (Group Relative Policy Optimization with Adaptive Temperature Sampling), an algorithm that applies distinct temperatures to text and code generation to balance reasoning exploration with code execution precision. We conduct extensive experimental analysis and ablation studies. Comprehensive evaluations on nearly 20 benchmarks show that Thyme yields significant and consistent performance gains, particularly in challenging high-resolution perception and complex reasoning tasks.</p> + https://arxiv.org/abs/2508.11630 + Fri, 15 Aug 2025 17:59:49 +0000 - π^3: Scalable Permutation-Equivariant Visual Geometry Learning - https://arxiv.org/abs/2507.13347 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.13347.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yifan Wang, Jianjun Zhou, Haoyi Zhu, Wenzheng Chang, Yang Zhou, Zizun Li, Junyi Chen, Jiangmiao Pang, Chunhua Shen, Tong He</p><p><b>Upvotes:</b> 62</p><p><b>Summary:</b> We introduce pi^3, a feed-forward neural network that offers a novel approach to visual geometry reconstruction, breaking the reliance on a conventional fixed reference view. Previous methods often anchor their reconstructions to a designated viewpoint, an inductive bias that can lead to instability and failures if the reference is suboptimal. In contrast, pi^3 employs a fully permutation-equivariant architecture to predict affine-invariant camera poses and scale-invariant local point maps without any reference frames. This design makes our model inherently robust to input ordering and highly scalable. These advantages enable our simple and bias-free approach to achieve state-of-the-art performance on a wide range of tasks, including camera pose estimation, monocular/video depth estimation, and dense point map reconstruction. Code and models are publicly available.</p> - https://arxiv.org/abs/2507.13347 - Thu, 17 Jul 2025 17:59:53 +0000 + FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction + https://arxiv.org/abs/2508.11987 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.11987.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhiyuan Zeng, Jiashuo Liu, Siyuan Chen, Tianci He, Yali Liao, Jinpeng Wang, Zaiyuan Wang, Yang Yang, Lingyue Yin, Mingren Yin, Zhenwei Zhu, Tianle Cai, Zehui Chen, Jiecao Chen, Yantao Du, Xiang Gao, Jiacheng Guo, Liang Hu, Jianpeng Jiao, Xiangsheng Li, Jingkai Liu, Shuang Ni, Zhoufutu Wen, Ge Zhang, Kaiyuan Zhang, Xin Zhou, Jose Blanchet, Xipeng Qiu, Mengdi Wang, Wenhao Huang</p><p><b>Upvotes:</b> 62</p><p><b>Summary:</b> Future prediction is a complex task for LLM agents, requiring a high level of analytical thinking, information gathering, contextual understanding, and decision-making under uncertainty. Agents must not only gather and interpret vast amounts of dynamic information but also integrate diverse data sources, weigh uncertainties, and adapt predictions based on emerging trends, just as human experts do in fields like politics, economics, and finance. Despite its importance, no large-scale benchmark exists for evaluating agents on future prediction, largely due to challenges in handling real-time updates and retrieving timely, accurate answers. To address this, we introduce FutureX, a dynamic and live evaluation benchmark specifically designed for LLM agents performing future prediction tasks. FutureX is the largest and most diverse live benchmark for future prediction, supporting real-time daily updates and eliminating data contamination through an automated pipeline for question gathering and answer collection. We evaluate 25 LLM/agent models, including those with reasoning, search capabilities, and integration of external tools such as the open-source Deep Research Agent and closed-source Deep Research models. This comprehensive evaluation assesses agents' adaptive reasoning and performance in dynamic environments. Additionally, we provide in-depth analyses of agents' failure modes and performance pitfalls in future-oriented tasks, including the vulnerability to fake web pages and the temporal validity. Our goal is to establish a dynamic, contamination-free evaluation standard that drives the development of LLM agents capable of performing at the level of professional human analysts in complex reasoning and predictive thinking.</p> + https://arxiv.org/abs/2508.11987 + Sat, 16 Aug 2025 08:54:08 +0000 - VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learning - https://arxiv.org/abs/2507.13348 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.13348.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Senqiao Yang, Junyi Li, Xin Lai, Bei Yu, Hengshuang Zhao, Jiaya Jia</p><p><b>Upvotes:</b> 71</p><p><b>Summary:</b> Recent advancements in vision-language models (VLMs) have improved performance by increasing the number of visual tokens, which are often significantly longer than text tokens. However, we observe that most real-world scenarios do not require such an extensive number of visual tokens. While the performance drops significantly in a small subset of OCR-related tasks, models still perform accurately in most other general VQA tasks with only 1/4 resolution. Therefore, we propose to dynamically process distinct samples with different resolutions, and present a new paradigm for visual token compression, namely, VisionThink. It starts with a downsampled image and smartly decides whether it is sufficient for problem solving. Otherwise, the model could output a special token to request the higher-resolution image. Compared to existing Efficient VLM methods that compress tokens using fixed pruning ratios or thresholds, VisionThink autonomously decides whether to compress tokens case by case. As a result, it demonstrates strong fine-grained visual understanding capability on OCR-related tasks, and meanwhile saves substantial visual tokens on simpler tasks. We adopt reinforcement learning and propose the LLM-as-Judge strategy to successfully apply RL to general VQA tasks. Moreover, we carefully design a reward function and penalty mechanism to achieve a stable and reasonable image resize call ratio. Extensive experiments demonstrate the superiority, efficiency, and effectiveness of our method. Our code is available at https://github.com/dvlab-research/VisionThink.</p> - https://arxiv.org/abs/2507.13348 - Thu, 17 Jul 2025 17:59:55 +0000 + Next Visual Granularity Generation + https://arxiv.org/abs/2508.12811 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.12811.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yikai Wang, Zhouxia Wang, Zhonghua Wu, Qingyi Tao, Kang Liao, Chen Change Loy</p><p><b>Upvotes:</b> 46</p><p><b>Summary:</b> We propose a novel approach to image generation by decomposing an image into a structured sequence, where each element in the sequence shares the same spatial resolution but differs in the number of unique tokens used, capturing different level of visual granularity. Image generation is carried out through our newly introduced Next Visual Granularity (NVG) generation framework, which generates a visual granularity sequence beginning from an empty image and progressively refines it, from global layout to fine details, in a structured manner. This iterative process encodes a hierarchical, layered representation that offers fine-grained control over the generation process across multiple granularity levels. We train a series of NVG models for class-conditional image generation on the ImageNet dataset and observe clear scaling behavior. Compared to the VAR series, NVG consistently outperforms it in terms of FID scores (3.30 -> 3.03, 2.57 ->2.44, 2.09 -> 2.06). We also conduct extensive analysis to showcase the capability and potential of the NVG framework. Our code and models will be released.</p> + https://arxiv.org/abs/2508.12811 + Mon, 18 Aug 2025 10:47:37 +0000 - nablaNABLA: Neighborhood Adaptive Block-Level Attention - https://arxiv.org/abs/2507.13546 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.13546.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dmitrii Mikhailov, Aleksey Letunovskiy, Maria Kovaleva, Vladimir Arkhipkin, Vladimir Korviakov, Vladimir Polovnikov, Viacheslav Vasilev, Evelina Sidorova, Denis Dimitrov</p><p><b>Upvotes:</b> 117</p><p><b>Summary:</b> Recent progress in transformer-based architectures has demonstrated remarkable success in video generation tasks. However, the quadratic complexity of full attention mechanisms remains a critical bottleneck, particularly for high-resolution and long-duration video sequences. In this paper, we propose NABLA, a novel Neighborhood Adaptive Block-Level Attention mechanism that dynamically adapts to sparsity patterns in video diffusion transformers (DiTs). By leveraging block-wise attention with adaptive sparsity-driven threshold, NABLA reduces computational overhead while preserving generative quality. Our method does not require custom low-level operator design and can be seamlessly integrated with PyTorch's Flex Attention operator. Experiments demonstrate that NABLA achieves up to 2.7x faster training and inference compared to baseline almost without compromising quantitative metrics (CLIP score, VBench score, human evaluation score) and visual quality drop. The code and model weights are available here: https://github.com/gen-ai-team/Wan2.1-NABLA</p> - https://arxiv.org/abs/2507.13546 - Thu, 17 Jul 2025 21:36:36 +0000 + S^2-Guidance: Stochastic Self Guidance for Training-Free Enhancement of Diffusion Models + https://arxiv.org/abs/2508.12880 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.12880.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chubin Chen, Jiashu Zhu, Xiaokun Feng, Nisha Huang, Meiqi Wu, Fangyuan Mao, Jiahong Wu, Xiangxiang Chu, Xiu Li</p><p><b>Upvotes:</b> 44</p><p><b>Summary:</b> Classifier-free Guidance (CFG) is a widely used technique in modern diffusion models for enhancing sample quality and prompt adherence. However, through an empirical analysis on Gaussian mixture modeling with a closed-form solution, we observe a discrepancy between the suboptimal results produced by CFG and the ground truth. The model's excessive reliance on these suboptimal predictions often leads to semantic incoherence and low-quality outputs. To address this issue, we first empirically demonstrate that the model's suboptimal predictions can be effectively refined using sub-networks of the model itself. Building on this insight, we propose S^2-Guidance, a novel method that leverages stochastic block-dropping during the forward process to construct stochastic sub-networks, effectively guiding the model away from potential low-quality predictions and toward high-quality outputs. Extensive qualitative and quantitative experiments on text-to-image and text-to-video generation tasks demonstrate that S^2-Guidance delivers superior performance, consistently surpassing CFG and other advanced guidance strategies. Our code will be released.</p> + https://arxiv.org/abs/2508.12880 + Mon, 18 Aug 2025 12:31:20 +0000 - A Data-Centric Framework for Addressing Phonetic and Prosodic Challenges in Russian Speech Generative Models - https://arxiv.org/abs/2507.13563 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.13563.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kirill Borodin, Nikita Vasiliev, Vasiliy Kudryavtsev, Maxim Maslov, Mikhail Gorodnichev, Oleg Rogov, Grach Mkrtchian</p><p><b>Upvotes:</b> 50</p><p><b>Summary:</b> Russian speech synthesis presents distinctive challenges, including vowel reduction, consonant devoicing, variable stress patterns, homograph ambiguity, and unnatural intonation. This paper introduces Balalaika, a novel dataset comprising more than 2,000 hours of studio-quality Russian speech with comprehensive textual annotations, including punctuation and stress markings. Experimental results show that models trained on Balalaika significantly outperform those trained on existing datasets in both speech synthesis and enhancement tasks. We detail the dataset construction pipeline, annotation methodology, and results of comparative evaluations.</p> - https://arxiv.org/abs/2507.13563 - Thu, 17 Jul 2025 22:41:40 +0000 + Has GPT-5 Achieved Spatial Intelligence? An Empirical Study + https://arxiv.org/abs/2508.13142 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.13142.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhongang Cai, Yubo Wang, Qingping Sun, Ruisi Wang, Chenyang Gu, Wanqi Yin, Zhiqian Lin, Zhitao Yang, Chen Wei, Xuanke Shi, Kewang Deng, Xiaoyang Han, Zukai Chen, Jiaqi Li, Xiangyu Fan, Hanming Deng, Lewei Lu, Bo Li, Ziwei Liu, Quan Wang, Dahua Lin, Lei Yang</p><p><b>Upvotes:</b> 31</p><p><b>Summary:</b> Multi-modal models have achieved remarkable progress in recent years. Nevertheless, they continue to exhibit notable limitations in spatial understanding and reasoning, which are fundamental capabilities to achieving artificial general intelligence. With the recent release of GPT-5, allegedly the most powerful AI model to date, it is timely to examine where the leading models stand on the path toward spatial intelligence. First, we propose a comprehensive taxonomy of spatial tasks that unifies existing benchmarks and discuss the challenges in ensuring fair evaluation. We then evaluate state-of-the-art proprietary and open-source models on eight key benchmarks, at a cost exceeding one billion total tokens. Our empirical study reveals that (1) GPT-5 demonstrates unprecedented strength in spatial intelligence, yet (2) still falls short of human performance across a broad spectrum of tasks. Moreover, we (3) identify the more challenging spatial intelligence problems for multi-modal models, and (4) proprietary models do not exhibit a decisive advantage when facing the most difficult problems. In addition, we conduct a qualitative evaluation across a diverse set of scenarios that are intuitive for humans yet fail even the most advanced multi-modal models.</p> + https://arxiv.org/abs/2508.13142 + Mon, 18 Aug 2025 17:55:17 +0000 - NoHumansRequired: Autonomous High-Quality Image Editing Triplet Mining - https://arxiv.org/abs/2507.14119 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.14119.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Maksim Kuprashevich, Grigorii Alekseenko, Irina Tolstykh, Georgii Fedorov, Bulat Suleimanov, Vladimir Dokholyan, Aleksandr Gordeev</p><p><b>Upvotes:</b> 53</p><p><b>Summary:</b> Recent advances in generative modeling enable image editing assistants that follow natural language instructions without additional user input. Their supervised training requires millions of triplets: original image, instruction, edited image. Yet mining pixel-accurate examples is hard. Each edit must affect only prompt-specified regions, preserve stylistic coherence, respect physical plausibility, and retain visual appeal. The lack of robust automated edit-quality metrics hinders reliable automation at scale. We present an automated, modular pipeline that mines high-fidelity triplets across domains, resolutions, instruction complexities, and styles. Built on public generative models and running without human intervention, our system uses a task-tuned Gemini validator to score instruction adherence and aesthetics directly, removing any need for segmentation or grounding models. Inversion and compositional bootstrapping enlarge the mined set by approximately 2.2x, enabling large-scale high-fidelity training data. By automating the most repetitive annotation steps, the approach allows a new scale of training without human labeling effort. To democratize research in this resource-intensive area, we release NHR-Edit: an open dataset of 358k high-quality triplets. In the largest cross-dataset evaluation, it surpasses all public alternatives. We also release Bagel-NHR-Edit, an open-source fine-tuned Bagel model, which achieves state-of-the-art metrics in our experiments.</p> - https://arxiv.org/abs/2507.14119 - Fri, 18 Jul 2025 17:50:00 +0000 + 4DNeX: Feed-Forward 4D Generative Modeling Made Easy + https://arxiv.org/abs/2508.13154 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.13154.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhaoxi Chen, Tianqi Liu, Long Zhuo, Jiawei Ren, Zeng Tao, He Zhu, Fangzhou Hong, Liang Pan, Ziwei Liu</p><p><b>Upvotes:</b> 58</p><p><b>Summary:</b> We present 4DNeX, the first feed-forward framework for generating 4D (i.e., dynamic 3D) scene representations from a single image. In contrast to existing methods that rely on computationally intensive optimization or require multi-frame video inputs, 4DNeX enables efficient, end-to-end image-to-4D generation by fine-tuning a pretrained video diffusion model. Specifically, 1) to alleviate the scarcity of 4D data, we construct 4DNeX-10M, a large-scale dataset with high-quality 4D annotations generated using advanced reconstruction approaches. 2) we introduce a unified 6D video representation that jointly models RGB and XYZ sequences, facilitating structured learning of both appearance and geometry. 3) we propose a set of simple yet effective adaptation strategies to repurpose pretrained video diffusion models for 4D modeling. 4DNeX produces high-quality dynamic point clouds that enable novel-view video synthesis. Extensive experiments demonstrate that 4DNeX outperforms existing 4D generation methods in efficiency and generalizability, offering a scalable solution for image-to-4D modeling and laying the foundation for generative 4D world models that simulate dynamic scene evolution.</p> + https://arxiv.org/abs/2508.13154 + Mon, 18 Aug 2025 17:59:55 +0000 - Franca: Nested Matryoshka Clustering for Scalable Visual Representation Learning - https://arxiv.org/abs/2507.14137 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.14137.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shashanka Venkataramanan, Valentinos Pariza, Mohammadreza Salehi, Lukas Knobel, Spyros Gidaris, Elias Ramzi, Andrei Bursuc, Yuki M. Asano</p><p><b>Upvotes:</b> 31</p><p><b>Summary:</b> We present Franca (pronounced Fran-ka): free one; the first fully open-source (data, code, weights) vision foundation model that matches and in many cases surpasses the performance of state-of-the-art proprietary models, e.g., DINOv2, CLIP, SigLIPv2, etc. Our approach is grounded in a transparent training pipeline inspired by Web-SSL and uses publicly available data: ImageNet-21K and a subset of ReLAION-2B. Beyond model release, we tackle critical limitations in SSL clustering methods. While modern models rely on assigning image features to large codebooks via clustering algorithms like Sinkhorn-Knopp, they fail to account for the inherent ambiguity in clustering semantics. To address this, we introduce a parameter-efficient, multi-head clustering projector based on nested Matryoshka representations. This design progressively refines features into increasingly fine-grained clusters without increasing the model size, enabling both performance and memory efficiency. Additionally, we propose a novel positional disentanglement strategy that explicitly removes positional biases from dense representations, thereby improving the encoding of semantic content. This leads to consistent gains on several downstream benchmarks, demonstrating the utility of cleaner feature spaces. Our contributions establish a new standard for transparent, high-performance vision models and open a path toward more reproducible and generalizable foundation models for the broader AI community. The code and model checkpoints are available at https://github.com/valeoai/Franca.