From 69c709bf76d92f1539546c691a475e9e70689835 Mon Sep 17 00:00:00 2001 From: "github-actions[bot]" Date: Sat, 1 Nov 2025 00:13:30 +0000 Subject: [PATCH] bot: update monthly RSS feed --- feed_monthly.xml | 1052 +++++++++++++++++++++++----------------------- 1 file changed, 526 insertions(+), 526 deletions(-) diff --git a/feed_monthly.xml b/feed_monthly.xml index 6694097..ab736b1 100644 --- a/feed_monthly.xml +++ b/feed_monthly.xml @@ -7,741 +7,741 @@ http://www.rssboard.org/rss-specification python-feedgen en - Wed, 01 Oct 2025 00:13:26 +0000 + Sat, 01 Nov 2025 00:13:30 +0000 - A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code - https://arxiv.org/abs/2508.18106 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.18106.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Keke Lian, Bin Wang, Lei Zhang, Libo Chen, Junjie Wang, Ziming Zhao, Yujiu Yang, Haotong Duan, Haoran Zhao, Shuang Liao, Mingda Guo, Jiazheng Quan, Yilu Zhong, Chenhao He, Zichuan Chen, Jie Wu, Haoling Li, Zhaoxuan Li, Jiongchi Yu, Hui Li, Dong Zhang</p><p><b>Upvotes:</b> 342</p><p><b>Summary:</b> The increasing adoption of large language models (LLMs) in software engineering necessitates rigorous security evaluation of their generated code. However, existing benchmarks often lack relevance to real-world AI programming scenarios, making them inadequate for assessing the practical security risks associated with AI-generated code in production environments. To address this gap, we introduce A.S.E (AI Code Generation Security Evaluation), a repository-level evaluation benchmark designed to closely mirror real-world AI programming tasks, offering a comprehensive and reliable framework for assessing the security of AI-generated code. Our evaluation of leading LLMs on A.S.E reveals several key findings. In particular, current LLMs still struggle with secure coding. The complexity in repository-level scenarios presents challenges for LLMs that typically perform well on snippet-level tasks. Morever, a larger reasoning budget does not necessarily lead to better code generation. These observations offer valuable insights into the current state of AI code generation, assisting developers in selecting the most appropriate models for practical tasks, while laying the foundation for refining LLMs to generate secure and efficient code in real-world applications.</p> - https://arxiv.org/abs/2508.18106 - Mon, 25 Aug 2025 15:11:11 +0000 + Meta-Awareness Enhances Reasoning Models: Self-Alignment Reinforcement Learning + https://arxiv.org/abs/2510.03259 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.03259.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yoonjeon Kim, Doohyuk Jang, Eunho Yang</p><p><b>Upvotes:</b> 57</p><p><b>Summary:</b> Recent studies on reasoning models explore the meta-awareness of language models, the ability to know how to think by itself. We argue that large reasoning models lack this meta-awareness property by proving severe misalignment between true rollouts and predicted meta information. We posit that aligning meta-prediction with true rollouts will lead to significant performance gains. To verify this hypothesis, we design a training pipeline that boosts Meta-Awareness via Self-Alignment (MASA), and prove that enhanced meta-awareness directly translates to improved accuracy. Unlike existing meta-cognitive reasoning models, our method does not require external training sources but leverages self-generated signals to train meta-awareness. Moreover, our method enables efficient training by i) filtering out zero-variance prompts that are either trivial or unsolvable and ii) cutting off lengthy rollouts when they are unlikely to lead to correct answers. The results are inspiring: our strategy yields significant improvements in both accuracy and training efficiency on in-domain tasks and shows strong generalization to out-of-domain benchmarks. More specifically, our method can speed up GRPO training by over 1.28x to reach the same performance, and achieve a 19.3% gain in accuracy on AIME25, and a 6.2 % average gain over six mathematics benchmarks. Training with meta-cognitive guidance enhances out-of-domain generalization, giving a 3.87 % boost on GPQA-Diamond and a 2.08 % overall accuracy gain across 13 benchmarks spanning logical, scientific, and coding domains.</p> + https://arxiv.org/abs/2510.03259 + Fri, 26 Sep 2025 14:05:48 +0000 - Droplet3D: Commonsense Priors from Videos Facilitate 3D Generation - https://arxiv.org/abs/2508.20470 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.20470.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiaochuan Li, Guoguang Du, Runze Zhang, Liang Jin, Qi Jia, Lihua Lu, Zhenhua Guo, Yaqian Zhao, Haiyang Liu, Tianqi Wang, Changsheng Li, Xiaoli Gong, Rengang Li, Baoyu Fan</p><p><b>Upvotes:</b> 73</p><p><b>Summary:</b> Scaling laws have validated the success and promise of large-data-trained models in creative generation across text, image, and video domains. However, this paradigm faces data scarcity in the 3D domain, as there is far less of it available on the internet compared to the aforementioned modalities. Fortunately, there exist adequate videos that inherently contain commonsense priors, offering an alternative supervisory signal to mitigate the generalization bottleneck caused by limited native 3D data. On the one hand, videos capturing multiple views of an object or scene provide a spatial consistency prior for 3D generation. On the other hand, the rich semantic information contained within the videos enables the generated content to be more faithful to the text prompts and semantically plausible. This paper explores how to apply the video modality in 3D asset generation, spanning datasets to models. We introduce Droplet3D-4M, the first large-scale video dataset with multi-view level annotations, and train Droplet3D, a generative model supporting both image and dense text input. Extensive experiments validate the effectiveness of our approach, demonstrating its ability to produce spatially consistent and semantically plausible content. Moreover, in contrast to the prevailing 3D solutions, our approach exhibits the potential for extension to scene-level applications. This indicates that the commonsense priors from the videos significantly facilitate 3D creation. We have open-sourced all resources including the dataset, code, technical framework, and model weights: https://dropletx.github.io/.</p> - https://arxiv.org/abs/2508.20470 - Thu, 28 Aug 2025 06:39:41 +0000 + SINQ: Sinkhorn-Normalized Quantization for Calibration-Free Low-Precision LLM Weights + https://arxiv.org/abs/2509.22944 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.22944.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lorenz K. Müller, Philippe Bich, Jiawei Zhuang, Ahmet Çelik, Luca Benfenati, Lukas Cavigelli</p><p><b>Upvotes:</b> 76</p><p><b>Summary:</b> Post-training quantization has emerged as the most widely used strategy for deploying large language models at low precision. Still, current methods show perplexity degradation at bit-widths less than or equal to 4, partly because representing outliers causes precision issues in parameters that share the same scales as these outliers. This problem is especially pronounced for calibration-free, uniform quantization methods. We introduce SINQ to augment existing post-training quantizers with an additional second-axis scale factor and a fast Sinkhorn-Knopp-style algorithm that finds scales to normalize per-row and per-column variances, thereby minimizing a novel per-matrix proxy target for quantization: the matrix imbalance. Our method has no interactions between layers and can be trivially applied to new architectures to quantize any linear layers. We evaluate our method on the Qwen3 model family and DeepSeek-V2.5. SINQ improves WikiText2 and C4 perplexity significantly against uncalibrated uniform quantization baselines and can be further enhanced by combining it with calibration and non-uniform quantization levels. Code to reproduce the results of this work and to easily quantize models using SINQ is available at https://github.com/huawei-csl/SINQ.</p> + https://arxiv.org/abs/2509.22944 + Fri, 26 Sep 2025 21:22:54 +0000 - EmbodiedOneVision: Interleaved Vision-Text-Action Pretraining for General Robot Control - https://arxiv.org/abs/2508.21112 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.21112.