</p> - https://arxiv.org/abs/2507.14137 - Fri, 18 Jul 2025 17:59:55 +0000 + From Scores to Skills: A Cognitive Diagnosis Framework for Evaluating Financial Large Language Models + https://arxiv.org/abs/2508.13491 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.13491.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ziyan Kuang, Feiyu Zhu, Maowei Jiang, Yanzhao Lai, Zelin Wang, Zhitong Wang, Meikang Qiu, Jiajia Huang, Min Peng, Qianqian Xie, Sophia Ananiadou</p><p><b>Upvotes:</b> 58</p><p><b>Summary:</b> Large Language Models (LLMs) have shown promise for financial applications, yet their suitability for this high-stakes domain remains largely unproven due to inadequacies in existing benchmarks. Existing benchmarks solely rely on score-level evaluation, summarizing performance with a single score that obscures the nuanced understanding of what models truly know and their precise limitations. They also rely on datasets that cover only a narrow subset of financial concepts, while overlooking other essentials for real-world applications. To address these gaps, we introduce FinCDM, the first cognitive diagnosis evaluation framework tailored for financial LLMs, enabling the evaluation of LLMs at the knowledge-skill level, identifying what financial skills and knowledge they have or lack based on their response patterns across skill-tagged tasks, rather than a single aggregated number. We construct CPA-QKA, the first cognitively informed financial evaluation dataset derived from the Certified Public Accountant (CPA) examination, with comprehensive coverage of real-world accounting and financial skills. It is rigorously annotated by domain experts, who author, validate, and annotate questions with high inter-annotator agreement and fine-grained knowledge labels. Our extensive experiments on 30 proprietary, open-source, and domain-specific LLMs show that FinCDM reveals hidden knowledge gaps, identifies under-tested areas such as tax and regulatory reasoning overlooked by traditional benchmarks, and uncovers behavioral clusters among models. FinCDM introduces a new paradigm for financial LLM evaluation by enabling interpretable, skill-aware diagnosis that supports more trustworthy and targeted model development, and all datasets and evaluation scripts will be publicly released to support further research.</p> + https://arxiv.org/abs/2508.13491 + Tue, 19 Aug 2025 03:52:15 +0000 - MiroMind-M1: An Open-Source Advancement in Mathematical Reasoning via Context-Aware Multi-Stage Policy Optimization - https://arxiv.org/abs/2507.14683 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.14683.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xingxuan Li, Yao Xiao, Dianwen Ng, Hai Ye, Yue Deng, Xiang Lin, Bin Wang, Zhanfeng Mo, Chong Zhang, Yueyi Zhang, Zonglin Yang, Ruilin Li, Lei Lei, Shihao Xu, Han Zhao, Weiling Chen, Feng Ji, Lidong Bing</p><p><b>Upvotes:</b> 117</p><p><b>Summary:</b> Large language models have recently evolved from fluent text generation to advanced reasoning across diverse domains, giving rise to reasoning language models. Among these domains, mathematical reasoning serves as a representative benchmark as it requires precise multi-step logic and abstract reasoning, which can be generalized to other tasks. While closed-source RLMs such as GPT-o3 demonstrate impressive reasoning capabilities, their proprietary nature limits transparency and reproducibility. Although many open-source projects aim to close this gap, most of them lack sufficient openness by omitting critical resources such as datasets and detailed training configurations, which hinders reproducibility. To contribute toward greater transparency in RLM development, we introduce the MiroMind-M1 series, a set of fully open-source RLMs built on the Qwen-2.5 backbone that match or exceed the performance of existing open-source RLMs. Specifically, our models are trained in two stages: SFT on a carefully curated corpus of 719K math-reasoning problems with verified CoT trajectories, followed by RLVR on 62K challenging and verifiable problems. To enhance the robustness and efficiency of the RLVR process, we introduce Context-Aware Multi-Stage Policy Optimization, an algorithm that integrates length-progressive training with an adaptive repetition penalty to encourage context-aware RL training. Our model achieves state-of-the-art or competitive performance and superior token efficiency among Qwen-2.5-based open-source 7B and 32B models on the AIME24, AIME25, and MATH benchmarks. To facilitate reproducibility, we release the complete stack: models (MiroMind-M1-SFT-7B, MiroMind-M1-RL-7B, MiroMind-M1-RL-32B); datasets (MiroMind-M1-SFT-719K, MiroMind-M1-RL-62K); and all training and evaluation configurations. We hope these resources will support further research and foster community advancement.</p> - https://arxiv.org/abs/2507.14683 - Sat, 19 Jul 2025 16:21:23 +0000 + Prompt Orchestration Markup Language + https://arxiv.org/abs/2508.13948 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.13948.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuge Zhang, Nan Chen, Jiahang Xu, Yuqing Yang</p><p><b>Upvotes:</b> 44</p><p><b>Summary:</b> Large Language Models (LLMs) require sophisticated prompting, yet current practices face challenges in structure, data integration, format sensitivity, and tooling. Existing methods lack comprehensive solutions for organizing complex prompts involving diverse data types (documents, tables, images) or managing presentation variations systematically. To address these gaps, we introduce POML (Prompt Orchestration Markup Language). POML employs component-based markup for logical structure (roles, tasks, examples), specialized tags for seamless data integration, and a CSS-like styling system to decouple content from presentation, reducing formatting sensitivity. It includes templating for dynamic prompts and a comprehensive developer toolkit (IDE support, SDKs) to improve version control and collaboration. We validate POML through two case studies demonstrating its impact on complex application integration (PomLink) and accuracy performance (TableQA), as well as a user study assessing its effectiveness in real-world development scenarios.</p> + https://arxiv.org/abs/2508.13948 + Tue, 19 Aug 2025 15:37:29 +0000 - The Invisible Leash: Why RLVR May Not Escape Its Origin - https://arxiv.org/abs/2507.14843 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.14843.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fang Wu, Weihao Xuan, Ximing Lu, Zaid Harchaoui, Yejin Choi</p><p><b>Upvotes:</b> 81</p><p><b>Summary:</b> Recent advances in large reasoning models highlight Reinforcement Learning with Verifiable Rewards (RLVR) as a promising method for enhancing AI's capabilities, particularly in solving complex logical tasks. However, it remains unclear whether RLVR truly expands a model's reasoning boundary or merely amplifies high-reward outputs that the base model already knows for improved precision. This study presents a theoretical and empirical investigation that provides fresh insights into the potential limits of RLVR. First, we offer a new theoretical perspective that RLVR is constrained by the base model's support-unable to sample solutions with zero initial probability-and operates as a conservative reweighting mechanism that may restrict the discovery of entirely original solutions. We also identify an entropy-reward tradeoff: while RLVR reliably enhances precision, it may progressively narrow exploration and potentially overlook correct yet underrepresented solutions. Extensive empirical experiments validate that while RLVR consistently improves pass@1, the shrinkage of empirical support generally outweighs the expansion of empirical support under larger sampling budgets, failing to recover correct answers that were previously accessible to the base model. Interestingly, we also observe that while RLVR sometimes increases token-level entropy, resulting in greater uncertainty at each generation step, answer-level entropy declines, indicating that these seemingly more uncertain paths ultimately converge onto a smaller set of distinct answers. Taken together, these findings reveal potential limits of RLVR in extending reasoning horizons. Breaking this invisible leash may require future algorithmic innovations such as explicit exploration mechanisms or hybrid strategies that seed probability mass into underrepresented solution regions.</p> - https://arxiv.org/abs/2507.14843 - Sun, 20 Jul 2025 07:04:08 +0000 + Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR + https://arxiv.org/abs/2508.14029 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.14029.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiao Liang, Zhongzhi Li, Yeyun Gong, Yelong Shen, Ying Nian Wu, Zhijiang Guo, Weizhu Chen</p><p><b>Upvotes:</b> 115</p><p><b>Summary:</b> Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as a key paradigm for post-training Large Language Models (LLMs), particularly for complex reasoning tasks. However, vanilla RLVR training has been shown to improve Pass@1 performance at the expense of policy entropy, leading to reduced generation diversity and limiting the Pass@k performance, which typically represents the upper bound of LLM reasoning capability. In this paper, we systematically analyze the policy's generation diversity from the perspective of training problems and find that augmenting and updating training problems helps mitigate entropy collapse during training. Based on these observations, we propose an online Self-play with Variational problem Synthesis (SvS) strategy for RLVR training, which uses the policy's correct solutions to synthesize variational problems while ensuring their reference answers remain identical to the originals. This self-improving strategy effectively maintains policy entropy during training and substantially improves Pass@k compared with standard RLVR, sustaining prolonged improvements and achieving absolute gains of 18.3% and 22.8% in Pass@32 performance on the competition-level AIME24 and AIME25 benchmarks. Experiments on 12 reasoning benchmarks across varying model sizes from 3B to 32B consistently demonstrate the generalizability and robustness of SvS.</p> + https://arxiv.org/abs/2508.14029 + Tue, 19 Aug 2025 17:42:45 +0000 - MUR: Momentum Uncertainty guided Reasoning for Large Language Models - https://arxiv.org/abs/2507.14958 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.14958.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hang Yan, Fangzhi Xu, Rongman Xu, Yifei Li, Jian Zhang, Haoran Luo, Xiaobao Wu, Luu Anh Tuan, Haiteng Zhao, Qika Lin, Jun Liu</p><p><b>Upvotes:</b> 45</p><p><b>Summary:</b> Large Language Models (LLMs) have achieved impressive performance on reasoning-intensive tasks, yet optimizing their reasoning efficiency remains an open challenge. While Test-Time Scaling (TTS) improves reasoning quality, it often leads to overthinking, wasting tokens on redundant computations. This work investigates how to efficiently and adaptively guide LLM test-time scaling without additional training. Inspired by the concept of momentum in physics, we propose Momentum Uncertainty-guided Reasoning (MUR), which dynamically allocates thinking budgets to critical reasoning steps by tracking and aggregating stepwise uncertainty over time. To support flexible inference-time control, we introduce gamma-control, a simple mechanism that tunes the reasoning budget via a single hyperparameter. We provide in-depth theoretical proof to support the superiority of MUR in terms of stability and biases. MUR is comprehensively evaluated against various TTS methods across four challenging benchmarks (MATH-500, AIME24, AIME25, and GPQA-diamond) using different sizes of recent Qwen3 models (1.7B, 4B, and 8B). Results demonstrate that MUR reduces computation by over 50% on average while improving accuracy by 0.62-3.37%.</p> - https://arxiv.org/abs/2507.14958 - Sun, 20 Jul 2025 13:36:19 +0000 + LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos + https://arxiv.org/abs/2508.14041 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.14041.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chin-Yang Lin, Cheng Sun, Fu-En Yang, Min-Hung Chen, Yen-Yu Lin, Yu-Lun Liu</p><p><b>Upvotes:</b> 57</p><p><b>Summary:</b> LongSplat addresses critical challenges in novel view synthesis (NVS) from casually captured long videos characterized by irregular camera motion, unknown camera poses, and expansive scenes. Current methods often suffer from pose drift, inaccurate geometry initialization, and severe memory limitations. To address these issues, we introduce LongSplat, a robust unposed 3D Gaussian Splatting framework featuring: (1) Incremental Joint Optimization that concurrently optimizes camera poses and 3D Gaussians to avoid local minima and ensure global consistency; (2) a robust Pose Estimation Module leveraging learned 3D priors; and (3) an efficient Octree Anchor Formation mechanism that converts dense point clouds into anchors based on spatial density. Extensive experiments on challenging benchmarks demonstrate that LongSplat achieves state-of-the-art results, substantially improving rendering quality, pose accuracy, and computational efficiency compared to prior approaches. Project page: https://linjohnss.github.io/longsplat/</p> + https://arxiv.org/abs/2508.14041 + Tue, 19 Aug 2025 17:59:56 +0000 - WebShaper: Agentically Data Synthesizing via Information-Seeking Formalization - https://arxiv.org/abs/2507.15061 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.15061.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhengwei Tao, Jialong Wu, Wenbiao Yin, Junkai Zhang, Baixuan Li, Haiyang Shen, Kuan Li, Liwen Zhang, Xinyu Wang, Yong Jiang, Pengjun Xie, Fei Huang, Jingren Zhou</p><p><b>Upvotes:</b> 44</p><p><b>Summary:</b> The advent of Large Language Model (LLM)-powered agents has revolutionized artificial intelligence by enabling solutions to complex, open-ended tasks through web-based information-seeking (IS) capabilities. The scarcity of high-quality training data has limited the development of IS agents. Existing approaches typically adopt an information-driven paradigm that first collects web data and then generates questions based on the retrieval. However, this may lead to inconsistency between information structure and reasoning structure, question and answer. To mitigate, we propose a formalization-driven IS data synthesis framework WebShaper to construct a dataset. WebShaper systematically formalizes IS tasks through set theory. Central to the formalization is the concept of Knowledge Projections (KP), which enables precise control over reasoning structure by KP operation compositions. During synthesis, we begin by creating seed tasks, then use a multi-step expansion process. At each step, an agentic Expander expands the current formal question more complex with retrieval and validation tools based on our formalization. We train our model on the synthesized dataset. Experiment results demonstrate that WebShaper achieves state-of-the-art performance among open-sourced IS agents on GAIA and WebWalkerQA benchmarks.</p> - https://arxiv.org/abs/2507.15061 - Sun, 20 Jul 2025 17:53:37 +0000 + NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model + https://arxiv.org/abs/2508.14444 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.14444.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> NVIDIA, Aarti Basant, Abhijit Khairnar, Abhijit Paithankar, Abhinav Khattar, Adi Renduchintala, Adithya Renduchintala, Aditya Malte, Akhiad Bercovich, Akshay Hazare, Alejandra Rico, Aleksander Ficek, Alex Kondratenko, Alex Shaposhnikov, Ali Taghibakhshi, Amelia Barton, Ameya Sunil Mahabaleshwarkar, Amy Shen, Andrew Tao, Ann Guan, Anna Shors, Anubhav Mandarwal, Arham Mehta, Arun Venkatesan, Ashton Sharabiani, Ashwath Aithal, Ashwin Poojary, Ayush Dattagupta, Balaram Buddharaju, Banghua Zhu, Barnaby Simkin, Bilal Kartal, Bita Darvish Rouhani, Bobby Chen, Boris Ginsburg, Brandon Norick, Brian Yu, Bryan Catanzaro, Charles Wang, Charlie Truong, Chetan Mungekar, Chintan Patel, Chris Alexiuk, Christian Munley, Christopher Parisien, Dan Su, Daniel Afrimi, Daniel Korzekwa, Daniel Rohrer, Daria Gitman, David Mosallanezhad, Deepak Narayanan, Dima Rekesh, Dina Yared, Dmytro Pykhtar, Dong Ahn, Duncan Riach, Eileen Long, Elliott Ning, Eric Chung, Erick Galinkin, Evelina Bakhturina, Gargi Prasad, Gerald Shen, Haim Elisha, Harsh Sharma, Hayley Ross, Helen Ngo, Herman Sahota, Hexin Wang, Hoo Chang Shin, Hua Huang, Iain Cunningham, Igor Gitman, Ivan Moshkov, Jaehun Jung, Jan Kautz, Jane Polak Scowcroft, Jared Casper, Jimmy Zhang, Jinze Xue, Jocelyn Huang, Joey Conway, John Kamalu, Jonathan Cohen, Joseph Jennings, Julien Veron Vialard, Junkeun Yi, Jupinder Parmar, Kari Briski, Katherine Cheung, Katherine Luna, Keith Wyss, Keshav Santhanam, Kezhi Kong, Krzysztof Pawelec, Kumar Anik, Kunlun Li, Kushan Ahmadian, Lawrence McAfee, Laya Sleiman, Leon Derczynski, Luis Vega, Maer Rodrigues de Melo, Makesh Narsimhan Sreedhar, Marcin Chochowski, Mark Cai, Markus Kliegl, Marta Stepniewska-Dziubinska, Matvei Novikov, Mehrzad Samadi, Meredith Price, Meriem Boubdir, Michael Boone, Michael Evans, Michal Bien, Michal Zawalski, Miguel Martinez, Mike Chrzanowski, Mohammad Shoeybi, Mostofa Patwary, Namit Dhameja, Nave Assaf, Negar Habibi, Nidhi Bhatia, Nikki Pope, Nima Tajbakhsh, Nirmal Kumar Juluru, Oleg Rybakov, Oleksii Hrinchuk, Oleksii Kuchaiev, Oluwatobi Olabiyi, Pablo Ribalta, Padmavathy Subramanian, Parth Chadha, Pavlo Molchanov, Peter Dykas, Peter Jin, Piotr Bialecki, Piotr Januszewski, Pradeep Thalasta, Prashant Gaikwad, Prasoon Varshney, Pritam Gundecha, Przemek Tredak, Rabeeh Karimi Mahabadi, Rajen Patel, Ran El-Yaniv, Ranjit Rajan, Ria Cheruvu, Rima Shahbazyan, Ritika Borkar, Ritu Gala, Roger Waleffe, Ruoxi Zhang, Russell J. Hewett, Ryan Prenger, Sahil Jain, Samuel Kriman, Sanjeev Satheesh, Saori Kaji, Sarah Yurick, Saurav Muralidharan, Sean Narenthiran, Seonmyeong Bak, Sepehr Sameni, Seungju Han, Shanmugam Ramasamy, Shaona Ghosh, Sharath Turuvekere Sreenivas, Shelby Thomas, Shizhe Diao, Shreya Gopal, Shrimai Prabhumoye, Shubham Toshniwal, Shuoyang Ding, Siddharth Singh, Siddhartha Jain, Somshubra Majumdar, Stefania Alborghetti, Syeda Nahida Akter, Terry Kong, Tim Moon, Tomasz Hliwiak, Tomer Asida, Tony Wang, Twinkle Vashishth, Tyler Poon, Udi Karpas, Vahid Noroozi, Venkat Srinivasan, Vijay Korthikanti, Vikram Fugro, Vineeth Kalluru, Vitaly Kurin, Vitaly Lavrukhin, Wasi Uddin Ahmad, Wei Du, Wonmin Byeon, Ximing Lu, Xin Dong, Yashaswi Karnati, Yejin Choi, Yian Zhang, Ying Lin, Yonggan Fu, Yoshi Suhara, Zhen Dong, Zhiyu Li, Zhongbo Zhu, Zijia Chen</p><p><b>Upvotes:</b> 31</p><p><b>Summary:</b> We introduce Nemotron-Nano-9B-v2, a hybrid Mamba-Transformer language model designed to increase throughput for reasoning workloads while achieving state-of-the-art accuracy compared to similarly-sized models. Nemotron-Nano-9B-v2 builds on the Nemotron-H architecture, in which the majority of the self-attention layers in the common Transformer architecture are replaced with Mamba-2 layers, to achieve improved inference speed when generating the long thinking traces needed for reasoning. We create Nemotron-Nano-9B-v2 by first pre-training a 12-billion-parameter model (Nemotron-Nano-12B-v2-Base) on 20 trillion tokens using an FP8 training recipe. After aligning Nemotron-Nano-12B-v2-Base, we employ the Minitron strategy to compress and distill the model with the goal of enabling inference on up to 128k tokens on a single NVIDIA A10G GPU (22GiB of memory, bfloat16 precision). Compared to existing similarly-sized models (e.g., Qwen3-8B), we show that Nemotron-Nano-9B-v2 achieves on-par or better accuracy on reasoning benchmarks while achieving up to 6x higher inference throughput in reasoning settings like 8k input and 16k output tokens. We are releasing Nemotron-Nano-9B-v2, Nemotron-Nano12B-v2-Base, and Nemotron-Nano-9B-v2-Base checkpoints along with the majority of our pre- and post-training datasets on Hugging Face.</p> + https://arxiv.org/abs/2508.14444 + Wed, 20 Aug 2025 06:00:57 +0000 - GR-3 Technical Report - https://arxiv.org/abs/2507.15493 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.15493.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chilam Cheang, Sijin Chen, Zhongren Cui, Yingdong Hu, Liqun Huang, Tao Kong, Hang Li, Yifeng Li, Yuxiao Liu, Xiao Ma, Hao Niu, Wenxuan Ou, Wanli Peng, Zeyu Ren, Haixin Shi, Jiawen Tian, Hongtao Wu, Xin Xiao, Yuyang Xiao, Jiafeng Xu, Yichu Yang</p><p><b>Upvotes:</b> 44</p><p><b>Summary:</b> We report our recent progress towards building generalist robot policies, the development of GR-3. GR-3 is a large-scale vision-language-action (VLA) model. It showcases exceptional capabilities in generalizing to novel objects, environments, and instructions involving abstract concepts. Furthermore, it can be efficiently fine-tuned with minimal human trajectory data, enabling rapid and cost-effective adaptation to new settings. GR-3 also excels in handling long-horizon and dexterous tasks, including those requiring bi-manual manipulation and mobile movement, showcasing robust and reliable performance. These capabilities are achieved through a multi-faceted training recipe that includes co-training with web-scale vision-language data, efficient fine-tuning from human trajectory data collected via VR devices, and effective imitation learning with robot trajectory data. In addition, we introduce ByteMini, a versatile bi-manual mobile robot designed with exceptional flexibility and reliability, capable of accomplishing a wide range of tasks when integrated with GR-3. Through extensive real-world experiments, we show GR-3 surpasses the state-of-the-art baseline method, pi_0, on a wide variety of challenging tasks. We hope GR-3 can serve as a step towards building generalist robots capable of assisting humans in daily life.</p> - https://arxiv.org/abs/2507.15493 - Mon, 21 Jul 2025 10:54:13 +0000 + DuPO: Enabling Reliable LLM Self-Verification via Dual Preference Optimization + https://arxiv.org/abs/2508.14460 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.14460.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shuaijie She, Yu Bao, Yu Lu, Lu Xu, Tao Li, Wenhao Zhu, Shujian Huang, Shanbo Cheng, Lu Lu, Yuxuan Wang</p><p><b>Upvotes:</b> 79</p><p><b>Summary:</b> We present DuPO, a dual learning-based preference optimization framework that generates annotation-free feedback via a generalized duality. DuPO addresses two key limitations: Reinforcement Learning with Verifiable Rewards (RLVR)'s reliance on costly labels and applicability restricted to verifiable tasks, and traditional dual learning's restriction to strictly dual task pairs (e.g., translation and back-translation). Specifically, DuPO decomposes a primal task's input into known and unknown components, then constructs its dual task to reconstruct the unknown part using the primal output and known information (e.g., reversing math solutions to recover hidden variables), broadening applicability to non-invertible tasks. The quality of this reconstruction serves as a self-supervised reward to optimize the primal task, synergizing with LLMs' ability to instantiate both tasks via a single model. Empirically, DuPO achieves substantial gains across diverse tasks: it enhances the average translation quality by 2.13 COMET over 756 directions, boosts the mathematical reasoning accuracy by an average of 6.4 points on three challenge benchmarks, and enhances performance by 9.3 points as an inference-time reranker (trading computation for accuracy). These results position DuPO as a scalable, general, and annotation-free paradigm for LLM optimization.</p> + https://arxiv.org/abs/2508.14460 + Wed, 20 Aug 2025 06:31:18 +0000 - GUI-G^2: Gaussian Reward Modeling for GUI Grounding - https://arxiv.org/abs/2507.15846 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.15846.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fei Tang, Zhangxuan Gu, Zhengxi Lu, Xuyang Liu, Shuheng Shen, Changhua Meng, Wen Wang, Wenqi Zhang, Yongliang Shen, Weiming Lu, Jun Xiao, Yueting Zhuang</p><p><b>Upvotes:</b> 126</p><p><b>Summary:</b> Graphical User Interface (GUI) grounding maps natural language instructions to precise interface locations for autonomous interaction. Current reinforcement learning approaches use binary rewards that treat elements as hit-or-miss targets, creating sparse signals that ignore the continuous nature of spatial interactions. Motivated by human clicking behavior that naturally forms Gaussian distributions centered on target elements, we introduce GUI Gaussian Grounding Rewards (GUI-G^2), a principled reward framework that models GUI elements as continuous Gaussian distributions across the interface plane. GUI-G^2 incorporates two synergistic mechanisms: Gaussian point rewards model precise localization through exponentially decaying distributions centered on element centroids, while coverage rewards assess spatial alignment by measuring the overlap between predicted Gaussian distributions and target regions. To handle diverse element scales, we develop an adaptive variance mechanism that calibrates reward distributions based on element dimensions. This framework transforms GUI grounding from sparse binary classification to dense continuous optimization, where Gaussian distributions generate rich gradient signals that guide models toward optimal interaction positions. Extensive experiments across ScreenSpot, ScreenSpot-v2, and ScreenSpot-Pro benchmarks demonstrate that GUI-G^2, substantially outperforms state-of-the-art method UI-TARS-72B, with the most significant improvement of 24.7% on ScreenSpot-Pro. Our analysis reveals that continuous modeling provides superior robustness to interface variations and enhanced generalization to unseen layouts, establishing a new paradigm for spatial reasoning in GUI interaction tasks.</p> - https://arxiv.org/abs/2507.15846 - Mon, 21 Jul 2025 17:53:42 +0000 + MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers + https://arxiv.org/abs/2508.14704 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.14704.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ziyang Luo, Zhiqi Shen, Wenzhuo Yang, Zirui Zhao, Prathyusha Jwalapuram, Amrita Saha, Doyen Sahoo, Silvio Savarese, Caiming Xiong, Junnan Li</p><p><b>Upvotes:</b> 41</p><p><b>Summary:</b> The Model Context Protocol has emerged as a transformative standard for connecting large language models to external data sources and tools, rapidly gaining adoption across major AI providers and development platforms. However, existing benchmarks are overly simplistic and fail to capture real application challenges such as long-horizon reasoning and large, unfamiliar tool spaces. To address this critical gap, we introduce MCP-Universe, the first comprehensive benchmark specifically designed to evaluate LLMs in realistic and hard tasks through interaction with real-world MCP servers. Our benchmark encompasses 6 core domains spanning 11 different MCP servers: Location Navigation, Repository Management, Financial Analysis, 3D Design, Browser Automation, and Web Searching. To ensure rigorous evaluation, we implement execution-based evaluators, including format evaluators for agent format compliance, static evaluators for time-invariant content matching, and dynamic evaluators that automatically retrieve real-time ground truth for temporally sensitive tasks. Through extensive evaluation of leading LLMs, we find that even SOTA models such as GPT-5 (43.72%), Grok-4 (33.33%) and Claude-4.0-Sonnet (29.44%) exhibit significant performance limitations. In addition, our benchmark poses a significant long-context challenge for LLM agents, as the number of input tokens increases rapidly with the number of interaction steps. Moreover, it introduces an unknown-tools challenge, as LLM agents often lack familiarity with the precise usage of the MCP servers. Notably, enterprise-level agents like Cursor cannot achieve better performance than standard ReAct frameworks. Beyond evaluation, we open-source our extensible evaluation framework with UI support, enabling researchers and practitioners to seamlessly integrate new agents and MCP servers while fostering innovation in the rapidly evolving MCP ecosystem.</p> + https://arxiv.org/abs/2508.14704 + Wed, 20 Aug 2025 13:28:58 +0000 - SeC: Advancing Complex Video Object Segmentation via Progressive Concept Construction - https://arxiv.org/abs/2507.15852 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.15852.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhixiong Zhang, Shuangrui Ding, Xiaoyi Dong, Songxin He, Jianfan Lin, Junsong Tang, Yuhang Zang, Yuhang Cao, Dahua Lin, Jiaqi Wang</p><p><b>Upvotes:</b> 37</p><p><b>Summary:</b> Video Object Segmentation (VOS) is a core task in computer vision, requiring models to track and segment target objects across video frames. Despite notable advances with recent efforts, current techniques still lag behind human capabilities in handling drastic visual variations, occlusions, and complex scene changes. This limitation arises from their reliance on appearance matching, neglecting the human-like conceptual understanding of objects that enables robust identification across temporal dynamics. Motivated by this gap, we propose Segment Concept (SeC), a concept-driven segmentation framework that shifts from conventional feature matching to the progressive construction and utilization of high-level, object-centric representations. SeC employs Large Vision-Language Models (LVLMs) to integrate visual cues across diverse frames, constructing robust conceptual priors. During inference, SeC forms a comprehensive semantic representation of the target based on processed frames, realizing robust segmentation of follow-up frames. Furthermore, SeC adaptively balances LVLM-based semantic reasoning with enhanced feature matching, dynamically adjusting computational efforts based on scene complexity. To rigorously assess VOS methods in scenarios demanding high-level conceptual reasoning and robust semantic understanding, we introduce the Semantic Complex Scenarios Video Object Segmentation benchmark (SeCVOS). SeCVOS comprises 160 manually annotated multi-scenario videos designed to challenge models with substantial appearance variations and dynamic scene transformations. In particular, SeC achieves an 11.8-point improvement over SAM 2.1 on SeCVOS, establishing a new state-of-the-art in concept-aware video object segmentation.</p> - https://arxiv.org/abs/2507.15852 - Mon, 21 Jul 2025 17:59:02 +0000 + Tinker: Diffusion's Gift to 3D--Multi-View Consistent Editing From Sparse Inputs without Per-Scene Optimization + https://arxiv.org/abs/2508.14811 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.14811.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Canyu Zhao, Xiaoman Li, Tianjian Feng, Zhiyue Zhao, Hao Chen, Chunhua Shen</p><p><b>Upvotes:</b> 39</p><p><b>Summary:</b> We introduce Tinker, a versatile framework for high-fidelity 3D editing that operates in both one-shot and few-shot regimes without any per-scene finetuning. Unlike prior techniques that demand extensive per-scene optimization to ensure multi-view consistency or to produce dozens of consistent edited input views, Tinker delivers robust, multi-view consistent edits from as few as one or two images. This capability stems from repurposing pretrained diffusion models, which unlocks their latent 3D awareness. To drive research in this space, we curate the first large-scale multi-view editing dataset and data pipeline, spanning diverse scenes and styles. Building on this dataset, we develop our framework capable of generating multi-view consistent edited views without per-scene training, which consists of two novel components: (1) Referring multi-view editor: Enables precise, reference-driven edits that remain coherent across all viewpoints. (2) Any-view-to-video synthesizer: Leverages spatial-temporal priors from video diffusion to perform high-quality scene completion and novel-view generation even from sparse inputs. Through extensive experiments, Tinker significantly reduces the barrier to generalizable 3D content creation, achieving state-of-the-art performance on editing, novel-view synthesis, and rendering enhancement tasks. We believe that Tinker represents a key step towards truly scalable, zero-shot 3D editing. Project webpage: https://aim-uofa.github.io/Tinker</p> + https://arxiv.org/abs/2508.14811 + Wed, 20 Aug 2025 16:02:59 +0000 - Deep Researcher with Test-Time Diffusion - https://arxiv.org/abs/2507.16075 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.16075.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Rujun Han, Yanfei Chen, Zoey CuiZhu, Lesly Miculicich, Guan Sun, Yuanjun Bi, Weiming Wen, Hui Wan, Chunfeng Wen, Solène Maître, George Lee, Vishy Tirumalashetty, Emily Xue, Zizhao Zhang, Salem Haykal, Burak Gokturk, Tomas Pfister, Chen-Yu Lee</p><p><b>Upvotes:</b> 51</p><p><b>Summary:</b> Deep research agents, powered by Large Language Models (LLMs), are rapidly advancing; yet, their performance often plateaus when generating complex, long-form research reports using generic test-time scaling algorithms. Drawing inspiration from the iterative nature of human research, which involves cycles of searching, reasoning, and revision, we propose the Test-Time Diffusion Deep Researcher (TTD-DR). This novel framework conceptualizes research report generation as a diffusion process. TTD-DR initiates this process with a preliminary draft, an updatable skeleton that serves as an evolving foundation to guide the research direction. The draft is then iteratively refined through a "denoising" process, which is dynamically informed by a retrieval mechanism that incorporates external information at each step. The core process is further enhanced by a self-evolutionary algorithm applied to each component of the agentic workflow, ensuring the generation of high-quality context for the diffusion process. This draft-centric design makes the report writing process more timely and coherent while reducing information loss during the iterative search process. We demonstrate that our TTD-DR achieves state-of-the-art results on a wide array of benchmarks that require intensive search and multi-hop reasoning, significantly outperforming existing deep research agents.</p> - https://arxiv.org/abs/2507.16075 - Mon, 21 Jul 2025 21:23:21 +0000 + MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Clouds + https://arxiv.org/abs/2508.14879 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.14879.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bingquan Dai, Li Ray Luo, Qihong Tang, Jie Wang, Xinyu Lian, Hao Xu, Minghan Qin, Xudong Xu, Bo Dai, Haoqian Wang, Zhaoyang Lyu, Jiangmiao Pang</p><p><b>Upvotes:</b> 62</p><p><b>Summary:</b> Reconstructing 3D objects into editable programs is pivotal for applications like reverse engineering and shape editing. However, existing methods often rely on limited domain-specific languages (DSLs) and small-scale datasets, restricting their ability to model complex geometries and structures. To address these challenges, we introduce MeshCoder, a novel framework that reconstructs complex 3D objects from point clouds into editable Blender Python scripts. We develop a comprehensive set of expressive Blender Python APIs capable of synthesizing intricate geometries. Leveraging these APIs, we construct a large-scale paired object-code dataset, where the code for each object is decomposed into distinct semantic parts. Subsequently, we train a multimodal large language model (LLM) that translates 3D point cloud into executable Blender Python scripts. Our approach not only achieves superior performance in shape-to-code reconstruction tasks but also facilitates intuitive geometric and topological editing through convenient code modifications. Furthermore, our code-based representation enhances the reasoning capabilities of LLMs in 3D shape understanding tasks. Together, these contributions establish MeshCoder as a powerful and flexible solution for programmatic 3D shape reconstruction and understanding.