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Delin Qu, Haoming Song, Qizhi Chen, Zhaoqing Chen, Xianqiang Gao, Xinyi Ye, Qi Lv, Modi Shi, Guanghui Ren, Cheng Ruan, Maoqing Yao, Haoran Yang, Jiacheng Bao, Bin Zhao, Dong Wang</p><p><b>Upvotes:</b> 76</p><p><b>Summary:</b> The human ability to seamlessly perform multimodal reasoning and physical interaction in the open world is a core goal for general-purpose embodied intelligent systems. Recent vision-language-action (VLA) models, which are co-trained on large-scale robot and visual-text data, have demonstrated notable progress in general robot control. However, they still fail to achieve human-level flexibility in interleaved reasoning and interaction. In this work, introduce EO-Robotics, consists of EO-1 model and EO-Data1.5M dataset. EO-1 is a unified embodied foundation model that achieves superior performance in multimodal embodied reasoning and robot control through interleaved vision-text-action pre-training. The development of EO-1 is based on two key pillars: (i) a unified architecture that processes multimodal inputs indiscriminately (image, text, video, and action), and (ii) a massive, high-quality multimodal embodied reasoning dataset, EO-Data1.5M, which contains over 1.5 million samples with emphasis on interleaved vision-text-action comprehension. EO-1 is trained through synergies between auto-regressive decoding and flow matching denoising on EO-Data1.5M, enabling seamless robot action generation and multimodal embodied reasoning. Extensive experiments demonstrate the effectiveness of interleaved vision-text-action learning for open-world understanding and generalization, validated through a variety of long-horizon, dexterous manipulation tasks across multiple embodiments. This paper details the architecture of EO-1, the data construction strategy of EO-Data1.5M, and the training methodology, offering valuable insights for developing advanced embodied foundation models.</p> - https://arxiv.org/abs/2508.21112 - Thu, 28 Aug 2025 17:26:15 +0000 + From What to Why: A Multi-Agent System for Evidence-based Chemical Reaction Condition Reasoning + https://arxiv.org/abs/2509.23768 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.23768.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Cheng Yang, Jiaxuan Lu, Haiyuan Wan, Junchi Yu, Feiwei Qin</p><p><b>Upvotes:</b> 49</p><p><b>Summary:</b> The chemical reaction recommendation is to select proper reaction condition parameters for chemical reactions, which is pivotal to accelerating chemical science. With the rapid development of large language models (LLMs), there is growing interest in leveraging their reasoning and planning capabilities for reaction condition recommendation. Despite their success, existing methods rarely explain the rationale behind the recommended reaction conditions, limiting their utility in high-stakes scientific workflows. In this work, we propose ChemMAS, a multi-agent system that reframes condition prediction as an evidence-based reasoning task. ChemMAS decomposes the task into mechanistic grounding, multi-channel recall, constraint-aware agentic debate, and rationale aggregation. Each decision is backed by interpretable justifications grounded in chemical knowledge and retrieved precedents. Experiments show that ChemMAS achieves 20-35% gains over domain-specific baselines and outperforms general-purpose LLMs by 10-15% in Top-1 accuracy, while offering falsifiable, human-trustable rationales, which establishes a new paradigm for explainable AI in scientific discovery.</p> + https://arxiv.org/abs/2509.23768 + Sun, 28 Sep 2025 09:34:35 +0000 - R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Annealing and Reinforce Learning - https://arxiv.org/abs/2508.21113 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.21113.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jie Jiang, Qi Yang, Bolin Ni, Shiming Xiang, Han Hu, Houwen Peng</p><p><b>Upvotes:</b> 108</p><p><b>Summary:</b> Multimodal Large Language Models (MLLMs) equipped with step-by-step thinking capabilities have demonstrated remarkable performance on complex reasoning problems. However, this thinking process is redundant for simple problems solvable without complex reasoning. To address this inefficiency, we propose R-4B, an auto-thinking MLLM, which can adaptively decide when to think based on problem complexity. The central idea of R-4B is to empower the model with both thinking and non-thinking capabilities using bi-mode annealing, and apply Bi-mode Policy Optimization~(BPO) to improve the model's accuracy in determining whether to activate the thinking process. Specifically, we first train the model on a carefully curated dataset spanning various topics, which contains samples from both thinking and non-thinking modes. Then it undergoes a second phase of training under an improved GRPO framework, where the policy model is forced to generate responses from both modes for each input query. Experimental results show that R-4B achieves state-of-the-art performance across 25 challenging benchmarks. It outperforms Qwen2.5-VL-7B in most tasks and achieves performance comparable to larger models such as Kimi-VL-A3B-Thinking-2506 (16B) on reasoning-intensive benchmarks with lower computational cost.</p> - https://arxiv.org/abs/2508.21113 - Thu, 28 Aug 2025 17:48:19 +0000 + Winning the Pruning Gamble: A Unified Approach to Joint Sample and Token Pruning for Efficient Supervised Fine-Tuning + https://arxiv.org/abs/2509.23873 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.23873.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shaobo Wang, Jiaming Wang, Jiajun Zhang, Cong Wang, Yue Min, Zichen Wen, Fei Huang, Huiqiang Jiang, Junyang Lin, Dayiheng Liu, Linfeng Zhang</p><p><b>Upvotes:</b> 67</p><p><b>Summary:</b> As supervised fine-tuning (SFT) evolves from a lightweight post-training step into a compute-intensive phase rivaling mid-training in scale, data efficiency has become critical for aligning large language models (LLMs) under tight budgets. Existing data pruning methods suffer from a fragmented design: they operate either at the sample level or the token level in isolation, failing to jointly optimize both dimensions. This disconnect leads to significant inefficiencies--high-value samples may still contain redundant tokens, while token-level pruning often discards crucial instructional or corrective signals embedded in individual examples. To address this bottleneck, we introduce the Error-Uncertainty (EU) Plane, a diagnostic framework that jointly characterizes the heterogeneous utility of training data across samples and tokens. Guided by this insight, we propose Quadrant-based Tuning (Q-Tuning), a unified framework that strategically coordinates sample pruning and token pruning. Q-Tuning employs a two-stage strategy: first, it performs sample-level triage to retain examples rich in informative misconceptions or calibration signals; second, it applies an asymmetric token-pruning policy, using a context-aware scoring mechanism to trim less salient tokens exclusively from misconception samples while preserving calibration samples in their entirety. Our method sets a new state of the art across five diverse benchmarks. Remarkably, on SmolLM2-1.7B, Q-Tuning achieves a +38\% average improvement over the full-data SFT baseline using only 12.5\% of the original training data. As the first dynamic pruning approach to consistently outperform full-data training, Q-Tuning provides a practical and scalable blueprint for maximizing data utilization in budget-constrained LLM SFT.</p> + https://arxiv.org/abs/2509.23873 + Sun, 28 Sep 2025 13:27:38 +0000 - A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers - https://arxiv.org/abs/2508.21148 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.21148.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ming Hu, Chenglong Ma, Wei Li, Wanghan Xu, Jiamin Wu, Jucheng Hu, Tianbin Li, Guohang Zhuang, Jiaqi Liu, Yingzhou Lu, Ying Chen, Chaoyang Zhang, Cheng Tan, Jie Ying, Guocheng Wu, Shujian Gao, Pengcheng Chen, Jiashi Lin, Haitao Wu, Lulu Chen, Fengxiang Wang, Yuanyuan Zhang, Xiangyu Zhao, Feilong Tang, Encheng Su, Junzhi Ning, Xinyao Liu, Ye Du, Changkai Ji, Cheng Tang, Huihui Xu, Ziyang Chen, Ziyan Huang, Jiyao Liu, Pengfei Jiang, Yizhou Wang, Chen Tang, Jianyu Wu, Yuchen Ren, Siyuan Yan, Zhonghua Wang, Zhongxing Xu, Shiyan Su, Shangquan Sun, Runkai Zhao, Zhisheng Zhang, Yu Liu, Fudi Wang, Yuanfeng Ji, Yanzhou Su, Hongming Shan, Chunmei Feng, Jiahao Xu, Jiangtao Yan, Wenhao Tang, Diping Song, Lihao Liu, Yanyan Huang, Lequan Yu, Bin Fu, Shujun Wang, Xiaomeng Li, Xiaowei Hu, Yun Gu, Ben Fei, Zhongying Deng, Benyou Wang, Yuewen Cao, Minjie Shen, Haodong Duan, Jie Xu, Yirong Chen, Fang Yan, Hongxia Hao, Jielan Li, Jiajun Du, Yanbo Wang, Imran Razzak, Chi Zhang, Lijun Wu, Conghui He, Zhaohui Lu, Jinhai Huang, Yihao Liu, Fenghua Ling, Yuqiang Li, Aoran Wang, Qihao Zheng, Nanqing Dong, Tianfan Fu, Dongzhan Zhou, Yan Lu, Wenlong Zhang, Jin Ye, Jianfei Cai, Wanli Ouyang, Yu Qiao, Zongyuan Ge, Shixiang Tang, Junjun He, Chunfeng Song, Lei Bai, Bowen Zhou</p><p><b>Upvotes:</b> 141</p><p><b>Summary:</b> Scientific Large Language Models (Sci-LLMs) are transforming how knowledge is represented, integrated, and applied in scientific research, yet their progress is shaped by the complex nature of scientific data. This survey presents a comprehensive, data-centric synthesis that reframes the development of Sci-LLMs as a co-evolution between models and their underlying data substrate. We formulate a unified taxonomy of scientific data and a hierarchical model of scientific knowledge, emphasizing the multimodal, cross-scale, and domain-specific challenges that differentiate scientific corpora from general natural language processing datasets. We systematically review recent Sci-LLMs, from general-purpose foundations to specialized models across diverse scientific disciplines, alongside an extensive analysis of over 270 pre-/post-training datasets, showing why Sci-LLMs pose distinct demands -- heterogeneous, multi-scale, uncertainty-laden corpora that require representations preserving domain invariance and enabling cross-modal reasoning. On evaluation, we examine over 190 benchmark datasets and trace a shift from static exams toward process- and discovery-oriented assessments with advanced evaluation protocols. These data-centric analyses highlight persistent issues in scientific data development and discuss emerging solutions involving semi-automated annotation pipelines and expert validation. Finally, we outline a paradigm shift toward closed-loop systems where autonomous agents based on Sci-LLMs actively experiment, validate, and contribute to a living, evolving knowledge base. Collectively, this work provides a roadmap for building trustworthy, continually evolving artificial intelligence (AI) systems that function as a true partner in accelerating scientific discovery.</p> - https://arxiv.org/abs/2508.21148 - Thu, 28 Aug 2025 18:30:52 +0000 + MemMamba: Rethinking Memory Patterns in State Space Model + https://arxiv.org/abs/2510.03279 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.03279.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Youjin Wang, Yangjingyi Chen, Jiahao Yan, Jiaxuan Lu, Xiao Sun</p><p><b>Upvotes:</b> 69</p><p><b>Summary:</b> With the explosive growth of data, long-sequence modeling has become increasingly important in tasks such as natural language processing and bioinformatics. However, existing methods face inherent trade-offs between efficiency and memory. Recurrent neural networks suffer from gradient vanishing and explosion, making them hard to scale. Transformers can model global dependencies but are constrained by quadratic complexity. Recently, selective state-space models such as Mamba have demonstrated high efficiency with O(n) time and O(1) recurrent inference, yet their long-range memory decays exponentially. In this work, we conduct mathematical derivations and information-theoretic analysis to systematically uncover the memory decay mechanism of Mamba, answering a fundamental question: what is the nature of Mamba's long-range memory and how does it retain information? To quantify key information loss, we further introduce horizontal-vertical memory fidelity metrics that capture degradation both within and across layers. Inspired by how humans distill and retain salient information when reading long documents, we propose MemMamba, a novel architectural framework that integrates state summarization mechanism together with cross-layer and cross-token attention, which alleviates long-range forgetting while preserving linear complexity. MemMamba achieves significant improvements over existing Mamba variants and Transformers on long-sequence benchmarks such as PG19 and Passkey Retrieval, while delivering a 48% speedup in inference efficiency. Both theoretical analysis and empirical results demonstrate that MemMamba achieves a breakthrough in the complexity-memory trade-off, offering a new paradigm for ultra-long sequence modeling.</p> + https://arxiv.org/abs/2510.03279 + Sun, 28 Sep 2025 14:40:58 +0000 - Open Data Synthesis For Deep Research - https://arxiv.org/abs/2509.00375 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.00375.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ziyi Xia, Kun Luo, Hongjin Qian, Zheng Liu</p><p><b>Upvotes:</b> 68</p><p><b>Summary:</b> Large language models (LLMs) are increasingly expected to go beyond simple factual queries toward Deep Research-tasks that require decomposing questions into sub-problems, coordinating multi-step reasoning, and synthesizing evidence from diverse sources. We formalize Deep Research tasks with verifiable answers as Hierarchical Constraint Satisfaction Problems (HCSPs), which are fundamentally different from single-constraint, multi-hop, or flat CSP formulations. However, existing benchmarks (e.g., Natural Questions, HotpotQA) fail to capture this complexity, while recent synthetic datasets often introduce shortcut reasoning, knowledge leakage, or lack sufficient structural depth. To address this gap, we introduce InfoSeek, a scalable framework for synthesizing complex Deep Research tasks. InfoSeek uses a dual-agent system to recursively build a Research Tree from large-scale webpages, blurring intermediate nodes into valid sub-problems, and converting these trees into natural language questions that require traversing the full hierarchy. It also enables rapid scaling, yielding over 50K training examples, a curated test set, and reasoning trajectories generated via reject sampling. Experiments show that models trained on InfoSeek consistently outperform strong baselines. On a challenging benchmark BrowseComp-Plus, 3B LLMs optimized with InfoSeek surpass much larger 32B models and lightweight commercial APIs (e.g., Gemini2.5-Flash), while achieving performance comparable to stronger APIs (e.g., Gemini2.5-Pro). By preserving meta-information such as intermediate steps and retrieval labels, InfoSeek further supports advanced optimization strategies, including compound reward design and trajectory-level exploration. We provide our codes and datasets in https://github.com/VectorSpaceLab/InfoSeek{this repository}.</p> - https://arxiv.org/abs/2509.00375 - Sat, 30 Aug 2025 06:02:56 +0000 + MCPMark: A Benchmark for Stress-Testing Realistic and Comprehensive MCP Use + https://arxiv.org/abs/2509.24002 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.24002.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zijian Wu, Xiangyan Liu, Xinyuan Zhang, Lingjun Chen, Fanqing Meng, Lingxiao Du, Yiran Zhao, Fanshi Zhang, Yaoqi Ye, Jiawei Wang, Zirui Wang, Jinjie Ni, Yufan Yang, Arvin Xu, Michael Qizhe Shieh</p><p><b>Upvotes:</b> 170</p><p><b>Summary:</b> MCP standardizes how LLMs interact with external systems, forming the foundation for general agents. However, existing MCP benchmarks remain narrow in scope: they focus on read-heavy tasks or tasks with limited interaction depth, and fail to capture the complexity and realism of real-world workflows. To address this gap, we propose MCPMark, a benchmark designed to evaluate MCP use in a more realistic and comprehensive manner. It consists of 127 high-quality tasks collaboratively created by domain experts and AI agents. Each task begins with a curated initial state and includes a programmatic script for automatic verification. These tasks demand richer and more diverse interactions with the environment, involving a broad range of create, read, update, and delete (CRUD) operations. We conduct a comprehensive evaluation of cutting-edge LLMs using a minimal agent framework that operates in a tool-calling loop. Empirical results show that the best-performing model, gpt-5-medium, reaches only 52.56\% pass@1 and 33.86\% pass^4, while other widely regarded strong models, including claude-sonnet-4 and o3, fall below 30\% pass@1 and 15\% pass^4. On average, LLMs require 16.2 execution turns and 17.4 tool calls per task, significantly surpassing those in previous MCP benchmarks and highlighting the stress-testing nature of MCPMark.</p> + https://arxiv.org/abs/2509.24002 + Sun, 28 Sep 2025 17:53:27 +0000 - Gated Associative Memory: A Parallel O(N) Architecture for Efficient Sequence Modeling - https://arxiv.org/abs/2509.00605 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.00605.