</p> + https://arxiv.org/abs/2508.14879 + Wed, 20 Aug 2025 17:50:15 +0000 - Pixels, Patterns, but No Poetry: To See The World like Humans - https://arxiv.org/abs/2507.16863 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.16863.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hongcheng Gao, Zihao Huang, Lin Xu, Jingyi Tang, Xinhao Li, Yue Liu, Haoyang Li, Taihang Hu, Minhua Lin, Xinlong Yang, Ge Wu, Balong Bi, Hongyu Chen, Wentao Zhang</p><p><b>Upvotes:</b> 62</p><p><b>Summary:</b> Achieving human-like perception and reasoning in Multimodal Large Language Models (MLLMs) remains a central challenge in artificial intelligence. While recent research has primarily focused on enhancing reasoning capabilities in MLLMs, a fundamental question persists: Can Multimodal Large Language Models truly perceive the world as humans do? This paper shifts focus from reasoning to perception. Rather than constructing benchmarks specifically for reasoning, we introduce the Turing Eye Test (TET), a challenging perception-oriented benchmark comprising four diagnostic tasks that evaluate MLLMs' performance on synthetic images that humans process intuitively. Our findings reveal that state-of-the-art MLLMs exhibit catastrophic failures on our perceptual tasks trivial for humans. Both in-context learning and training on language backbone-effective for previous benchmarks-fail to improve performance on our tasks, while fine-tuning the vision tower enables rapid adaptation, suggesting that our benchmark poses challenges for vision tower generalization rather than for the knowledge and reasoning capabilities of the language backbone-a key gap between current MLLMs and human perception. We release a representative subset of TET tasks in this version, and will introduce more diverse tasks and methods to enhance visual generalization in future work.</p> - https://arxiv.org/abs/2507.16863 - Mon, 21 Jul 2025 21:50:16 +0000 + Pixie: Fast and Generalizable Supervised Learning of 3D Physics from Pixels + https://arxiv.org/abs/2508.17437 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.17437.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Long Le, Ryan Lucas, Chen Wang, Chuhao Chen, Dinesh Jayaraman, Eric Eaton, Lingjie Liu</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> Inferring the physical properties of 3D scenes from visual information is a critical yet challenging task for creating interactive and realistic virtual worlds. While humans intuitively grasp material characteristics such as elasticity or stiffness, existing methods often rely on slow, per-scene optimization, limiting their generalizability and application. To address this problem, we introduce PIXIE, a novel method that trains a generalizable neural network to predict physical properties across multiple scenes from 3D visual features purely using supervised losses. Once trained, our feed-forward network can perform fast inference of plausible material fields, which coupled with a learned static scene representation like Gaussian Splatting enables realistic physics simulation under external forces. To facilitate this research, we also collected PIXIEVERSE, one of the largest known datasets of paired 3D assets and physic material annotations. Extensive evaluations demonstrate that PIXIE is about 1.46-4.39x better and orders of magnitude faster than test-time optimization methods. By leveraging pretrained visual features like CLIP, our method can also zero-shot generalize to real-world scenes despite only ever been trained on synthetic data. https://pixie-3d.github.io/</p> + https://arxiv.org/abs/2508.17437 + Wed, 20 Aug 2025 19:24:04 +0000 - Step-Audio 2 Technical Report - https://arxiv.org/abs/2507.16632 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.16632.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Boyong Wu, Chao Yan, Chen Hu, Cheng Yi, Chengli Feng, Fei Tian, Feiyu Shen, Gang Yu, Haoyang Zhang, Jingbei Li, Mingrui Chen, Peng Liu, Wang You, Xiangyu Tony Zhang, Xingyuan Li, Xuerui Yang, Yayue Deng, Yechang Huang, Yuxin Li, Yuxin Zhang, Zhao You, Brian Li, Changyi Wan, Hanpeng Hu, Jiangjie Zhen, Siyu Chen, Song Yuan, Xuelin Zhang, Yimin Jiang, Yu Zhou, Yuxiang Yang, Bingxin Li, Buyun Ma, Changhe Song, Dongqing Pang, Guoqiang Hu, Haiyang Sun, Kang An, Na Wang, Shuli Gao, Wei Ji, Wen Li, Wen Sun, Xuan Wen, Yong Ren, Yuankai Ma, Yufan Lu, Bin Wang, Bo Li, Changxin Miao, Che Liu, Chen Xu, Dapeng Shi, Dingyuan Hu, Donghang Wu, Enle Liu, Guanzhe Huang, Gulin Yan, Han Zhang, Hao Nie, Haonan Jia, Hongyu Zhou, Jianjian Sun, Jiaoren Wu, Jie Wu, Jie Yang, Jin Yang, Junzhe Lin, Kaixiang Li, Lei Yang, Liying Shi, Li Zhou, Longlong Gu, Ming Li, Mingliang Li, Mingxiao Li, Nan Wu, Qi Han, Qinyuan Tan, Shaoliang Pang, Shengjie Fan, Siqi Liu, Tiancheng Cao, Wanying Lu, Wenqing He, Wuxun Xie, Xu Zhao, Xueqi Li, Yanbo Yu, Yang Yang, Yi Liu, Yifan Lu, Yilei Wang, Yuanhao Ding, Yuanwei Liang, Yuanwei Lu, Yuchu Luo, Yuhe Yin, Yumeng Zhan, Yuxiang Zhang, Zidong Yang, Zixin Zhang, Binxing Jiao, Daxin Jiang, Heung-Yeung Shum, Jiansheng Chen, Jing Li, Xiangyu Zhang, Yibo Zhu</p><p><b>Upvotes:</b> 59</p><p><b>Summary:</b> This paper presents Step-Audio~2, an end-to-end multi-modal large language model designed for industry-strength audio understanding and speech conversation. By integrating a latent audio encoder and reasoning-centric reinforcement learning (RL), Step-Audio 2 achieves promising performance in automatic speech recognition (ASR) and audio understanding. To facilitate genuine end-to-end speech conversation, Step-Audio 2 incorporates the generation of discrete audio tokens into language modeling, significantly enhancing its responsiveness to paralinguistic information such as speaking styles and emotions. To effectively leverage the rich textual and acoustic knowledge in real-world data, Step-Audio 2 integrates retrieval-augmented generation (RAG) and is able to call external tools such as web search to mitigate hallucination and audio search to switch timbres. Trained on millions of hours of speech and audio data, Step-Audio 2 delivers intelligence and expressiveness across diverse conversational scenarios. Evaluation results demonstrate that Step-Audio 2 achieves state-of-the-art performance on various audio understanding and conversational benchmarks compared to other open-source and commercial solutions. Please visit https://github.com/stepfun-ai/Step-Audio2 for more information.</p> - https://arxiv.org/abs/2507.16632 - Tue, 22 Jul 2025 14:23:55 +0000 + Mobile-Agent-v3: Foundamental Agents for GUI Automation + https://arxiv.org/abs/2508.15144 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.15144.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiabo Ye, Xi Zhang, Haiyang Xu, Haowei Liu, Junyang Wang, Zhaoqing Zhu, Ziwei Zheng, Feiyu Gao, Junjie Cao, Zhengxi Lu, Jitong Liao, Qi Zheng, Fei Huang, Jingren Zhou, Ming Yan</p><p><b>Upvotes:</b> 55</p><p><b>Summary:</b> This paper introduces GUI-Owl, a foundational GUI agent model that achieves state-of-the-art performance among open-source end-to-end models on ten GUI benchmarks across desktop and mobile environments, covering grounding, question answering, planning, decision-making, and procedural knowledge. GUI-Owl-7B achieves 66.4 on AndroidWorld and 29.4 on OSWorld. Building on this, we propose Mobile-Agent-v3, a general-purpose GUI agent framework that further improves performance to 73.3 on AndroidWorld and 37.7 on OSWorld, setting a new state-of-the-art for open-source GUI agent frameworks. GUI-Owl incorporates three key innovations: (1) Large-scale Environment Infrastructure: a cloud-based virtual environment spanning Android, Ubuntu, macOS, and Windows, enabling our Self-Evolving GUI Trajectory Production framework. This generates high-quality interaction data via automated query generation and correctness validation, leveraging GUI-Owl to refine trajectories iteratively, forming a self-improving loop. It supports diverse data pipelines and reduces manual annotation. (2) Diverse Foundational Agent Capabilities: by integrating UI grounding, planning, action semantics, and reasoning patterns, GUI-Owl supports end-to-end decision-making and can act as a modular component in multi-agent systems. (3) Scalable Environment RL: we develop a scalable reinforcement learning framework with fully asynchronous training for real-world alignment. We also introduce Trajectory-aware Relative Policy Optimization (TRPO) for online RL, achieving 34.9 on OSWorld. GUI-Owl and Mobile-Agent-v3 are open-sourced at https://github.com/X-PLUG/MobileAgent.</p> + https://arxiv.org/abs/2508.15144 + Thu, 21 Aug 2025 00:39:12 +0000 - Zebra-CoT: A Dataset for Interleaved Vision Language Reasoning - https://arxiv.org/abs/2507.16746 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.16746.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ang Li, Charles Wang, Kaiyu Yue, Zikui Cai, Ollie Liu, Deqing Fu, Peng Guo, Wang Bill Zhu, Vatsal Sharan, Robin Jia, Willie Neiswanger, Furong Huang, Tom Goldstein, Micah Goldblum</p><p><b>Upvotes:</b> 32</p><p><b>Summary:</b> Humans often use visual aids, for example diagrams or sketches, when solving complex problems. Training multimodal models to do the same, known as Visual Chain of Thought (Visual CoT), is challenging due to: (1) poor off-the-shelf visual CoT performance, which hinders reinforcement learning, and (2) the lack of high-quality visual CoT training data. We introduce Zebra-CoT, a diverse large-scale dataset with 182,384 samples, containing logically coherent interleaved text-image reasoning traces. We focus on four categories of tasks where sketching or visual reasoning is especially natural, spanning scientific questions such as geometry, physics, and algorithms; 2D visual reasoning tasks like visual search and jigsaw puzzles; 3D reasoning tasks including 3D multi-hop inference, embodied and robot planning; visual logic problems and strategic games like chess. Fine-tuning the Anole-7B model on the Zebra-CoT training corpus results in an improvement of +12% in our test-set accuracy and yields up to +13% performance gain on standard VLM benchmark evaluations. Fine-tuning Bagel-7B yields a model that generates high-quality interleaved visual reasoning chains, underscoring Zebra-CoT's effectiveness for developing multimodal reasoning abilities. We open-source our dataset and models to support development and evaluation of visual CoT.</p> - https://arxiv.org/abs/2507.16746 - Tue, 22 Jul 2025 16:35:36 +0000 + Deep Think with Confidence + https://arxiv.org/abs/2508.15260 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.15260.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yichao Fu, Xuewei Wang, Yuandong Tian, Jiawei Zhao</p><p><b>Upvotes:</b> 78</p><p><b>Summary:</b> Large Language Models (LLMs) have shown great potential in reasoning tasks through test-time scaling methods like self-consistency with majority voting. However, this approach often leads to diminishing returns in accuracy and high computational overhead. To address these challenges, we introduce Deep Think with Confidence (DeepConf), a simple yet powerful method that enhances both reasoning efficiency and performance at test time. DeepConf leverages model-internal confidence signals to dynamically filter out low-quality reasoning traces during or after generation. It requires no additional model training or hyperparameter tuning and can be seamlessly integrated into existing serving frameworks. We evaluate DeepConf across a variety of reasoning tasks and the latest open-source models, including Qwen 3 and GPT-OSS series. Notably, on challenging benchmarks such as AIME 2025, DeepConf@512 achieves up to 99.9% accuracy and reduces generated tokens by up to 84.7% compared to full parallel thinking.</p> + https://arxiv.org/abs/2508.15260 + Thu, 21 Aug 2025 05:48:38 +0000 - Beyond Context Limits: Subconscious Threads for Long-Horizon Reasoning - https://arxiv.org/abs/2507.16784 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.16784.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hongyin Luo, Nathaniel Morgan, Tina Li, Derek Zhao, Ai Vy Ngo, Philip Schroeder, Lijie Yang, Assaf Ben-Kish, Jack O'Brien, James Glass</p><p><b>Upvotes:</b> 112</p><p><b>Summary:</b> To break the context limits of large language models (LLMs) that bottleneck reasoning accuracy and efficiency, we propose the Thread Inference Model (TIM), a family of LLMs trained for recursive and decompositional problem solving, and TIMRUN, an inference runtime enabling long-horizon structured reasoning beyond context limits. Together, TIM hosted on TIMRUN supports virtually unlimited working memory and multi-hop tool calls within a single language model inference, overcoming output limits, positional-embedding constraints, and GPU-memory bottlenecks. Performance is achieved by modeling natural language as reasoning trees measured by both length and depth instead of linear sequences. The reasoning trees consist of tasks with thoughts, recursive subtasks, and conclusions based on the concept we proposed in Schroeder et al, 2025. During generation, we maintain a working memory that retains only the key-value states of the most relevant context tokens, selected by a rule-based subtask-pruning mechanism, enabling reuse of positional embeddings and GPU memory pages throughout reasoning. Experimental results show that our system sustains high inference throughput, even when manipulating up to 90% of the KV cache in GPU memory. It also delivers accurate reasoning on mathematical tasks and handles information retrieval challenges that require long-horizon reasoning and multi-hop tool use.</p> - https://arxiv.org/abs/2507.16784 - Tue, 22 Jul 2025 17:30:04 +0000 + Beyond Transcription: Mechanistic Interpretability in ASR + https://arxiv.org/abs/2508.15882 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.15882.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Neta Glazer, Yael Segal-Feldman, Hilit Segev, Aviv Shamsian, Asaf Buchnick, Gill Hetz, Ethan Fetaya, Joseph Keshet, Aviv Navon</p><p><b>Upvotes:</b> 80</p><p><b>Summary:</b> Interpretability methods have recently gained significant attention, particularly in the context of large language models, enabling insights into linguistic representations, error detection, and model behaviors such as hallucinations and repetitions. However, these techniques remain underexplored in automatic speech recognition (ASR), despite their potential to advance both the performance and interpretability of ASR systems. In this work, we adapt and systematically apply established interpretability methods such as logit lens, linear probing, and activation patching, to examine how acoustic and semantic information evolves across layers in ASR systems. Our experiments reveal previously unknown internal dynamics, including specific encoder-decoder interactions responsible for repetition hallucinations and semantic biases encoded deep within acoustic representations. These insights demonstrate the benefits of extending and applying interpretability techniques to speech recognition, opening promising directions for future research on improving model transparency and robustness.</p> + https://arxiv.org/abs/2508.15882 + Thu, 21 Aug 2025 15:42:53 +0000 - MegaScience: Pushing the Frontiers of Post-Training Datasets for Science Reasoning - https://arxiv.org/abs/2507.16812 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.16812.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Run-Ze Fan, Zengzhi Wang, Pengfei Liu</p><p><b>Upvotes:</b> 50</p><p><b>Summary:</b> Scientific reasoning is critical for developing AI scientists and supporting human researchers in advancing the frontiers of natural science discovery. However, the open-source community has primarily focused on mathematics and coding while neglecting the scientific domain, largely due to the absence of open, large-scale, high-quality, verifiable scientific reasoning datasets. To bridge this gap, we first present TextbookReasoning, an open dataset featuring truthful reference answers extracted from 12k university-level scientific textbooks, comprising 650k reasoning questions spanning 7 scientific disciplines. We further introduce MegaScience, a large-scale mixture of high-quality open-source datasets totaling 1.25 million instances, developed through systematic ablation studies that evaluate various data selection methodologies to identify the optimal subset for each publicly available scientific dataset. Meanwhile, we build a comprehensive evaluation system covering diverse subjects and question types across 15 benchmarks, incorporating comprehensive answer extraction strategies to ensure accurate evaluation metrics. Our experiments demonstrate that our datasets achieve superior performance and training efficiency with more concise response lengths compared to existing open-source scientific datasets. Furthermore, we train Llama3.1, Qwen2.5, and Qwen3 series base models on MegaScience, which significantly outperform the corresponding official instruct models in average performance. In addition, MegaScience exhibits greater effectiveness for larger and stronger models, suggesting a scaling benefit for scientific tuning. We release our data curation pipeline, evaluation system, datasets, and seven trained models to the community to advance scientific reasoning research.</p> - https://arxiv.org/abs/2507.16812 - Tue, 22 Jul 2025 17:59:03 +0000 + LiveMCP-101: Stress Testing and Diagnosing MCP-enabled Agents on Challenging Queries + https://arxiv.org/abs/2508.15760 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.15760.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ming Yin, Dinghan Shen, Silei Xu, Jianbing Han, Sixun Dong, Mian Zhang, Yebowen Hu, Shujian Liu, Simin Ma, Song Wang, Sathish Reddy Indurthi, Xun Wang, Yiran Chen, Kaiqiang Song</p><p><b>Upvotes:</b> 43</p><p><b>Summary:</b> Tool calling has emerged as a critical capability for AI agents to interact with the real world and solve complex tasks. While the Model Context Protocol (MCP) provides a powerful standardized framework for tool integration, there is a significant gap in benchmarking how well AI agents can effectively solve multi-step tasks using diverse MCP tools in realistic, dynamic scenarios. In this work, we present LiveMCP-101, a benchmark of 101 carefully curated real-world queries, refined through iterative LLM rewriting and manual review, that require coordinated use of multiple MCP tools including web search, file operations, mathematical reasoning, and data analysis. Moreover, we introduce a novel evaluation approach that leverages ground-truth execution plans rather than raw API outputs, better reflecting the evolving nature of real-world environments. Experiments show that even frontier LLMs achieve a success rate below 60\%, highlighting major challenges in tool orchestration. Detailed ablations and error analysis further reveal distinct failure modes and inefficiencies in token usage, pointing to concrete directions for advancing current models. LiveMCP-101 sets a rigorous standard for evaluating real-world agent capabilities, advancing toward autonomous AI systems that reliably execute complex tasks through tool use.