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Rishiraj Acharya</p><p><b>Upvotes:</b> 42</p><p><b>Summary:</b> The Transformer architecture, underpinned by the self-attention mechanism, has become the de facto standard for sequence modeling tasks. However, its core computational primitive scales quadratically with sequence length (O(N^2)), creating a significant bottleneck for processing long contexts. In this paper, we propose the Gated Associative Memory (GAM) network, a novel, fully parallel architecture for sequence modeling that exhibits linear complexity (O(N)) with respect to sequence length. The GAM block replaces the self-attention layer with two parallel pathways: a causal convolution to efficiently capture local, position-dependent context, and a parallel associative memory retrieval mechanism to model global, content-based patterns. These pathways are dynamically fused using a gating mechanism, allowing the model to flexibly combine local and global information for each token. We implement GAM from scratch and conduct a rigorous comparative analysis against a standard Transformer model and a modern linear-time baseline (Mamba) on the WikiText-2 benchmark, as well as against the Transformer on the TinyStories dataset. Our experiments demonstrate that GAM is consistently faster, outperforming both baselines on training speed, and achieves a superior or competitive final validation perplexity across all datasets, establishing it as a promising and efficient alternative for sequence modeling.</p> - https://arxiv.org/abs/2509.00605 - Sat, 30 Aug 2025 20:59:46 +0000 + Fathom-DeepResearch: Unlocking Long Horizon Information Retrieval and Synthesis for SLMs + https://arxiv.org/abs/2509.24107 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.24107.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shreyas Singh, Kunal Singh, Pradeep Moturi</p><p><b>Upvotes:</b> 76</p><p><b>Summary:</b> Tool-integrated reasoning has emerged as a key focus for enabling agentic applications. Among these, DeepResearch Agents have gained significant attention for their strong performance on complex, open-ended information-seeking tasks. We introduce Fathom-DeepResearch, an agentic system composed of two specialized models. The first is Fathom-Search-4B, a DeepSearch model trained from Qwen3-4B and optimized for evidence-based investigation through live web search and targeted webpage querying. Its training combines three advances: (i) DUETQA, a 5K-sample dataset generated via multi-agent self-play that enforces strict web-search dependence and heterogeneous source grounding; (ii) RAPO, a zero-overhead extension of GRPO that stabilizes multi-turn Reinforcement Learning with Verifiable Rewards through curriculum pruning, reward-aware advantage scaling, and per-prompt replay buffers; and (iii) a steerable step-level reward that classifies each tool call by cognitive behavior and marginal utility, enabling explicit control over search trajectory breadth, depth, and horizon. These improvements enable reliable extension of tool-calling beyond 20 calls when warranted. The second is Fathom-Synthesizer-4B, trained from Qwen3-4B, which converts multi-turn DeepSearch traces into structured, citation-dense DeepResearch Reports for comprehensive synthesis. Evaluated on DeepSearch benchmarks (SimpleQA, FRAMES, WebWalker, Seal0, MuSiQue) and DeepResearch-Bench, the system achieves state-of-the-art performance in the open-weights category while demonstrating strong generalization to diverse reasoning tasks including HLE, AIME-25, GPQA-Diamond, and MedQA.</p> + https://arxiv.org/abs/2509.24107 + Sun, 28 Sep 2025 22:58:11 +0000 - LLaVA-Critic-R1: Your Critic Model is Secretly a Strong Policy Model - https://arxiv.org/abs/2509.00676 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.00676.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiyao Wang, Chunyuan Li, Jianwei Yang, Kai Zhang, Bo Liu, Tianyi Xiong, Furong Huang</p><p><b>Upvotes:</b> 83</p><p><b>Summary:</b> In vision-language modeling, critic models are typically trained to evaluate outputs -- assigning scalar scores or pairwise preferences -- rather than to generate responses. This separation from policy models, which produce the responses, is so entrenched that critics are rarely considered for direct policy use. In this work, we challenge this convention. We propose to reorganize preference-labeled critic datasets into verifiable training signals and perform reinforcement learning directly on a base generative model, producing LLaVA-Critic-R1, a multimodal critic trained to optimize preference judgments while retaining full generation ability. Surprisingly, LLaVA-Critic-R1 emerges not only as a top-performing critic but also as a competitive policy model -- matching or surpassing specialized reasoning VLMs trained with in-domain data across 26 visual reasoning and understanding benchmarks, with an average gain of +5.7% over its base model (Qwen-2.5-VL-7B). Extending this approach to existing strong reasoning VLMs yields LLaVA-Critic-R1+, which further advances policy performance without sacrificing critic quality, achieving a SoTA performance of 71.9 on MMMU at the 7B scale. Finally, we show that the enhanced critic ability benefits inference: applying self-critique at test time yields an average +13.8% improvement on five representative reasoning tasks without additional training. Our results reveal that RL training on critic data can produce a unified model excelling at both evaluation and generation, offering a simple path toward scalable, self-improving multimodal systems.</p> - https://arxiv.org/abs/2509.00676 - Sun, 31 Aug 2025 03:08:02 +0000 + DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Monte Carlo Tree Search + https://arxiv.org/abs/2509.25454 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.25454.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fang Wu, Weihao Xuan, Heli Qi, Ximing Lu, Aaron Tu, Li Erran Li, Yejin Choi</p><p><b>Upvotes:</b> 136</p><p><b>Summary:</b> Although RLVR has become an essential component for developing advanced reasoning skills in LLMs, contemporary studies have documented training plateaus that emerge following thousands of optimization steps, demonstrating notable decreases in performance gains despite increased computational investment. This limitation stems from the sparse exploration patterns inherent in current RLVR practices, where models rely on limited rollouts that often miss critical reasoning paths and fail to provide systematic coverage of the solution space. We present DeepSearch, a framework that integrates Monte Carlo Tree Search directly into RLVR training. In contrast to existing methods that rely on tree search only at inference, DeepSearch embeds structured search into the training loop, enabling systematic exploration and fine-grained credit assignment across reasoning steps. Through training-time exploration, DeepSearch addresses the fundamental bottleneck of insufficient exploration, which leads to diminishing performance improvements over prolonged training steps. Our contributions include: (1) a global frontier selection strategy that prioritizes promising nodes across the search tree, (2) selection with entropy-based guidance that identifies confident paths for supervision, and (3) adaptive replay buffer training with solution caching for efficiency. Experiments on mathematical reasoning benchmarks show that DeepSearch achieves 62.95% average accuracy and establishes a new state-of-the-art for 1.5B reasoning models - using 5.7x fewer GPU hours than extended training approaches. These results highlight the importance of strategic exploration over brute-force scaling and demonstrate the promise of algorithmic innovation for advancing RLVR methodologies. DeepSearch establishes a new direction for scaling reasoning capabilities through systematic search rather than prolonged computation.</p> + https://arxiv.org/abs/2509.25454 + Mon, 29 Sep 2025 20:00:29 +0000 - VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use - https://arxiv.org/abs/2509.01055 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.01055.