</p> + https://arxiv.org/abs/2508.15760 + Thu, 21 Aug 2025 17:55:54 +0000 - ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planning - https://arxiv.org/abs/2507.16815 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.16815.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chi-Pin Huang, Yueh-Hua Wu, Min-Hung Chen, Yu-Chiang Frank Wang, Fu-En Yang</p><p><b>Upvotes:</b> 35</p><p><b>Summary:</b> Vision-language-action (VLA) reasoning tasks require agents to interpret multimodal instructions, perform long-horizon planning, and act adaptively in dynamic environments. Existing approaches typically train VLA models in an end-to-end fashion, directly mapping inputs to actions without explicit reasoning, which hinders their ability to plan over multiple steps or adapt to complex task variations. In this paper, we propose ThinkAct, a dual-system framework that bridges high-level reasoning with low-level action execution via reinforced visual latent planning. ThinkAct trains a multimodal LLM to generate embodied reasoning plans guided by reinforcing action-aligned visual rewards based on goal completion and trajectory consistency. These reasoning plans are compressed into a visual plan latent that conditions a downstream action model for robust action execution on target environments. Extensive experiments on embodied reasoning and robot manipulation benchmarks demonstrate that ThinkAct enables few-shot adaptation, long-horizon planning, and self-correction behaviors in complex embodied AI tasks.</p> - https://arxiv.org/abs/2507.16815 - Tue, 22 Jul 2025 17:59:46 +0000 + Waver: Wave Your Way to Lifelike Video Generation + https://arxiv.org/abs/2508.15761 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.15761.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yifu Zhang, Hao Yang, Yuqi Zhang, Yifei Hu, Fengda Zhu, Chuang Lin, Xiaofeng Mei, Yi Jiang, Zehuan Yuan, Bingyue Peng</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> We present Waver, a high-performance foundation model for unified image and video generation. Waver can directly generate videos with durations ranging from 5 to 10 seconds at a native resolution of 720p, which are subsequently upscaled to 1080p. The model simultaneously supports text-to-video (T2V), image-to-video (I2V), and text-to-image (T2I) generation within a single, integrated framework. We introduce a Hybrid Stream DiT architecture to enhance modality alignment and accelerate training convergence. To ensure training data quality, we establish a comprehensive data curation pipeline and manually annotate and train an MLLM-based video quality model to filter for the highest-quality samples. Furthermore, we provide detailed training and inference recipes to facilitate the generation of high-quality videos. Building on these contributions, Waver excels at capturing complex motion, achieving superior motion amplitude and temporal consistency in video synthesis. Notably, it ranks among the Top 3 on both the T2V and I2V leaderboards at Artificial Analysis (data as of 2025-07-30 10:00 GMT+8), consistently outperforming existing open-source models and matching or surpassing state-of-the-art commercial solutions. We hope this technical report will help the community more efficiently train high-quality video generation models and accelerate progress in video generation technologies. Official page: https://github.com/FoundationVision/Waver.</p> + https://arxiv.org/abs/2508.15761 + Thu, 21 Aug 2025 17:56:10 +0000 - DesignLab: Designing Slides Through Iterative Detection and Correction - https://arxiv.org/abs/2507.17202 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.17202.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jooyeol Yun, Heng Wang, Yotaro Shimose, Jaegul Choo, Shingo Takamatsu</p><p><b>Upvotes:</b> 47</p><p><b>Summary:</b> Designing high-quality presentation slides can be challenging for non-experts due to the complexity involved in navigating various design choices. Numerous automated tools can suggest layouts and color schemes, yet often lack the ability to refine their own output, which is a key aspect in real-world workflows. We propose DesignLab, which separates the design process into two roles, the design reviewer, who identifies design-related issues, and the design contributor who corrects them. This decomposition enables an iterative loop where the reviewer continuously detects issues and the contributor corrects them, allowing a draft to be further polished with each iteration, reaching qualities that were unattainable. We fine-tune large language models for these roles and simulate intermediate drafts by introducing controlled perturbations, enabling the design reviewer learn design errors and the contributor learn how to fix them. Our experiments show that DesignLab outperforms existing design-generation methods, including a commercial tool, by embracing the iterative nature of designing which can result in polished, professional slides.</p> - https://arxiv.org/abs/2507.17202 - Wed, 23 Jul 2025 04:49:48 +0000 + Intern-S1: A Scientific Multimodal Foundation Model + https://arxiv.org/abs/2508.15763 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.15763.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lei Bai, Zhongrui Cai, Maosong Cao, Weihan Cao, Chiyu Chen, Haojiong Chen, Kai Chen, Pengcheng Chen, Ying Chen, Yongkang Chen, Yu Cheng, Yu Cheng, Pei Chu, Tao Chu, Erfei Cui, Ganqu Cui, Long Cui, Ziyun Cui, Nianchen Deng, Ning Ding, Nanqin Dong, Peijie Dong, Shihan Dou, Sinan Du, Haodong Duan, Caihua Fan, Ben Gao, Changjiang Gao, Jianfei Gao, Songyang Gao, Yang Gao, Zhangwei Gao, Jiaye Ge, Qiming Ge, Lixin Gu, Yuzhe Gu, Aijia Guo, Qipeng Guo, Xu Guo, Conghui He, Junjun He, Yili Hong, Siyuan Hou, Caiyu Hu, Hanglei Hu, Jucheng Hu, Ming Hu, Zhouqi Hua, Haian Huang, Junhao Huang, Xu Huang, Zixian Huang, Zhe Jiang, Lingkai Kong, Linyang Li, Peiji Li, Pengze Li, Shuaibin Li, Tianbin Li, Wei Li, Yuqiang Li, Dahua Lin, Junyao Lin, Tianyi Lin, Zhishan Lin, Hongwei Liu, Jiangning Liu, Jiyao Liu, Junnan Liu, Kai Liu, Kaiwen Liu, Kuikun Liu, Shichun Liu, Shudong Liu, Wei Liu, Xinyao Liu, Yuhong Liu, Zhan Liu, Yinquan Lu, Haijun Lv, Hongxia Lv, Huijie Lv, Qidang Lv, Ying Lv, Chengqi Lyu, Chenglong Ma, Jianpeng Ma, Ren Ma, Runmin Ma, Runyuan Ma, Xinzhu Ma, Yichuan Ma, Zihan Ma, Sixuan Mi, Junzhi Ning, Wenchang Ning, Xinle Pang, Jiahui Peng, Runyu Peng, Yu Qiao, Jiantao Qiu, Xiaoye Qu, Yuan Qu, Yuchen Ren, Fukai Shang, Wenqi Shao, Junhao Shen, Shuaike Shen, Chunfeng Song, Demin Song, Diping Song, Chenlin Su, Weijie Su, Weigao Sun, Yu Sun, Qian Tan, Cheng Tang, Huanze Tang, Kexian Tang, Shixiang Tang, Jian Tong, Aoran Wang, Bin Wang, Dong Wang, Lintao Wang, Rui Wang, Weiyun Wang, Wenhai Wang, Yi Wang, Ziyi Wang, Ling-I Wu, Wen Wu, Yue Wu, Zijian Wu, Linchen Xiao, Shuhao Xing, Chao Xu, Huihui Xu, Jun Xu, Ruiliang Xu, Wanghan Xu, GanLin Yang, Yuming Yang, Haochen Ye, Jin Ye, Shenglong Ye, Jia Yu, Jiashuo Yu, Jing Yu, Fei Yuan, Bo Zhang, Chao Zhang, Chen Zhang, Hongjie Zhang, Jin Zhang, Qiaosheng Zhang, Qiuyinzhe Zhang, Songyang Zhang, Taolin Zhang, Wenlong Zhang, Wenwei Zhang, Yechen Zhang, Ziyang Zhang, Haiteng Zhao, Qian Zhao, Xiangyu Zhao, Xiangyu Zhao, Bowen Zhou, Dongzhan Zhou, Peiheng Zhou, Yuhao Zhou, Yunhua Zhou, Dongsheng Zhu, Lin Zhu, Yicheng Zou</p><p><b>Upvotes:</b> 242</p><p><b>Summary:</b> In recent years, a plethora of open-source foundation models have emerged, achieving remarkable progress in some widely attended fields, with performance being quite close to that of closed-source models. However, in high-value but more challenging scientific professional fields, either the fields still rely on expert models, or the progress of general foundation models lags significantly compared to those in popular areas, far from sufficient for transforming scientific research and leaving substantial gap between open-source models and closed-source models in these scientific domains. To mitigate this gap and explore a step further toward Artificial General Intelligence (AGI), we introduce Intern-S1, a specialized generalist equipped with general understanding and reasoning capabilities with expertise to analyze multiple science modal data. Intern-S1 is a multimodal Mixture-of-Experts (MoE) model with 28 billion activated parameters and 241 billion total parameters, continually pre-trained on 5T tokens, including over 2.5T tokens from scientific domains. In the post-training stage, Intern-S1 undergoes offline and then online reinforcement learning (RL) in InternBootCamp, where we propose Mixture-of-Rewards (MoR) to synergize the RL training on more than 1000 tasks simultaneously. Through integrated innovations in algorithms, data, and training systems, Intern-S1 achieved top-tier performance in online RL training.On comprehensive evaluation benchmarks, Intern-S1 demonstrates competitive performance on general reasoning tasks among open-source models and significantly outperforms open-source models in scientific domains, surpassing closed-source state-of-the-art models in professional tasks, such as molecular synthesis planning, reaction condition prediction, predicting thermodynamic stabilities for crystals. Our models are available at https://huggingface.co/internlm/Intern-S1.</p> + https://arxiv.org/abs/2508.15763 + Thu, 21 Aug 2025 17:58:00 +0000 - Can One Domain Help Others? A Data-Centric Study on Multi-Domain Reasoning via Reinforcement Learning - https://arxiv.org/abs/2507.17512 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.17512.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yu Li, Zhuoshi Pan, Honglin Lin, Mengyuan Sun, Conghui He, Lijun Wu</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a powerful paradigm for enhancing the reasoning capabilities of LLMs. Existing research has predominantly concentrated on isolated reasoning domains such as mathematical problem-solving, coding tasks, or logical reasoning. However, real world reasoning scenarios inherently demand an integrated application of multiple cognitive skills. Despite this, the interplay among these reasoning skills under reinforcement learning remains poorly understood. To bridge this gap, we present a systematic investigation of multi-domain reasoning within the RLVR framework, explicitly focusing on three primary domains: mathematical reasoning, code generation, and logical puzzle solving. We conduct a comprehensive study comprising four key components: (1) Leveraging the GRPO algorithm and the Qwen-2.5-7B model family, our study thoroughly evaluates the models' in-domain improvements and cross-domain generalization capabilities when trained on single-domain datasets. (2) Additionally, we examine the intricate interactions including mutual enhancements and conflicts that emerge during combined cross-domain training. (3) To further understand the influence of SFT on RL, we also analyze and compare performance differences between base and instruct models under identical RL configurations. (4) Furthermore, we delve into critical RL training details, systematically exploring the impacts of curriculum learning strategies, variations in reward design, and language-specific factors. Through extensive experiments, our results offer significant insights into the dynamics governing domain interactions, revealing key factors influencing both specialized and generalizable reasoning performance. These findings provide valuable guidance for optimizing RL methodologies to foster comprehensive, multi-domain reasoning capabilities in LLMs.</p> - https://arxiv.org/abs/2507.17512 - Wed, 23 Jul 2025 13:51:04 +0000 + AgentFly: Fine-tuning LLM Agents without Fine-tuning LLMs + https://arxiv.org/abs/2508.16153 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.16153.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Huichi Zhou, Yihang Chen, Siyuan Guo, Xue Yan, Kin Hei Lee, Zihan Wang, Ka Yiu Lee, Guchun Zhang, Kun Shao, Linyi Yang, Jun Wang</p><p><b>Upvotes:</b> 115</p><p><b>Summary:</b> In this paper, we introduce a novel learning paradigm for adaptive Large Language Model (LLM) agents that eliminates the need for fine-tuning the underlying LLMs. Existing approaches are often either rigid, relying on static, handcrafted reflection workflows, or computationally intensive, requiring gradient updates of LLM model parameters. In contrast, our method enables low-cost continual adaptation via memory-based online reinforcement learning. We formalise this as a Memory-augmented Markov Decision Process (M-MDP), equipped with a neural case-selection policy to guide action decisions. Past experiences are stored in an episodic memory, either differentiable or non-parametric. The policy is continually updated based on environmental feedback through a memory rewriting mechanism, whereas policy improvement is achieved through efficient memory reading (retrieval). We instantiate our agent model in the deep research setting, namely AgentFly, which attains top-1 on GAIA validation (87.88% Pass@3) and 79.40% on the test set. It reaches 66.6% F1 and 80.4% PM on the DeepResearcher dataset, outperforming the state-of-the-art training-based method, while case-based memory adds 4.7% to 9.6% absolute points on out-of-distribution tasks. Our approach offers a scalable and efficient pathway for developing generalist LLM agents capable of continuous, real-time learning without gradient updates, advancing machine learning towards open-ended skill acquisition and deep research scenarios. The code is available at https://github.com/Agent-on-the-Fly/AgentFly.</p> + https://arxiv.org/abs/2508.16153 + Fri, 22 Aug 2025 07:25:30 +0000 - Yume: An Interactive World Generation Model - https://arxiv.org/abs/2507.17744 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.17744.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiaofeng Mao, Shaoheng Lin, Zhen Li, Chuanhao Li, Wenshuo Peng, Tong He, Jiangmiao Pang, Mingmin Chi, Yu Qiao, Kaipeng Zhang</p><p><b>Upvotes:</b> 77</p><p><b>Summary:</b> Yume aims to use images, text, or videos to create an interactive, realistic, and dynamic world, which allows exploration and control using peripheral devices or neural signals. In this report, we present a preview version of \method, which creates a dynamic world from an input image and allows exploration of the world using keyboard actions. To achieve this high-fidelity and interactive video world generation, we introduce a well-designed framework, which consists of four main components, including camera motion quantization, video generation architecture, advanced sampler, and model acceleration. First, we quantize camera motions for stable training and user-friendly interaction using keyboard inputs. Then, we introduce the Masked Video Diffusion Transformer~(MVDT) with a memory module for infinite video generation in an autoregressive manner. After that, training-free Anti-Artifact Mechanism (AAM) and Time Travel Sampling based on Stochastic Differential Equations (TTS-SDE) are introduced to the sampler for better visual quality and more precise control. Moreover, we investigate model acceleration by synergistic optimization of adversarial distillation and caching mechanisms. We use the high-quality world exploration dataset \sekai to train \method, and it achieves remarkable results in diverse scenes and applications. All data, codebase, and model weights are available on https://github.com/stdstu12/YUME. Yume will update monthly to achieve its original goal. Project page: https://stdstu12.github.io/YUME-Project/.</p> - https://arxiv.org/abs/2507.17744 - Wed, 23 Jul 2025 17:57:09 +0000 + MV-RAG: Retrieval Augmented Multiview Diffusion + https://arxiv.org/abs/2508.16577 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.16577.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yosef Dayani, Omer Benishu, Sagie Benaim</p><p><b>Upvotes:</b> 34</p><p><b>Summary:</b> Text-to-3D generation approaches have advanced significantly by leveraging pretrained 2D diffusion priors, producing high-quality and 3D-consistent outputs. However, they often fail to produce out-of-domain (OOD) or rare concepts, yielding inconsistent or inaccurate results. To this end, we propose MV-RAG, a novel text-to-3D pipeline that first retrieves relevant 2D images from a large in-the-wild 2D database and then conditions a multiview diffusion model on these images to synthesize consistent and accurate multiview outputs. Training such a retrieval-conditioned model is achieved via a novel hybrid strategy bridging structured multiview data and diverse 2D image collections. This involves training on multiview data using augmented conditioning views that simulate retrieval variance for view-specific reconstruction, alongside training on sets of retrieved real-world 2D images using a distinctive held-out view prediction objective: the model predicts the held-out view from the other views to infer 3D consistency from 2D data. To facilitate a rigorous OOD evaluation, we introduce a new collection of challenging OOD prompts. Experiments against state-of-the-art text-to-3D, image-to-3D, and personalization baselines show that our approach significantly improves 3D consistency, photorealism, and text adherence for OOD/rare concepts, while maintaining competitive performance on standard benchmarks.</p> + https://arxiv.org/abs/2508.16577 + Fri, 22 Aug 2025 17:59:40 +0000 - Group Sequence Policy Optimization - https://arxiv.org/abs/2507.18071 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.18071.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chujie Zheng, Shixuan Liu, Mingze Li, Xiong-Hui Chen, Bowen Yu, Chang Gao, Kai Dang, Yuqiong Liu, Rui Men, An Yang, Jingren Zhou, Junyang Lin</p><p><b>Upvotes:</b> 248</p><p><b>Summary:</b> This paper introduces Group Sequence Policy Optimization (GSPO), our stable, efficient, and performant reinforcement learning algorithm for training large language models. Unlike previous algorithms that adopt token-level importance ratios, GSPO defines the importance ratio based on sequence likelihood and performs sequence-level clipping, rewarding, and optimization. We demonstrate that GSPO achieves superior training efficiency and performance compared to the GRPO algorithm, notably stabilizes Mixture-of-Experts (MoE) RL training, and has the potential for simplifying the design of RL infrastructure. These merits of GSPO have contributed to the remarkable improvements in the latest Qwen3 models.</p> - https://arxiv.org/abs/2507.18071 - Thu, 24 Jul 2025 03:50:32 +0000 + TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling + https://arxiv.org/abs/2508.17445 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.17445.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yizhi Li, Qingshui Gu, Zhoufutu Wen, Ziniu Li, Tianshun Xing, Shuyue Guo, Tianyu Zheng, Xin Zhou, Xingwei Qu, Wangchunshu Zhou, Zheng Zhang, Wei Shen, Qian Liu, Chenghua Lin, Jian Yang, Ge Zhang, Wenhao Huang</p><p><b>Upvotes:</b> 74</p><p><b>Summary:</b> Recent advancements in aligning large language models via reinforcement learning have achieved remarkable gains in solving complex reasoning problems, but at the cost of expensive on-policy rollouts and limited exploration of diverse reasoning paths. In this work, we introduce TreePO, involving a self-guided rollout algorithm that views sequence generation as a tree-structured searching process. Composed of dynamic tree sampling policy and fixed-length segment decoding, TreePO leverages local uncertainty to warrant additional branches. By amortizing computation across common prefixes and pruning low-value paths early, TreePO essentially reduces the per-update compute burden while preserving or enhancing exploration diversity. Key contributions include: (1) a segment-wise sampling algorithm that alleviates the KV cache burden through contiguous segments and spawns new branches along with an early-stop mechanism; (2) a tree-based segment-level advantage estimation that considers both global and local proximal policy optimization. and (3) analysis on the effectiveness of probability and quality-driven dynamic divergence and fallback strategy. We empirically validate the performance gain of TreePO on a set reasoning benchmarks and the efficiency saving of GPU hours from 22\% up to 43\% of the sampling design for the trained models, meanwhile showing up to 40\% reduction at trajectory-level and 35\% at token-level sampling compute for the existing models. While offering a free lunch of inference efficiency, TreePO reveals a practical path toward scaling RL-based post-training with fewer samples and less compute. Home page locates at https://m-a-p.ai/TreePO.</p> + https://arxiv.org/abs/2508.17445 + Sun, 24 Aug 2025 16:52:37 +0000 - The Geometry of LLM Quantization: GPTQ as Babai's Nearest Plane Algorithm - https://arxiv.org/abs/2507.18553 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.18553.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiale Chen, Torsten Hoefler, Dan Alistarh</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> Quantizing the weights of large language models (LLMs) from 16-bit to lower bitwidth is the de facto approach to deploy massive transformers onto more affordable accelerators. GPTQ emerged as one of the standard methods for one-shot post-training quantization at LLM scale. Yet, its inner workings are described as a sequence of ad-hoc algebraic updates that obscure any geometric meaning or worst-case guarantees. In this work, we show that, when executed back-to-front (from the last to first dimension) for a linear layer, GPTQ is mathematically identical to Babai's nearest plane algorithm for the classical closest vector problem (CVP) on a lattice defined by the Hessian matrix of the layer's inputs. This equivalence is based on a sophisticated mathematical argument, and has two analytical consequences: (i) the GPTQ error propagation step gains an intuitive geometric interpretation; (ii) GPTQ inherits the error upper bound of Babai's algorithm under the no-clipping condition. Taken together, these results place GPTQ on firm theoretical footing and open the door to importing decades of progress in lattice algorithms towards the design of future quantization algorithms for billion-parameter models.</p> - https://arxiv.org/abs/2507.18553 - Thu, 24 Jul 2025 16:22:18 +0000 + Visual-CoG: Stage-Aware Reinforcement Learning with Chain of Guidance for Text-to-Image Generation + https://arxiv.org/abs/2508.18032 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.18032.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yaqi Li, Peng Chen, Mingyang Han, Bu Pi, Haoxiang Shi, Runzhou Zhao, Yang Yao, Xuan Zhang, Jun Song</p><p><b>Upvotes:</b> 40</p><p><b>Summary:</b> Despite the promising progress of recent autoregressive models in text-to-image (T2I) generation, their ability to handle multi-attribute and ambiguous prompts remains limited. To address these limitations, existing works have applied chain-of-thought (CoT) to enable stage-aware visual synthesis and employed reinforcement learning (RL) to improve reasoning capabilities. However, most models provide reward signals only at the end of the generation stage. This monolithic final-only guidance makes it difficult to identify which stages contribute positively to the final outcome and may lead to suboptimal policies. To tackle this issue, we propose a Visual-Chain of Guidance (Visual-CoG) paradigm consisting of three stages: semantic reasoning, process refining, and outcome evaluation, with stage-aware rewards providing immediate guidance throughout the image generation pipeline. We further construct a visual cognition benchmark, VisCog-Bench, which comprises four subtasks to evaluate the effectiveness of semantic reasoning. Comprehensive evaluations on GenEval, T2I-CompBench, and the proposed VisCog-Bench show improvements of 15%, 5%, and 19%, respectively, demonstrating the superior performance of the proposed Visual-CoG. We will release all the resources soon.</p> + https://arxiv.org/abs/2508.18032 + Mon, 25 Aug 2025 13:53:02 +0000 - Captain Cinema: Towards Short Movie Generation - https://arxiv.org/abs/2507.18634 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.18634.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junfei Xiao, Ceyuan Yang, Lvmin Zhang, Shengqu Cai, Yang Zhao, Yuwei Guo, Gordon Wetzstein, Maneesh Agrawala, Alan Yuille, Lu Jiang</p><p><b>Upvotes:</b> 37</p><p><b>Summary:</b> We present Captain Cinema, a generation framework for short movie generation. Given a detailed textual description of a movie storyline, our approach firstly generates a sequence of keyframes that outline the entire narrative, which ensures long-range coherence in both the storyline and visual appearance (e.g., scenes and characters). We refer to this step as top-down keyframe planning. These keyframes then serve as conditioning signals for a video synthesis model, which supports long context learning, to produce the spatio-temporal dynamics between them. This step is referred to as bottom-up video synthesis. To support stable and efficient generation of multi-scene long narrative cinematic works, we introduce an interleaved training strategy for Multimodal Diffusion Transformers (MM-DiT), specifically adapted for long-context video data. Our model is trained on a specially curated cinematic dataset consisting of interleaved data pairs. Our experiments demonstrate that Captain Cinema performs favorably in the automated creation of visually coherent and narrative consistent short movies in high quality and efficiency. Project page: https://thecinema.ai</p> - https://arxiv.org/abs/2507.18634 - Thu, 24 Jul 2025 17:59:56 +0000 + CMPhysBench: A Benchmark for Evaluating Large Language Models in Condensed Matter Physics + https://arxiv.org/abs/2508.18124 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.18124.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weida Wang, Dongchen Huang, Jiatong Li, Tengchao Yang, Ziyang Zheng, Di Zhang, Dong Han, Benteng Chen, Binzhao Luo, Zhiyu Liu, Kunling Liu, Zhiyuan Gao, Shiqi Geng, Wei Ma, Jiaming Su, Xin Li, Shuchen Pu, Yuhan Shui, Qianjia Cheng, Zhihao Dou, Dongfei Cui, Changyong He, Jin Zeng, Zeke Xie, Mao Su, Dongzhan Zhou, Yuqiang Li, Wanli Ouyang, Yunqi Cai, Xi Dai, Shufei Zhang, Lei Bai, Jinguang Cheng, Zhong Fang, Hongming Weng</p><p><b>Upvotes:</b> 46</p><p><b>Summary:</b> We introduce CMPhysBench, designed to assess the proficiency of Large Language Models (LLMs) in Condensed Matter Physics, as a novel Benchmark. CMPhysBench is composed of more than 520 graduate-level meticulously curated questions covering both representative subfields and foundational theoretical frameworks of condensed matter physics, such as magnetism, superconductivity, strongly correlated systems, etc. To ensure a deep understanding of the problem-solving process,we focus exclusively on calculation problems, requiring LLMs to independently generate comprehensive solutions. Meanwhile, leveraging tree-based representations of expressions, we introduce the Scalable Expression Edit Distance (SEED) score, which provides fine-grained (non-binary) partial credit and yields a more accurate assessment of similarity between prediction and ground-truth. Our results show that even the best models, Grok-4, reach only 36 average SEED score and 28% accuracy on CMPhysBench, underscoring a significant capability gap, especially for this practical and frontier domain relative to traditional physics. The code anddataset are publicly available at https://github.com/CMPhysBench/CMPhysBench.</p> + https://arxiv.org/abs/2508.18124 + Mon, 25 Aug 2025 15:32:22 +0000 - Agentic Reinforced Policy Optimization - https://arxiv.org/abs/2507.19849 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.19849.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Guanting Dong, Hangyu Mao, Kai Ma, Licheng Bao, Yifei Chen, Zhongyuan Wang, Zhongxia Chen, Jiazhen Du, Huiyang Wang, Fuzheng Zhang, Guorui Zhou, Yutao Zhu, Ji-Rong Wen, Zhicheng Dou</p><p><b>Upvotes:</b> 108</p><p><b>Summary:</b> Large-scale reinforcement learning with verifiable rewards (RLVR) has demonstrated its effectiveness in harnessing the potential of large language models (LLMs) for single-turn reasoning tasks. In realistic reasoning scenarios, LLMs can often utilize external tools to assist in task-solving processes. However, current RL algorithms inadequately balance the models' intrinsic long-horizon reasoning capabilities and their proficiency in multi-turn tool interactions. To bridge this gap, we propose Agentic Reinforced Policy Optimization (ARPO), a novel agentic RL algorithm tailored for training multi-turn LLM-based agents. Through preliminary experiments, we observe that LLMs tend to exhibit highly uncertain behavior, characterized by an increase in the entropy distribution of generated tokens, immediately following interactions with external tools. Motivated by this observation, ARPO incorporates an entropy-based adaptive rollout mechanism, dynamically balancing global trajectory sampling and step-level sampling, thereby promoting exploration at steps with high uncertainty after tool usage. By integrating an advantage attribution estimation, ARPO enables LLMs to internalize advantage differences in stepwise tool-use interactions. Our experiments across 13 challenging benchmarks in computational reasoning, knowledge reasoning, and deep search domains demonstrate ARPO's superiority over trajectory-level RL algorithms. Remarkably, ARPO achieves improved performance using only half of the tool-use budget required by existing methods, offering a scalable solution for aligning LLM-based agents with real-time dynamic environments. Our code and datasets are released at https://github.com/dongguanting/ARPO</p> - https://arxiv.org/abs/2507.19849 - Sat, 26 Jul 2025 07:53:11 +0000 + InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency + https://arxiv.org/abs/2508.18265 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.18265.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weiyun Wang, Zhangwei Gao, Lixin Gu, Hengjun Pu, Long Cui, Xingguang Wei, Zhaoyang Liu, Linglin Jing, Shenglong Ye, Jie Shao, Zhaokai Wang, Zhe Chen, Hongjie Zhang, Ganlin Yang, Haomin Wang, Qi Wei, Jinhui Yin, Wenhao Li, Erfei Cui, Guanzhou Chen, Zichen Ding, Changyao Tian, Zhenyu Wu, Jingjing Xie, Zehao Li, Bowen Yang, Yuchen Duan, Xuehui Wang, Songze Li, Xiangyu Zhao, Haodong Duan, Nianchen Deng, Bin Fu, Yinan He, Yi Wang, Conghui He, Botian Shi, Junjun He, Yingtong Xiong, Han Lv, Lijun Wu, Wenqi Shao, Kaipeng Zhang, Huipeng Deng, Biqing Qi, Jiaye Ge, Qipeng Guo, Wenwei Zhang, Wanli Ouyang, Limin Wang, Min Dou, Xizhou Zhu, Tong Lu, Dahua Lin, Jifeng Dai, Bowen Zhou, Weijie Su, Kai Chen, Yu Qiao, Wenhai Wang, Gen Luo</p><p><b>Upvotes:</b> 165</p><p><b>Summary:</b> We introduce InternVL 3.5, a new family of open-source multimodal models that significantly advances versatility, reasoning capability, and inference efficiency along the InternVL series. A key innovation is the Cascade Reinforcement Learning (Cascade RL) framework, which enhances reasoning through a two-stage process: offline RL for stable convergence and online RL for refined alignment. This coarse-to-fine training strategy leads to substantial improvements on downstream reasoning tasks, e.g., MMMU and MathVista. To optimize efficiency, we propose a Visual Resolution Router (ViR) that dynamically adjusts the resolution of visual tokens without compromising performance. Coupled with ViR, our Decoupled Vision-Language Deployment (DvD) strategy separates the vision encoder and language model across different GPUs, effectively balancing computational load. These contributions collectively enable InternVL3.5 to achieve up to a +16.0\% gain in overall reasoning performance and a 4.05times inference speedup compared to its predecessor, i.e., InternVL3. In addition, InternVL3.5 supports novel capabilities such as GUI interaction and embodied agency. Notably, our largest model, i.e., InternVL3.5-241B-A28B, attains state-of-the-art results among open-source MLLMs across general multimodal, reasoning, text, and agentic tasks -- narrowing the performance gap with leading commercial models like GPT-5. All models and code are publicly released.</p> + https://arxiv.org/abs/2508.18265 + Mon, 25 Aug 2025 17:58:17 +0000 - ARC-Hunyuan-Video-7B: Structured Video Comprehension of Real-World Shorts - https://arxiv.org/abs/2507.20939 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.20939.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuying Ge, Yixiao Ge, Chen Li, Teng Wang, Junfu Pu, Yizhuo Li, Lu Qiu, Jin Ma, Lisheng Duan, Xinyu Zuo, Jinwen Luo, Weibo Gu, Zexuan Li, Xiaojing Zhang, Yangyu Tao, Han Hu, Di Wang, Ying Shan</p><p><b>Upvotes:</b> 55</p><p><b>Summary:</b> Real-world user-generated short videos, especially those distributed on platforms such as WeChat Channel and TikTok, dominate the mobile internet. However, current large multimodal models lack essential temporally-structured, detailed, and in-depth video comprehension capabilities, which are the cornerstone of effective video search and recommendation, as well as emerging video applications. Understanding real-world shorts is actually challenging due to their complex visual elements, high information density in both visuals and audio, and fast pacing that focuses on emotional expression and viewpoint delivery. This requires advanced reasoning to effectively integrate multimodal information, including visual, audio, and text. In this work, we introduce ARC-Hunyuan-Video, a multimodal model that processes visual, audio, and textual signals from raw video inputs end-to-end for structured comprehension. The model is capable of multi-granularity timestamped video captioning and summarization, open-ended video question answering, temporal video grounding, and video reasoning. Leveraging high-quality data from an automated annotation pipeline, our compact 7B-parameter model is trained through a comprehensive regimen: pre-training, instruction fine-tuning, cold start, reinforcement learning (RL) post-training, and final instruction fine-tuning. Quantitative evaluations on our introduced benchmark ShortVid-Bench and qualitative comparisons demonstrate its strong performance in real-world video comprehension, and it supports zero-shot or fine-tuning with a few samples for diverse downstream applications. The real-world production deployment of our model has yielded tangible and measurable improvements in user engagement and satisfaction, a success supported by its remarkable efficiency, with stress tests indicating an inference time of just 10 seconds for a one-minute video on H20 GPU.</p> - https://arxiv.org/abs/2507.20939 - Mon, 28 Jul 2025 15:52:36 +0000 + UltraMemV2: Memory Networks Scaling to 120B Parameters with Superior Long-Context Learning + https://arxiv.org/abs/2508.18756 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.18756.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zihao Huang, Yu Bao, Qiyang Min, Siyan Chen, Ran Guo, Hongzhi Huang, Defa Zhu, Yutao Zeng, Banggu Wu, Xun Zhou, Siyuan Qiao</p><p><b>Upvotes:</b> 32</p><p><b>Summary:</b> While Mixture of Experts (MoE) models achieve remarkable efficiency by activating only subsets of parameters, they suffer from high memory access costs during inference. Memory-layer architectures offer an appealing alternative with very few memory access, but previous attempts like UltraMem have only matched the performance of 2-expert MoE models, falling significantly short of state-of-the-art 8-expert configurations. We present UltraMemV2, a redesigned memory-layer architecture that closes this performance gap. Our approach introduces five key improvements: integrating memory layers into every transformer block, simplifying value expansion with single linear projections, adopting FFN-based value processing from PEER, implementing principled parameter initialization, and rebalancing memory-to-FFN computation ratios. Through extensive evaluation, we demonstrate that UltraMemV2 achieves performance parity with 8-expert MoE models under same computation and parameters but significantly low memory access. Notably, UltraMemV2 shows superior performance on memory-intensive tasks, with improvements of +1.6 points on long-context memorization, +6.2 points on multi-round memorization, and +7.9 points on in-context learning. We validate our approach at scale with models up to 2.5B activated parameters from 120B total parameters, and establish that activation density has greater impact on performance than total sparse parameter count. Our work brings memory-layer architectures to performance parity with state-of-the-art MoE models, presenting a compelling alternative for efficient sparse computation.