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dongfu Jiang, Yi Lu, Zhuofeng Li, Zhiheng Lyu, Ping Nie, Haozhe Wang, Alex Su, Hui Chen, Kai Zou, Chao Du, Tianyu Pang, Wenhu Chen</p><p><b>Upvotes:</b> 70</p><p><b>Summary:</b> Reinforcement Learning with Verifiable Rewards (RLVR) has demonstrated success in enhancing LLM reasoning capabilities, but remains limited to single-turn interactions without tool integration. While recent Agentic Reinforcement Learning with Tool use (ARLT) approaches have emerged to address multi-turn tool interactions, existing works develop task-specific codebases that suffer from fragmentation, synchronous execution bottlenecks, and limited extensibility across domains. These inefficiencies hinder broader community adoption and algorithmic innovation. We introduce VerlTool, a unified and modular framework that addresses these limitations through systematic design principles. VerlTool provides four key contributions: (1) upstream alignment with VeRL ensuring compatibility and simplified maintenance, (2) unified tool management via standardized APIs supporting diverse modalities including code execution, search, SQL databases, and vision processing, (3) asynchronous rollout execution achieving near 2times speedup by eliminating synchronization bottlenecks, and (4) comprehensive evaluation demonstrating competitive performance across 6 ARLT domains. Our framework formalizes ARLT as multi-turn trajectories with multi-modal observation tokens (text/image/video), extending beyond single-turn RLVR paradigms. We train and evaluate models on mathematical reasoning, knowledge QA, SQL generation, visual reasoning, web search, and software engineering tasks, achieving results comparable to specialized systems while providing unified training infrastructure. The modular plugin architecture enables rapid tool integration requiring only lightweight Python definitions, significantly reducing development overhead and providing a scalable foundation for tool-augmented RL research. Our code is open-sourced at https://github.com/TIGER-AI-Lab/verl-tool.</p> - https://arxiv.org/abs/2509.01055 - Mon, 01 Sep 2025 01:45:18 +0000 + Vision-Zero: Scalable VLM Self-Improvement via Strategic Gamified Self-Play + https://arxiv.org/abs/2509.25541 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.25541.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qinsi Wang, Bo Liu, Tianyi Zhou, Jing Shi, Yueqian Lin, Yiran Chen, Hai Helen Li, Kun Wan, Wentian Zhao</p><p><b>Upvotes:</b> 137</p><p><b>Summary:</b> Although reinforcement learning (RL) can effectively enhance the reasoning capabilities of vision-language models (VLMs), current methods remain heavily dependent on labor-intensive datasets that require extensive manual construction and verification, leading to extremely high training costs and consequently constraining the practical deployment of VLMs. To address this challenge, we propose Vision-Zero, a domain-agnostic framework enabling VLM self-improvement through competitive visual games generated from arbitrary image pairs. Specifically, Vision-Zero encompasses three main attributes: (1) Strategic Self-Play Framework: Vision-Zero trains VLMs in "Who Is the Spy"-style games, where the models engage in strategic reasoning and actions across multiple roles. Through interactive gameplay, models autonomously generate their training data without human annotation. (2) Gameplay from Arbitrary Images: Unlike existing gamified frameworks, Vision-Zero can generate games from arbitrary images, thereby enhancing the model's reasoning ability across diverse domains and showing strong generalization to different tasks. We demonstrate this versatility using three distinct types of image datasets: CLEVR-based synthetic scenes, charts, and real-world images. (3) Sustainable Performance Gain: We introduce Iterative Self-Play Policy Optimization (Iterative-SPO), a novel training algorithm that alternates between Self-Play and reinforcement learning with verifiable rewards (RLVR), mitigating the performance plateau often seen in self-play-only training and achieving sustained long-term improvements. Despite using label-free data, Vision-Zero achieves state-of-the-art performance on reasoning, chart question answering, and vision-centric understanding tasks, surpassing other annotation-based methods. Models and code has been released at https://github.com/wangqinsi1/Vision-Zero.</p> + https://arxiv.org/abs/2509.25541 + Mon, 29 Sep 2025 21:55:55 +0000 - Robix: A Unified Model for Robot Interaction, Reasoning and Planning - https://arxiv.org/abs/2509.01106 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.01106.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Huang Fang, Mengxi Zhang, Heng Dong, Wei Li, Zixuan Wang, Qifeng Zhang, Xueyun Tian, Yucheng Hu, Hang Li</p><p><b>Upvotes:</b> 47</p><p><b>Summary:</b> We introduce Robix, a unified model that integrates robot reasoning, task planning, and natural language interaction within a single vision-language architecture. Acting as the high-level cognitive layer in a hierarchical robot system, Robix dynamically generates atomic commands for the low-level controller and verbal responses for human interaction, enabling robots to follow complex instructions, plan long-horizon tasks, and interact naturally with human within an end-to-end framework. Robix further introduces novel capabilities such as proactive dialogue, real-time interruption handling, and context-aware commonsense reasoning during task execution. At its core, Robix leverages chain-of-thought reasoning and adopts a three-stage training strategy: (1) continued pretraining to enhance foundational embodied reasoning abilities including 3D spatial understanding, visual grounding, and task-centric reasoning; (2) supervised finetuning to model human-robot interaction and task planning as a unified reasoning-action sequence; and (3) reinforcement learning to improve reasoning-action consistency and long-horizon task coherence. Extensive experiments demonstrate that Robix outperforms both open-source and commercial baselines (e.g., GPT-4o and Gemini 2.5 Pro) in interactive task execution, demonstrating strong generalization across diverse instruction types (e.g., open-ended, multi-stage, constrained, invalid, and interrupted) and various user-involved tasks such as table bussing, grocery shopping, and dietary filtering.</p> - https://arxiv.org/abs/2509.01106 - Mon, 01 Sep 2025 03:53:47 +0000 + TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning + https://arxiv.org/abs/2509.25760 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.25760.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhepei Wei, Xiao Yang, Kai Sun, Jiaqi Wang, Rulin Shao, Sean Chen, Mohammad Kachuee, Teja Gollapudi, Tony Liao, Nicolas Scheffer, Rakesh Wanga, Anuj Kumar, Yu Meng, Wen-tau Yih, Xin Luna Dong</p><p><b>Upvotes:</b> 53</p><p><b>Summary:</b> While large language models (LLMs) have demonstrated strong performance on factoid question answering, they are still prone to hallucination and untruthful responses, particularly when tasks demand information outside their parametric knowledge. Indeed, truthfulness requires more than accuracy -- models must also recognize uncertainty and abstain when unsure to avoid hallucinations. This presents a fundamental challenge for existing methods: approaches that optimize for accuracy often amplify hallucinations, while those that encourage abstention can become overly conservative, sacrificing correct answers. Both extremes ultimately compromise truthfulness. In this work, we present TruthRL, a general reinforcement learning (RL) framework that directly optimizes the truthfulness of LLMs. Specifically, we implement TruthRL using GRPO with a simple yet effective ternary reward that distinguishes correct answers, hallucinations, and abstentions. It incentivizes models to reduce hallucinations not only by providing correct responses, but also by enabling abstention when uncertain, thereby improving truthfulness. Extensive experiments across four knowledge-intensive benchmarks show that, compared to vanilla RL, TruthRL significantly reduces hallucinations by 28.9% and improves truthfulness by 21.1%, with consistent gains across various backbone models (e.g., Qwen, Llama) under both retrieval and non-retrieval setups. In-depth ablation study demonstrates that vanilla accuracy-driven methods, such as supervised fine-tuning or RL with a binary reward, struggle to balance factual correctness and uncertainty. In contrast, our proposed truthfulness-driven TruthRL achieves strong performance in both accuracy and truthfulness, underscoring the importance of learning objective design for developing truthful LLMs.</p> + https://arxiv.org/abs/2509.25760 + Tue, 30 Sep 2025 04:25:17 +0000 - POINTS-Reader: Distillation-Free Adaptation of Vision-Language Models for Document Conversion - https://arxiv.org/abs/2509.01215 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.01215.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuan Liu, Zhongyin Zhao, Le Tian, Haicheng Wang, Xubing Ye, Yangxiu You, Zilin Yu, Chuhan Wu, Xiao Zhou, Yang Yu, Jie Zhou</p><p><b>Upvotes:</b> 50</p><p><b>Summary:</b> High-quality labeled data is essential for training accurate document conversion models, particularly in domains with complex formats such as tables, formulas, and multi-column text. However, manual annotation is both costly and time-consuming, while automatic labeling using existing models often lacks accuracy in handling such challenging scenarios. Consequently, training student models by distilling outputs from teacher models can significantly limit their performance in real-world applications. In this paper, we propose a fully automated, distillation-free framework comprising two stages for constructing high-quality document extraction datasets and models capable of handling diverse document formats and layouts. In the first stage, we introduce a method for generating large-scale, diverse synthetic data, which enables a model to extract key elements in a unified format with strong initial performance. In the second stage, we present a self-improvement approach that further adapts the model, initially trained on synthetic data, to real-world documents. Specifically, we first use the fine-tuned model to annotate real documents, then apply a suite of filtering strategies to verify annotation quality, and finally retrain the model on the verified dataset. By iteratively repeating this process, we progressively enhance both the model's conversion capabilities and the quality of the generated data. We train a public POINTS-1.5 model to obtain POINTS-Reader, which surpasses many existing public and proprietary models of comparable or larger size. Our model is available at https://github.com/Tencent/POINTS-Reader.</p> - https://arxiv.org/abs/2509.01215 - Mon, 01 Sep 2025 07:54:18 +0000 + More Thought, Less Accuracy? On the Dual Nature of Reasoning in Vision-Language Models + https://arxiv.org/abs/2509.25848 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.25848.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xinyu Tian, Shu Zou, Zhaoyuan Yang, Mengqi He, Fabian Waschkowski, Lukas Wesemann, Peter Tu, Jing Zhang</p><p><b>Upvotes:</b> 78</p><p><b>Summary:</b> Reasoning has emerged as a pivotal capability in Large Language Models (LLMs). Through Reinforcement Learning (RL), typically Group Relative Policy Optimization (GRPO), these models are able to solve complex tasks such as mathematics and code generation. Building on these advances, recent research has sought to extend reasoning to Vision-Language Models (VLMs), yielding promising results across diverse visual tasks. Despite this progress, our study uncovers the dual nature of multimodal reasoning: while it substantially enhances logical inference and facilitates performance on challenging problems, it may gradually impair perceptual grounding, leading to recognition failures on otherwise basic visual questions. Through further analysis, we attribute this phenomenon to visual forgetting, wherein prolonged reasoning causes the model to increasingly disregard visual input. To address this, we propose Vision-Anchored Policy Optimization (VAPO), a simple yet effective method that explicitly steers the reasoning process toward visually grounded trajectories. Our result model, VAPO-Thinker-7B, significantly strengthens the model's reliance on visual information and achieves new state-of-the-art results on a wide range of established benchmarks. Project page: https://xytian1008.github.io/VAPO/</p> + https://arxiv.org/abs/2509.25848 + Tue, 30 Sep 2025 06:37:47 +0000 - Reasoning Vectors: Transferring Chain-of-Thought Capabilities via Task Arithmetic - https://arxiv.org/abs/2509.01363 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.01363.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mohammad Zbeeb, Hasan Abed Al Kader Hammoud, Bernard Ghanem</p><p><b>Upvotes:</b> 57</p><p><b>Summary:</b> Large language models often require costly optimization, such as reinforcement learning, to master complex reasoning tasks. This work demonstrates that reasoning ability, once learned, can be extracted and transferred between models as a compact task vector. We source two publicly available, identically initialized Qwen2.5 models, one fine-tuned with supervised fine-tuning (SFT) and the other with group relative policy optimization (GRPO) on the same dataset. From these, we extract a reasoning vector: v_{reason} = theta_{GRPO} - theta_{SFT}. We hypothesize that this vector captures the reasoning capability instilled by reinforcement learning while factoring out shared knowledge from the SFT process. When added to compatible instruction-tuned models through simple arithmetic, this vector consistently improves performance across diverse reasoning benchmarks: GSM8K (+4.9%), HumanEval (+4.3%), SciQ (+1.7%), and BigBenchHard (+12.3% for the 1.5B model). The performance improvements persist under adversarial conditions. Conversely, subtracting the vector causes significant performance degradation (-11.8% on GSM8K), demonstrating the vector's strong contribution to the model's reasoning abilities. This work shows how reasoning capabilities, typically developed through expensive training, can be extracted from existing open-source models and reused through simple tensor arithmetic, offering a practical way to enhance models by recycling prior computational investments.</p> - https://arxiv.org/abs/2509.01363 - Mon, 01 Sep 2025 11:04:51 +0000 + Knapsack RL: Unlocking Exploration of LLMs via Optimizing Budget Allocation + https://arxiv.org/abs/2509.25849 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.25849.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ziniu Li, Congliang Chen, Tianyun Yang, Tian Ding, Ruoyu Sun, Ge Zhang, Wenhao Huang, Zhi-Quan Luo</p><p><b>Upvotes:</b> 47</p><p><b>Summary:</b> Large Language Models (LLMs) can self-improve through reinforcement learning, where they generate trajectories to explore and discover better solutions. However, this exploration process is computationally expensive, often forcing current methods to assign limited exploration budgets to each task. This uniform allocation creates problematic edge cases: easy tasks consistently succeed while difficult tasks consistently fail, both producing zero gradients during training updates for the widely used Group Relative Policy Optimization (GRPO). We address this problem from the lens of exploration budget allocation. Viewing each task's exploration as an "item" with a distinct "value" and "cost", we establish a connection to the classical knapsack problem. This formulation allows us to derive an optimal assignment rule that adaptively distributes resources based on the model's current learning status. When applied to GRPO, our method increases the effective ratio of non-zero policy gradients by 20-40% during training. Acting as a computational "free lunch", our approach could reallocate exploration budgets from tasks where learning is saturated to those where it is most impactful. This enables significantly larger budgets (e.g., 93 rollouts) for especially challenging problems, which would be computationally prohibitive under a uniform allocation. These improvements translate to meaningful gains on mathematical reasoning benchmarks, with average improvements of 2-4 points and peak gains of 9 points on specific tasks. Notably, achieving comparable performance with traditional homogeneous allocation would require about 2x the computational resources.</p> + https://arxiv.org/abs/2509.25849 + Tue, 30 Sep 2025 06:41:57 +0000 - DeepResearch Arena: The First Exam of LLMs' Research Abilities via Seminar-Grounded Tasks - https://arxiv.org/abs/2509.01396 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.01396.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haiyuan Wan, Chen Yang, Junchi Yu, Meiqi Tu, Jiaxuan Lu, Di Yu, Jianbao Cao, Ben Gao, Jiaqing Xie, Aoran Wang, Wenlong Zhang, Philip Torr, Dongzhan Zhou</p><p><b>Upvotes:</b> 56</p><p><b>Summary:</b> Deep research agents have attracted growing attention for their potential to orchestrate multi-stage research workflows, spanning literature synthesis, methodological design, and empirical verification. Despite these strides, evaluating their research capability faithfully is rather challenging due to the difficulty of collecting frontier research questions that genuinely capture researchers' attention and intellectual curiosity. To address this gap, we introduce DeepResearch Arena, a benchmark grounded in academic seminars that capture rich expert discourse and interaction, better reflecting real-world research environments and reducing the risk of data leakage. To automatically construct DeepResearch Arena, we propose a Multi-Agent Hierarchical Task Generation (MAHTG) system that extracts research-worthy inspirations from seminar transcripts. The MAHTG system further translates research-worthy inspirations into high-quality research tasks, ensuring the traceability of research task formulation while filtering noise. With the MAHTG system, we curate DeepResearch Arena with over 10,000 high-quality research tasks from over 200 academic seminars, spanning 12 disciplines, such as literature, history, and science. Our extensive evaluation shows that DeepResearch Arena presents substantial challenges for current state-of-the-art agents, with clear performance gaps observed across different models.