</p> + https://arxiv.org/abs/2508.18756 + Tue, 26 Aug 2025 07:33:11 +0000 - SmallThinker: A Family of Efficient Large Language Models Natively Trained for Local Deployment - https://arxiv.org/abs/2507.20984 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.20984.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yixin Song, Zhenliang Xue, Dongliang Wei, Feiyang Chen, Jianxiang Gao, Junchen Liu, Hangyu Liang, Guangshuo Qin, Chengrong Tian, Bo Wen, Longyu Zhao, Xinrui Zheng, Zeyu Mi, Haibo Chen</p><p><b>Upvotes:</b> 41</p><p><b>Summary:</b> While frontier large language models (LLMs) continue to push capability boundaries, their deployment remains confined to GPU-powered cloud infrastructure. We challenge this paradigm with SmallThinker, a family of LLMs natively designed - not adapted - for the unique constraints of local devices: weak computational power, limited memory, and slow storage. Unlike traditional approaches that mainly compress existing models built for clouds, we architect SmallThinker from the ground up to thrive within these limitations. Our innovation lies in a deployment-aware architecture that transforms constraints into design principles. First, We introduce a two-level sparse structure combining fine-grained Mixture-of-Experts (MoE) with sparse feed-forward networks, drastically reducing computational demands without sacrificing model capacity. Second, to conquer the I/O bottleneck of slow storage, we design a pre-attention router that enables our co-designed inference engine to prefetch expert parameters from storage while computing attention, effectively hiding storage latency that would otherwise cripple on-device inference. Third, for memory efficiency, we utilize NoPE-RoPE hybrid sparse attention mechanism to slash KV cache requirements. We release SmallThinker-4B-A0.6B and SmallThinker-21B-A3B, which achieve state-of-the-art performance scores and even outperform larger LLMs. Remarkably, our co-designed system mostly eliminates the need for expensive GPU hardware: with Q4_0 quantization, both models exceed 20 tokens/s on ordinary consumer CPUs, while consuming only 1GB and 8GB of memory respectively. SmallThinker is publicly available at hf.co/PowerInfer/SmallThinker-4BA0.6B-Instruct and hf.co/PowerInfer/SmallThinker-21BA3B-Instruct.</p> - https://arxiv.org/abs/2507.20984 - Mon, 28 Jul 2025 16:45:14 +0000 + USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning + https://arxiv.org/abs/2508.18966 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.18966.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shaojin Wu, Mengqi Huang, Yufeng Cheng, Wenxu Wu, Jiahe Tian, Yiming Luo, Fei Ding, Qian He</p><p><b>Upvotes:</b> 45</p><p><b>Summary:</b> Existing literature typically treats style-driven and subject-driven generation as two disjoint tasks: the former prioritizes stylistic similarity, whereas the latter insists on subject consistency, resulting in an apparent antagonism. We argue that both objectives can be unified under a single framework because they ultimately concern the disentanglement and re-composition of content and style, a long-standing theme in style-driven research. To this end, we present USO, a Unified Style-Subject Optimized customization model. First, we construct a large-scale triplet dataset consisting of content images, style images, and their corresponding stylized content images. Second, we introduce a disentangled learning scheme that simultaneously aligns style features and disentangles content from style through two complementary objectives, style-alignment training and content-style disentanglement training. Third, we incorporate a style reward-learning paradigm denoted as SRL to further enhance the model's performance. Finally, we release USO-Bench, the first benchmark that jointly evaluates style similarity and subject fidelity across multiple metrics. Extensive experiments demonstrate that USO achieves state-of-the-art performance among open-source models along both dimensions of subject consistency and style similarity. Code and model: https://github.com/bytedance/USO</p> + https://arxiv.org/abs/2508.18966 + Tue, 26 Aug 2025 12:10:24 +0000 - Reconstructing 4D Spatial Intelligence: A Survey - https://arxiv.org/abs/2507.21045 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.21045.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yukang Cao, Jiahao Lu, Zhisheng Huang, Zhuowei Shen, Chengfeng Zhao, Fangzhou Hong, Zhaoxi Chen, Xin Li, Wenping Wang, Yuan Liu, Ziwei Liu</p><p><b>Upvotes:</b> 31</p><p><b>Summary:</b> Reconstructing 4D spatial intelligence from visual observations has long been a central yet challenging task in computer vision, with broad real-world applications. These range from entertainment domains like movies, where the focus is often on reconstructing fundamental visual elements, to embodied AI, which emphasizes interaction modeling and physical realism. Fueled by rapid advances in 3D representations and deep learning architectures, the field has evolved quickly, outpacing the scope of previous surveys. Additionally, existing surveys rarely offer a comprehensive analysis of the hierarchical structure of 4D scene reconstruction. To address this gap, we present a new perspective that organizes existing methods into five progressive levels of 4D spatial intelligence: (1) Level 1 -- reconstruction of low-level 3D attributes (e.g., depth, pose, and point maps); (2) Level 2 -- reconstruction of 3D scene components (e.g., objects, humans, structures); (3) Level 3 -- reconstruction of 4D dynamic scenes; (4) Level 4 -- modeling of interactions among scene components; and (5) Level 5 -- incorporation of physical laws and constraints. We conclude the survey by discussing the key challenges at each level and highlighting promising directions for advancing toward even richer levels of 4D spatial intelligence. To track ongoing developments, we maintain an up-to-date project page: https://github.com/yukangcao/Awesome-4D-Spatial-Intelligence.</p> - https://arxiv.org/abs/2507.21045 - Mon, 28 Jul 2025 17:59:02 +0000 + VibeVoice Technical Report + https://arxiv.org/abs/2508.19205 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.19205.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhiliang Peng, Jianwei Yu, Wenhui Wang, Yaoyao Chang, Yutao Sun, Li Dong, Yi Zhu, Weijiang Xu, Hangbo Bao, Zehua Wang, Shaohan Huang, Yan Xia, Furu Wei</p><p><b>Upvotes:</b> 102</p><p><b>Summary:</b> This report presents VibeVoice, a novel model designed to synthesize long-form speech with multiple speakers by employing next-token diffusion, which is a unified method for modeling continuous data by autoregressively generating latent vectors via diffusion. To enable this, we introduce a novel continuous speech tokenizer that, when compared to the popular Encodec model, improves data compression by 80 times while maintaining comparable performance. The tokenizer effectively preserves audio fidelity while significantly boosting computational efficiency for processing long sequences. Thus, VibeVoice can synthesize long-form speech for up to 90 minutes (in a 64K context window length) with a maximum of 4 speakers, capturing the authentic conversational ``vibe'' and surpassing open-source and proprietary dialogue models.</p> + https://arxiv.org/abs/2508.19205 + Tue, 26 Aug 2025 17:09:12 +0000 - A Survey of Self-Evolving Agents: On Path to Artificial Super Intelligence - https://arxiv.org/abs/2507.21046 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.21046.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Huan-ang Gao, Jiayi Geng, Wenyue Hua, Mengkang Hu, Xinzhe Juan, Hongzhang Liu, Shilong Liu, Jiahao Qiu, Xuan Qi, Yiran Wu, Hongru Wang, Han Xiao, Yuhang Zhou, Shaokun Zhang, Jiayi Zhang, Jinyu Xiang, Yixiong Fang, Qiwen Zhao, Dongrui Liu, Qihan Ren, Cheng Qian, Zhenghailong Wang, Minda Hu, Huazheng Wang, Qingyun Wu, Heng Ji, Mengdi Wang</p><p><b>Upvotes:</b> 65</p><p><b>Summary:</b> Large Language Models (LLMs) have demonstrated strong capabilities but remain fundamentally static, unable to adapt their internal parameters to novel tasks, evolving knowledge domains, or dynamic interaction contexts. As LLMs are increasingly deployed in open-ended, interactive environments, this static nature has become a critical bottleneck, necessitating agents that can adaptively reason, act, and evolve in real time. This paradigm shift -- from scaling static models to developing self-evolving agents -- has sparked growing interest in architectures and methods enabling continual learning and adaptation from data, interactions, and experiences. This survey provides the first systematic and comprehensive review of self-evolving agents, organized around three foundational dimensions -- what to evolve, when to evolve, and how to evolve. We examine evolutionary mechanisms across agent components (e.g., models, memory, tools, architecture), categorize adaptation methods by stages (e.g., intra-test-time, inter-test-time), and analyze the algorithmic and architectural designs that guide evolutionary adaptation (e.g., scalar rewards, textual feedback, single-agent and multi-agent systems). Additionally, we analyze evaluation metrics and benchmarks tailored for self-evolving agents, highlight applications in domains such as coding, education, and healthcare, and identify critical challenges and research directions in safety, scalability, and co-evolutionary dynamics. By providing a structured framework for understanding and designing self-evolving agents, this survey establishes a roadmap for advancing adaptive agentic systems in both research and real-world deployments, ultimately shedding lights to pave the way for the realization of Artificial Super Intelligence (ASI), where agents evolve autonomously, performing at or beyond human-level intelligence across a wide array of tasks.</p> - https://arxiv.org/abs/2507.21046 - Mon, 28 Jul 2025 17:59:05 +0000 + OmniHuman-1.5: Instilling an Active Mind in Avatars via Cognitive Simulation + https://arxiv.org/abs/2508.19209 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.19209.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jianwen Jiang, Weihong Zeng, Zerong Zheng, Jiaqi Yang, Chao Liang, Wang Liao, Han Liang, Yuan Zhang, Mingyuan Gao</p><p><b>Upvotes:</b> 36</p><p><b>Summary:</b> Existing video avatar models can produce fluid human animations, yet they struggle to move beyond mere physical likeness to capture a character's authentic essence. Their motions typically synchronize with low-level cues like audio rhythm, lacking a deeper semantic understanding of emotion, intent, or context. To bridge this gap, we propose a framework designed to generate character animations that are not only physically plausible but also semantically coherent and expressive. Our model, OmniHuman-1.5, is built upon two key technical contributions. First, we leverage Multimodal Large Language Models to synthesize a structured textual representation of conditions that provides high-level semantic guidance. This guidance steers our motion generator beyond simplistic rhythmic synchronization, enabling the production of actions that are contextually and emotionally resonant. Second, to ensure the effective fusion of these multimodal inputs and mitigate inter-modality conflicts, we introduce a specialized Multimodal DiT architecture with a novel Pseudo Last Frame design. The synergy of these components allows our model to accurately interpret the joint semantics of audio, images, and text, thereby generating motions that are deeply coherent with the character, scene, and linguistic content. Extensive experiments demonstrate that our model achieves leading performance across a comprehensive set of metrics, including lip-sync accuracy, video quality, motion naturalness and semantic consistency with textual prompts. Furthermore, our approach shows remarkable extensibility to complex scenarios, such as those involving multi-person and non-human subjects. Homepage: https://omnihuman-lab.github.io/v1_5/</p> + https://arxiv.org/abs/2508.19209 + Tue, 26 Aug 2025 17:15:26 +0000 - Rep-MTL: Unleashing the Power of Representation-level Task Saliency for Multi-Task Learning - https://arxiv.org/abs/2507.21049 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.21049.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zedong Wang, Siyuan Li, Dan Xu</p><p><b>Upvotes:</b> 38</p><p><b>Summary:</b> Despite the promise of Multi-Task Learning in leveraging complementary knowledge across tasks, existing multi-task optimization (MTO) techniques remain fixated on resolving conflicts via optimizer-centric loss scaling and gradient manipulation strategies, yet fail to deliver consistent gains. In this paper, we argue that the shared representation space, where task interactions naturally occur, offers rich information and potential for operations complementary to existing optimizers, especially for facilitating the inter-task complementarity, which is rarely explored in MTO. This intuition leads to Rep-MTL, which exploits the representation-level task saliency to quantify interactions between task-specific optimization and shared representation learning. By steering these saliencies through entropy-based penalization and sample-wise cross-task alignment, Rep-MTL aims to mitigate negative transfer by maintaining the effective training of individual tasks instead pure conflict-solving, while explicitly promoting complementary information sharing. Experiments are conducted on four challenging MTL benchmarks covering both task-shift and domain-shift scenarios. The results show that Rep-MTL, even paired with the basic equal weighting policy, achieves competitive performance gains with favorable efficiency. Beyond standard performance metrics, Power Law exponent analysis demonstrates Rep-MTL's efficacy in balancing task-specific learning and cross-task sharing. The project page is available at HERE.</p> - https://arxiv.org/abs/2507.21049 - Mon, 28 Jul 2025 17:59:28 +0000 + VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Space + https://arxiv.org/abs/2508.19247 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.19247.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lin Li, Zehuan Huang, Haoran Feng, Gengxiong Zhuang, Rui Chen, Chunchao Guo, Lu Sheng</p><p><b>Upvotes:</b> 36</p><p><b>Summary:</b> 3D local editing of specified regions is crucial for game industry and robot interaction. Recent methods typically edit rendered multi-view images and then reconstruct 3D models, but they face challenges in precisely preserving unedited regions and overall coherence. Inspired by structured 3D generative models, we propose VoxHammer, a novel training-free approach that performs precise and coherent editing in 3D latent space. Given a 3D model, VoxHammer first predicts its inversion trajectory and obtains its inverted latents and key-value tokens at each timestep. Subsequently, in the denoising and editing phase, we replace the denoising features of preserved regions with the corresponding inverted latents and cached key-value tokens. By retaining these contextual features, this approach ensures consistent reconstruction of preserved areas and coherent integration of edited parts. To evaluate the consistency of preserved regions, we constructed Edit3D-Bench, a human-annotated dataset comprising hundreds of samples, each with carefully labeled 3D editing regions. Experiments demonstrate that VoxHammer significantly outperforms existing methods in terms of both 3D consistency of preserved regions and overall quality. Our method holds promise for synthesizing high-quality edited paired data, thereby laying the data foundation for in-context 3D generation. See our project page at https://huanngzh.github.io/VoxHammer-Page/.</p> + https://arxiv.org/abs/2508.19247 + Tue, 26 Aug 2025 17:59:47 +0000 - BANG: Dividing 3D Assets via Generative Exploded Dynamics - https://arxiv.org/abs/2507.21493 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.21493.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Longwen Zhang, Qixuan Zhang, Haoran Jiang, Yinuo Bai, Wei Yang, Lan Xu, Jingyi Yu</p><p><b>Upvotes:</b> 44</p><p><b>Summary:</b> 3D creation has always been a unique human strength, driven by our ability to deconstruct and reassemble objects using our eyes, mind and hand. However, current 3D design tools struggle to replicate this natural process, requiring considerable artistic expertise and manual labor. This paper introduces BANG, a novel generative approach that bridges 3D generation and reasoning, allowing for intuitive and flexible part-level decomposition of 3D objects. At the heart of BANG is "Generative Exploded Dynamics", which creates a smooth sequence of exploded states for an input geometry, progressively separating parts while preserving their geometric and semantic coherence. BANG utilizes a pre-trained large-scale latent diffusion model, fine-tuned for exploded dynamics with a lightweight exploded view adapter, allowing precise control over the decomposition process. It also incorporates a temporal attention module to ensure smooth transitions and consistency across time. BANG enhances control with spatial prompts, such as bounding boxes and surface regions, enabling users to specify which parts to decompose and how. This interaction can be extended with multimodal models like GPT-4, enabling 2D-to-3D manipulations for more intuitive and creative workflows. The capabilities of BANG extend to generating detailed part-level geometry, associating parts with functional descriptions, and facilitating component-aware 3D creation and manufacturing workflows. Additionally, BANG offers applications in 3D printing, where separable parts are generated for easy printing and reassembly. In essence, BANG enables seamless transformation from imaginative concepts to detailed 3D assets, offering a new perspective on creation that resonates with human intuition.</p> - https://arxiv.org/abs/2507.21493 - Tue, 29 Jul 2025 04:21:21 +0000 + Self-Rewarding Vision-Language Model via Reasoning Decomposition + https://arxiv.org/abs/2508.19652 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.19652.