</p> - https://arxiv.org/abs/2509.01396 - Mon, 01 Sep 2025 11:42:47 +0000 + Fast-dLLM v2: Efficient Block-Diffusion LLM + https://arxiv.org/abs/2509.26328 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.26328.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chengyue Wu, Hao Zhang, Shuchen Xue, Shizhe Diao, Yonggan Fu, Zhijian Liu, Pavlo Molchanov, Ping Luo, Song Han, Enze Xie</p><p><b>Upvotes:</b> 49</p><p><b>Summary:</b> Autoregressive (AR) large language models (LLMs) have achieved remarkable performance across a wide range of natural language tasks, yet their inherent sequential decoding limits inference efficiency. In this work, we propose Fast-dLLM v2, a carefully designed block diffusion language model (dLLM) that efficiently adapts pretrained AR models into dLLMs for parallel text generation, requiring only approximately 1B tokens of fine-tuning. This represents a 500x reduction in training data compared to full-attention diffusion LLMs such as Dream (580B tokens), while preserving the original model's performance. Our approach introduces a novel training recipe that combines a block diffusion mechanism with a complementary attention mask, enabling blockwise bidirectional context modeling without sacrificing AR training objectives. To further accelerate decoding, we design a hierarchical caching mechanism: a block-level cache that stores historical context representations across blocks, and a sub-block cache that enables efficient parallel generation within partially decoded blocks. Coupled with our parallel decoding pipeline, Fast-dLLM v2 achieves up to 2.5x speedup over standard AR decoding without compromising generation quality. Extensive experiments across diverse benchmarks demonstrate that Fast-dLLM v2 matches or surpasses AR baselines in accuracy, while delivering state-of-the-art efficiency among dLLMs - marking a significant step toward the practical deployment of fast and accurate LLMs. Code and model will be publicly released.</p> + https://arxiv.org/abs/2509.26328 + Tue, 30 Sep 2025 14:40:18 +0000 - Kwai Keye-VL 1.5 Technical Report - https://arxiv.org/abs/2509.01563 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.01563.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Biao Yang, Bin Wen, Boyang Ding, Changyi Liu, Chenglong Chu, Chengru Song, Chongling Rao, Chuan Yi, Da Li, Dunju Zang, Fan Yang, Guorui Zhou, Guowang Zhang, Han Shen, Hao Peng, Haojie Ding, Hao Wang, Hengrui Ju, Jiaming Huang, Jiangxia Cao, Jiankang Chen, Jingyun Hua, Kaibing Chen, Kaiyu Jiang, Kaiyu Tang, Kun Gai, Muhao Wei, Qiang Wang, Ruitao Wang, Sen Na, Shengnan Zhang, Siyang Mao, Sui Huang, Tianke Zhang, Tingting Gao, Wei Chen, Wei Yuan, Xiangyu Wu, Xiao Hu, Xingyu Lu, Yi-Fan Zhang, Yiping Yang, Yulong Chen, Zeyi Lu, Zhenhua Wu, Zhixin Ling, Zhuoran Yang, Ziming Li, Di Xu, Haixuan Gao, Hang Li, Jing Wang, Lejian Ren, Qigen Hu, Qianqian Wang, Shiyao Wang, Xinchen Luo, Yan Li, Yuhang Hu, Zixing Zhang</p><p><b>Upvotes:</b> 36</p><p><b>Summary:</b> In recent years, the development of Large Language Models (LLMs) has significantly advanced, extending their capabilities to multimodal tasks through Multimodal Large Language Models (MLLMs). However, video understanding remains a challenging area due to the dynamic and information-dense nature of videos. Existing models struggle with the trade-off between spatial resolution and temporal coverage when processing video content. We present Keye-VL-1.5, which addresses fundamental challenges in video comprehension through three key innovations. First, we introduce a novel Slow-Fast video encoding strategy that dynamically allocates computational resources based on inter-frame similarity, processing key frames with significant visual changes at higher resolution (Slow pathway) while handling relatively static frames with increased temporal coverage at lower resolution (Fast pathway). Second, we implement a progressive four-stage pre-training methodology that systematically extends the model's context length from 8K to 128K tokens, enabling processing of longer videos and more complex visual content. Third, we develop a comprehensive post-training pipeline focusing on reasoning enhancement and human preference alignment, incorporating a 5-step chain-of-thought data construction process, iterative GSPO-based reinforcement learning with progressive prompt hinting for difficult cases, and alignment training. Through extensive evaluation on public benchmarks and rigorous internal human assessment, Keye-VL-1.5 demonstrates significant improvements over existing models, particularly excelling in video understanding tasks while maintaining competitive performance on general multimodal benchmarks.</p> - https://arxiv.org/abs/2509.01563 - Mon, 01 Sep 2025 15:46:58 +0000 + The Dragon Hatchling: The Missing Link between the Transformer and Models of the Brain + https://arxiv.org/abs/2509.26507 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.26507.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Adrian Kosowski, Przemysław Uznański, Jan Chorowski, Zuzanna Stamirowska, Michał Bartoszkiewicz</p><p><b>Upvotes:</b> 518</p><p><b>Summary:</b> The relationship between computing systems and the brain has served as motivation for pioneering theoreticians since John von Neumann and Alan Turing. Uniform, scale-free biological networks, such as the brain, have powerful properties, including generalizing over time, which is the main barrier for Machine Learning on the path to Universal Reasoning Models. We introduce `Dragon Hatchling' (BDH), a new Large Language Model architecture based on a scale-free biologically inspired network of \n locally-interacting neuron particles. BDH couples strong theoretical foundations and inherent interpretability without sacrificing Transformer-like performance. BDH is a practical, performant state-of-the-art attention-based state space sequence learning architecture. In addition to being a graph model, BDH admits a GPU-friendly formulation. It exhibits Transformer-like scaling laws: empirically BDH rivals GPT2 performance on language and translation tasks, at the same number of parameters (10M to 1B), for the same training data. BDH can be represented as a brain model. The working memory of BDH during inference entirely relies on synaptic plasticity with Hebbian learning using spiking neurons. We confirm empirically that specific, individual synapses strengthen connection whenever BDH hears or reasons about a specific concept while processing language inputs. The neuron interaction network of BDH is a graph of high modularity with heavy-tailed degree distribution. The BDH model is biologically plausible, explaining one possible mechanism which human neurons could use to achieve speech. BDH is designed for interpretability. Activation vectors of BDH are sparse and positive. We demonstrate monosemanticity in BDH on language tasks. Interpretability of state, which goes beyond interpretability of neurons and model parameters, is an inherent feature of the BDH architecture.</p> + https://arxiv.org/abs/2509.26507 + Tue, 30 Sep 2025 16:49:01 +0000 - OpenVision 2: A Family of Generative Pretrained Visual Encoders for Multimodal Learning - https://arxiv.org/abs/2509.01644 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.01644.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yanqing Liu, Xianhang Li, Letian Zhang, Zirui Wang, Zeyu Zheng, Yuyin Zhou, Cihang Xie</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> This paper provides a simplification on OpenVision's architecture and loss design for enhancing its training efficiency. Following the prior vision-language pretraining works CapPa and AIMv2, as well as modern multimodal designs like LLaVA, our changes are straightforward: we remove the text encoder (and therefore the contrastive loss), retaining only the captioning loss as a purely generative training signal. We name this new version OpenVision 2. The initial results are promising: despite this simplification, OpenVision 2 competitively matches the original model's performance on a broad set of multimodal benchmarks while substantially cutting both training time and memory consumption. For example, with ViT-L/14, it reduces training time by about 1.5x (from 83h to 57h), and memory usage by about 1.8x (from 24.5GB to 13.8GB, equivalently allowing the maximum batch size to grow from 2k to 8k). This superior training efficiency also allows us to scale far beyond the largest vision encoder used in OpenVision, reaching more than 1 billion parameters. We hold a strong belief that this lightweight, generative-only paradigm is compelling for future vision encoder development in multimodal foundation models.