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zongxia Li, Wenhao Yu, Chengsong Huang, Rui Liu, Zhenwen Liang, Fuxiao Liu, Jingxi Che, Dian Yu, Jordan Boyd-Graber, Haitao Mi, Dong Yu</p><p><b>Upvotes:</b> 77</p><p><b>Summary:</b> Vision-Language Models (VLMs) often suffer from visual hallucinations, saying things that are not actually in the image, and language shortcuts, where they skip the visual part and just rely on text priors. These issues arise because most post-training methods for VLMs rely on simple verifiable answer matching and supervise only final outputs, leaving intermediate visual reasoning without explicit guidance. As a result, VLMs receive sparse visual signals and often learn to prioritize language-based reasoning over visual perception. To mitigate this, some existing methods add visual supervision using human annotations or distilled labels from external large models. However, human annotations are labor-intensive and costly, and because external signals cannot adapt to the evolving policy, they cause distributional shifts that can lead to reward hacking. In this paper, we introduce Vision-SR1, a self-rewarding method that improves visual reasoning without relying on external visual supervisions via reinforcement learning. Vision-SR1 decomposes VLM reasoning into two stages: visual perception and language reasoning. The model is first prompted to produce self-contained visual perceptions that are sufficient to answer the question without referring back the input image. To validate this self-containment, the same VLM model is then re-prompted to perform language reasoning using only the generated perception as input to compute reward. This self-reward is combined with supervision on final outputs, providing a balanced training signal that strengthens both visual perception and language reasoning. Our experiments demonstrate that Vision-SR1 improves visual reasoning, mitigates visual hallucinations, and reduces reliance on language shortcuts across diverse vision-language tasks.</p> + https://arxiv.org/abs/2508.19652 + Wed, 27 Aug 2025 08:01:03 +0000 - HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels - https://arxiv.org/abs/2507.21809 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.21809.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> HunyuanWorld Team, Zhenwei Wang, Yuhao Liu, Junta Wu, Zixiao Gu, Haoyuan Wang, Xuhui Zuo, Tianyu Huang, Wenhuan Li, Sheng Zhang, Yihang Lian, Yulin Tsai, Lifu Wang, Sicong Liu, Puhua Jiang, Xianghui Yang, Dongyuan Guo, Yixuan Tang, Xinyue Mao, Jiaao Yu, Junlin Yu, Jihong Zhang, Meng Chen, Liang Dong, Yiwen Jia, Chao Zhang, Yonghao Tan, Hao Zhang, Zheng Ye, Peng He, Runzhou Wu, Minghui Chen, Zhan Li, Wangchen Qin, Lei Wang, Yifu Sun, Lin Niu, Xiang Yuan, Xiaofeng Yang, Yingping He, Jie Xiao, Yangyu Tao, Jianchen Zhu, Jinbao Xue, Kai Liu, Chongqing Zhao, Xinming Wu, Tian Liu, Peng Chen, Di Wang, Yuhong Liu, Linus, Jie Jiang, Tengfei Wang, Chunchao Guo</p><p><b>Upvotes:</b> 83</p><p><b>Summary:</b> Creating immersive and playable 3D worlds from texts or images remains a fundamental challenge in computer vision and graphics. Existing world generation approaches typically fall into two categories: video-based methods that offer rich diversity but lack 3D consistency and rendering efficiency, and 3D-based methods that provide geometric consistency but struggle with limited training data and memory-inefficient representations. To address these limitations, we present HunyuanWorld 1.0, a novel framework that combines the best of both worlds for generating immersive, explorable, and interactive 3D scenes from text and image conditions. Our approach features three key advantages: 1) 360{\deg} immersive experiences via panoramic world proxies; 2) mesh export capabilities for seamless compatibility with existing computer graphics pipelines; 3) disentangled object representations for augmented interactivity. The core of our framework is a semantically layered 3D mesh representation that leverages panoramic images as 360{\deg} world proxies for semantic-aware world decomposition and reconstruction, enabling the generation of diverse 3D worlds. Extensive experiments demonstrate that our method achieves state-of-the-art performance in generating coherent, explorable, and interactive 3D worlds while enabling versatile applications in virtual reality, physical simulation, game development, and interactive content creation.</p> - https://arxiv.org/abs/2507.21809 - Tue, 29 Jul 2025 13:43:35 +0000 + CODA: Coordinating the Cerebrum and Cerebellum for a Dual-Brain Computer Use Agent with Decoupled Reinforcement Learning + https://arxiv.org/abs/2508.20096 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.20096.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zeyi Sun, Yuhang Cao, Jianze Liang, Qiushi Sun, Ziyu Liu, Zhixiong Zhang, Yuhang Zang, Xiaoyi Dong, Kai Chen, Dahua Lin, Jiaqi Wang</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> Autonomous agents for Graphical User Interfaces (GUIs) face significant challenges in specialized domains such as scientific computing, where both long-horizon planning and precise execution are required. Existing approaches suffer from a trade-off: generalist agents excel at planning but perform poorly in execution, while specialized agents demonstrate the opposite weakness. Recent compositional frameworks attempt to bridge this gap by combining a planner and an actor, but they are typically static and non-trainable, which prevents adaptation from experience. This is a critical limitation given the scarcity of high-quality data in scientific domains. To address these limitations, we introduce CODA, a novel and trainable compositional framework that integrates a generalist planner (Cerebrum) with a specialist executor (Cerebellum), trained via a dedicated two-stage pipeline. In the first stage, Specialization, we apply a decoupled GRPO approach to train an expert planner for each scientific application individually, bootstrapping from a small set of task trajectories. In the second stage, Generalization, we aggregate all successful trajectories from the specialized experts to build a consolidated dataset, which is then used for supervised fine-tuning of the final planner. This equips CODA with both robust execution and cross-domain generalization. Evaluated on four challenging applications from the ScienceBoard benchmark, CODA significantly outperforms baselines and establishes a new state of the art among open-source models.</p> + https://arxiv.org/abs/2508.20096 + Wed, 27 Aug 2025 17:59:50 +0000 - X-Omni: Reinforcement Learning Makes Discrete Autoregressive Image Generative Models Great Again - https://arxiv.org/abs/2507.22058 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.22058.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zigang Geng, Yibing Wang, Yeyao Ma, Chen Li, Yongming Rao, Shuyang Gu, Zhao Zhong, Qinglin Lu, Han Hu, Xiaosong Zhang, Linus, Di Wang, Jie Jiang</p><p><b>Upvotes:</b> 31</p><p><b>Summary:</b> Numerous efforts have been made to extend the ``next token prediction'' paradigm to visual contents, aiming to create a unified approach for both image generation and understanding. Nevertheless, attempts to generate images through autoregressive modeling with discrete tokens have been plagued by issues such as low visual fidelity, distorted outputs, and failure to adhere to complex instructions when rendering intricate details. These shortcomings are likely attributed to cumulative errors during autoregressive inference or information loss incurred during the discretization process. Probably due to this challenge, recent research has increasingly shifted toward jointly training image generation with diffusion objectives and language generation with autoregressive objectives, moving away from unified modeling approaches. In this work, we demonstrate that reinforcement learning can effectively mitigate artifacts and largely enhance the generation quality of a discrete autoregressive modeling method, thereby enabling seamless integration of image and language generation. Our framework comprises a semantic image tokenizer, a unified autoregressive model for both language and images, and an offline diffusion decoder for image generation, termed X-Omni. X-Omni achieves state-of-the-art performance in image generation tasks using a 7B language model, producing images with high aesthetic quality while exhibiting strong capabilities in following instructions and rendering long texts.</p> - https://arxiv.org/abs/2507.22058 - Tue, 29 Jul 2025 17:59:04 +0000 + MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers + https://arxiv.org/abs/2508.20453 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.20453.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhenting Wang, Qi Chang, Hemani Patel, Shashank Biju, Cheng-En Wu, Quan Liu, Aolin Ding, Alireza Rezazadeh, Ankit Shah, Yujia Bao, Eugene Siow</p><p><b>Upvotes:</b> 41</p><p><b>Summary:</b> We introduce MCP-Bench, a benchmark for evaluating large language models (LLMs) on realistic, multi-step tasks that demand tool use, cross-tool coordination, precise parameter control, and planning/reasoning for solving tasks. Built on the Model Context Protocol (MCP), MCP-Bench connects LLMs to 28 representative live MCP servers spanning 250 tools across domains such as finance, traveling, scientific computing, and academic search. Unlike prior API-based benchmarks, each MCP server provides a set of complementary tools designed to work together, enabling the construction of authentic, multi-step tasks with rich input-output coupling. Tasks in MCP-Bench test agents' ability to retrieve relevant tools from fuzzy instructions without explicit tool names, plan multi-hop execution trajectories for complex objectives, ground responses in intermediate tool outputs, and orchestrate cross-domain workflows - capabilities not adequately evaluated by existing benchmarks that rely on explicit tool specifications, shallow few-step workflows, and isolated domain operations. We propose a multi-faceted evaluation framework covering tool-level schema understanding and usage, trajectory-level planning, and task completion. Experiments on 20 advanced LLMs reveal persistent challenges in MCP-Bench. Code and data: https://github.com/Accenture/mcp-bench.</p> + https://arxiv.org/abs/2508.20453 + Thu, 28 Aug 2025 05:58:57 +0000 - Falcon-H1: A Family of Hybrid-Head Language Models Redefining Efficiency and Performance - https://arxiv.org/abs/2507.22448 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.22448.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jingwei Zuo, Maksim Velikanov, Ilyas Chahed, Younes Belkada, Dhia Eddine Rhayem, Guillaume Kunsch, Hakim Hacid, Hamza Yous, Brahim Farhat, Ibrahim Khadraoui, Mugariya Farooq, Giulia Campesan, Ruxandra Cojocaru, Yasser Djilali, Shi Hu, Iheb Chaabane, Puneesh Khanna, Mohamed El Amine Seddik, Ngoc Dung Huynh, Phuc Le Khac, Leen AlQadi, Billel Mokeddem, Mohamed Chami, Abdalgader Abubaker, Mikhail Lubinets, Kacper Piskorski, Slim Frikha</p><p><b>Upvotes:</b> 42</p><p><b>Summary:</b> In this report, we introduce Falcon-H1, a new series of large language models (LLMs) featuring hybrid architecture designs optimized for both high performance and efficiency across diverse use cases. Unlike earlier Falcon models built solely on Transformer or Mamba architectures, Falcon-H1 adopts a parallel hybrid approach that combines Transformer-based attention with State Space Models (SSMs), known for superior long-context memory and computational efficiency. We systematically revisited model design, data strategy, and training dynamics, challenging conventional practices in the field. Falcon-H1 is released in multiple configurations, including base and instruction-tuned variants at 0.5B, 1.5B, 1.5B-deep, 3B, 7B, and 34B parameters. Quantized instruction-tuned models are also available, totaling over 30 checkpoints on Hugging Face Hub. Falcon-H1 models demonstrate state-of-the-art performance and exceptional parameter and training efficiency. The flagship Falcon-H1-34B matches or outperforms models up to 70B scale, such as Qwen3-32B, Qwen2.5-72B, and Llama3.3-70B, while using fewer parameters and less data. Smaller models show similar trends: the Falcon-H1-1.5B-Deep rivals current leading 7B-10B models, and Falcon-H1-0.5B performs comparably to typical 7B models from 2024. These models excel across reasoning, mathematics, multilingual tasks, instruction following, and scientific knowledge. With support for up to 256K context tokens and 18 languages, Falcon-H1 is suitable for a wide range of applications. All models are released under a permissive open-source license, underscoring our commitment to accessible and impactful AI research.</p> - https://arxiv.org/abs/2507.22448 - Wed, 30 Jul 2025 07:55:33 +0000 + rStar2-Agent: Agentic Reasoning Technical Report + https://arxiv.org/abs/2508.20722 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.20722.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ning Shang, Yifei Liu, Yi Zhu, Li Lyna Zhang, Weijiang Xu, Xinyu Guan, Buze Zhang, Bingcheng Dong, Xudong Zhou, Bowen Zhang, Ying Xin, Ziming Miao, Scarlett Li, Fan Yang, Mao Yang</p><p><b>Upvotes:</b> 67</p><p><b>Summary:</b> We introduce rStar2-Agent, a 14B math reasoning model trained with agentic reinforcement learning to achieve frontier-level performance. Beyond current long CoT, the model demonstrates advanced cognitive behaviors, such as thinking carefully before using Python coding tools and reflecting on code execution feedback to autonomously explore, verify, and refine intermediate steps in complex problem-solving. This capability is enabled through three key innovations that makes agentic RL effective at scale: (i) an efficient RL infrastructure with a reliable Python code environment that supports high-throughput execution and mitigates the high rollout costs, enabling training on limited GPU resources (64 MI300X GPUs); (ii) GRPO-RoC, an agentic RL algorithm with a Resample-on-Correct rollout strategy that addresses the inherent environment noises from coding tools, allowing the model to reason more effectively in a code environment; (iii) An efficient agent training recipe that starts with non-reasoning SFT and progresses through multi-RL stages, yielding advanced cognitive abilities with minimal compute cost. To this end, rStar2-Agent boosts a pre-trained 14B model to state of the art in only 510 RL steps within one week, achieving average pass@1 scores of 80.6% on AIME24 and 69.8% on AIME25, surpassing DeepSeek-R1 (671B) with significantly shorter responses. Beyond mathematics, rStar2-Agent-14B also demonstrates strong generalization to alignment, scientific reasoning, and agentic tool-use tasks. Code and training recipes are available at https://github.com/microsoft/rStar.</p> + https://arxiv.org/abs/2508.20722 + Thu, 28 Aug 2025 12:45:25 +0000 - ScreenCoder: Advancing Visual-to-Code Generation for Front-End Automation via Modular Multimodal Agents - https://arxiv.org/abs/2507.22827 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.22827.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yilei Jiang, Yaozhi Zheng, Yuxuan Wan, Jiaming Han, Qunzhong Wang, Michael R. Lyu, Xiangyu Yue</p><p><b>Upvotes:</b> 61</p><p><b>Summary:</b> Automating the transformation of user interface (UI) designs into front-end code holds significant promise for accelerating software development and democratizing design workflows. While recent large language models (LLMs) have demonstrated progress in text-to-code generation, many existing approaches rely solely on natural language prompts, limiting their effectiveness in capturing spatial layout and visual design intent. In contrast, UI development in practice is inherently multimodal, often starting from visual sketches or mockups. To address this gap, we introduce a modular multi-agent framework that performs UI-to-code generation in three interpretable stages: grounding, planning, and generation. The grounding agent uses a vision-language model to detect and label UI components, the planning agent constructs a hierarchical layout using front-end engineering priors, and the generation agent produces HTML/CSS code via adaptive prompt-based synthesis. This design improves robustness, interpretability, and fidelity over end-to-end black-box methods. Furthermore, we extend the framework into a scalable data engine that automatically produces large-scale image-code pairs. Using these synthetic examples, we fine-tune and reinforce an open-source VLM, yielding notable gains in UI understanding and code quality. Extensive experiments demonstrate that our approach achieves state-of-the-art performance in layout accuracy, structural coherence, and code correctness. Our code is made publicly available at https://github.com/leigest519/ScreenCoder.</p> - https://arxiv.org/abs/2507.22827 - Wed, 30 Jul 2025 16:41:21 +0000 + Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning + https://arxiv.org/abs/2508.20751 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.20751.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yibin Wang, Zhimin Li, Yuhang Zang, Yujie Zhou, Jiazi Bu, Chunyu Wang, Qinglin Lu, Cheng Jin, Jiaqi Wang</p><p><b>Upvotes:</b> 75</p><p><b>Summary:</b> Recent advancements highlight the importance of GRPO-based reinforcement learning methods and benchmarking in enhancing text-to-image (T2I) generation. However, current methods using pointwise reward models (RM) for scoring generated images are susceptible to reward hacking. We reveal that this happens when minimal score differences between images are amplified after normalization, creating illusory advantages that drive the model to over-optimize for trivial gains, ultimately destabilizing the image generation process. To address this, we propose Pref-GRPO, a pairwise preference reward-based GRPO method that shifts the optimization objective from score maximization to preference fitting, ensuring more stable training. In Pref-GRPO, images are pairwise compared within each group using preference RM, and the win rate is used as the reward signal. Extensive experiments demonstrate that PREF-GRPO differentiates subtle image quality differences, providing more stable advantages and mitigating reward hacking. Additionally, existing T2I benchmarks are limited by coarse evaluation criteria, hindering comprehensive model assessment. To solve this, we introduce UniGenBench, a unified T2I benchmark comprising 600 prompts across 5 main themes and 20 subthemes. It evaluates semantic consistency through 10 primary and 27 sub-criteria, leveraging MLLM for benchmark construction and evaluation. Our benchmarks uncover the strengths and weaknesses of both open and closed-source T2I models and validate the effectiveness of Pref-GRPO.</p> + https://arxiv.org/abs/2508.20751 + Thu, 28 Aug 2025 13:11:24 +0000