</p> - https://arxiv.org/abs/2509.01644 - Mon, 01 Sep 2025 17:38:21 +0000 + VLA-RFT: Vision-Language-Action Reinforcement Fine-tuning with Verified Rewards in World Simulators + https://arxiv.org/abs/2510.00406 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.00406.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hengtao Li, Pengxiang Ding, Runze Suo, Yihao Wang, Zirui Ge, Dongyuan Zang, Kexian Yu, Mingyang Sun, Hongyin Zhang, Donglin Wang, Weihua Su</p><p><b>Upvotes:</b> 63</p><p><b>Summary:</b> Vision-Language-Action (VLA) models enable embodied decision-making but rely heavily on imitation learning, leading to compounding errors and poor robustness under distribution shift. Reinforcement learning (RL) can mitigate these issues yet typically demands costly real-world interactions or suffers from sim-to-real gaps. We introduce VLA-RFT, a reinforcement fine-tuning framework that leverages a data-driven world model as a controllable simulator. Trained from real interaction data, the simulator predicts future visual observations conditioned on actions, allowing policy rollouts with dense, trajectory-level rewards derived from goal-achieving references. This design delivers an efficient and action-aligned learning signal, drastically lowering sample requirements. With fewer than 400 fine-tuning steps, VLA-RFT surpasses strong supervised baselines and achieves greater efficiency than simulator-based RL. Moreover, it exhibits strong robustness under perturbed conditions, sustaining stable task execution. Our results establish world-model-based RFT as a practical post-training paradigm to enhance the generalization and robustness of VLA models. For more details, please refer to https://vla-rft.github.io/.</p> + https://arxiv.org/abs/2510.00406 + Wed, 01 Oct 2025 01:33:10 +0000 - Baichuan-M2: Scaling Medical Capability with Large Verifier System - https://arxiv.org/abs/2509.02208 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.02208.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Baichuan-M2 Team, Chengfeng Dou, Chong Liu, Fan Yang, Fei Li, Jiyuan Jia, Mingyang Chen, Qiang Ju, Shuai Wang, Shunya Dang, Tianpeng Li, Xiangrong Zeng, Yijie Zhou, Chenzheng Zhu, Da Pan, Fei Deng, Guangwei Ai, Guosheng Dong, Hongda Zhang, Jinyang Tai, Jixiang Hong, Kai Lu, Linzhuang Sun, Peidong Guo, Qian Ma, Rihui Xin, Shihui Yang, Shusen Zhang, Yichuan Mo, Zheng Liang, Zhishou Zhang, Hengfu Cui, Zuyi Zhu, Xiaochuan Wang</p><p><b>Upvotes:</b> 39</p><p><b>Summary:</b> As large language models (LLMs) advance in conversational and reasoning capabilities, their practical application in healthcare has become a critical research focus. However, there is a notable gap between the performance of medical LLMs on static benchmarks such as USMLE and their utility in real-world clinical decision-making. This discrepancy arises because traditional exams fail to capture the dynamic, interactive nature of medical consultations. To address this challenge, we introduce a novel dynamic verification framework that moves beyond static answer verifier, establishing a large-scale, high-fidelity interactive reinforcement learning system. Our framework comprises two key components: a Patient Simulator that creates realistic clinical environments using de-identified medical records, and a Clinical Rubrics Generator that dynamically produces multi-dimensional evaluation metrics. Building on this foundation, we develop Baichuan-M2, a 32B-parameter medical augmented reasoning model trained through a multi-stage reinforcement learning strategy with an improved Group Relative Policy Optimization (GRPO) algorithm. Evaluated on HealthBench, Baichuan-M2 outperforms all other open-source models and most advanced closed-source counterparts, achieving a score above 32 on the challenging HealthBench Hard benchmark-previously exceeded only by GPT-5. Our work demonstrates that robust dynamic verifier system is essential for aligning LLM capabilities with practical clinical applications, establishing a new Pareto front in the performance-parameter trade-off for medical AI deployment.</p> - https://arxiv.org/abs/2509.02208 - Tue, 02 Sep 2025 11:23:35 +0000 + LongCodeZip: Compress Long Context for Code Language Models + https://arxiv.org/abs/2510.00446 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.00446.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuling Shi, Yichun Qian, Hongyu Zhang, Beijun Shen, Xiaodong Gu</p><p><b>Upvotes:</b> 107</p><p><b>Summary:</b> Code generation under long contexts is becoming increasingly critical as Large Language Models (LLMs) are required to reason over extensive information in the codebase. While recent advances enable code LLMs to process long inputs, high API costs and generation latency remain substantial bottlenecks. Existing context pruning techniques, such as LLMLingua, achieve promising results for general text but overlook code-specific structures and dependencies, leading to suboptimal performance in programming tasks. In this paper, we propose LongCodeZip, a novel plug-and-play code compression framework designed specifically for code LLMs. LongCodeZip employs a dual-stage strategy: (1) coarse-grained compression, which identifies and ranks function-level chunks using conditional perplexity with respect to the instruction, retaining only the most relevant functions; and (2) fine-grained compression, which segments retained functions into blocks based on perplexity and selects an optimal subset under an adaptive token budget to maximize relevance. Evaluations across multiple tasks, including code completion, summarization, and question answering, show that LongCodeZip consistently outperforms baseline methods, achieving up to a 5.6x compression ratio without degrading task performance. By effectively reducing context size while preserving essential information, LongCodeZip enables LLMs to better scale to real-world, large-scale code scenarios, advancing the efficiency and capability of code intelligence applications.</p> + https://arxiv.org/abs/2510.00446 + Wed, 01 Oct 2025 02:54:57 +0000 - SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning - https://arxiv.org/abs/2509.02479 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.02479.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhenghai Xue, Longtao Zheng, Qian Liu, Yingru Li, Xiaosen Zheng, Zejun Ma, Bo An</p><p><b>Upvotes:</b> 83</p><p><b>Summary:</b> Large Language Models (LLMs) can significantly improve their reasoning capabilities by interacting with external tools, a paradigm known as Tool-Integrated Reasoning (TIR). However, extending TIR to multi-turn scenarios using Reinforcement Learning (RL) is often hindered by training instability and performance collapse. We identify that such instability is primarily caused by a distributional drift from external tool feedback, leading to the generation of low-probability tokens. This issue compounds over successive turns, causing catastrophic gradient norm explosions that derail the training process. To address this challenge, we introduce SimpleTIR , a plug-and-play algorithm that stabilizes multi-turn TIR training. Its core strategy is to identify and filter out trajectories containing void turns, i.e., turns that yield neither a code block nor a final answer. By removing these problematic trajectories from the policy update, SimpleTIR effectively blocks the harmful, high-magnitude gradients, thus stabilizing the learning dynamics. Extensive experiments show that SimpleTIR achieves state-of-the-art performance on challenging math reasoning benchmarks, notably elevating the AIME24 score from a text-only baseline of 22.1 to 50.5 when starting from the Qwen2.5-7B base model. Furthermore, by avoiding the constraints of supervised fine-tuning, SimpleTIR encourages the model to discover diverse and sophisticated reasoning patterns, such as self-correction and cross-validation.</p> - https://arxiv.org/abs/2509.02479 - Tue, 02 Sep 2025 16:30:19 +0000 + GEM: A Gym for Agentic LLMs + https://arxiv.org/abs/2510.01051 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.01051.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zichen Liu, Anya Sims, Keyu Duan, Changyu Chen, Simon Yu, Xiangxin Zhou, Haotian Xu, Shaopan Xiong, Bo Liu, Chenmien Tan, Chuen Yang Beh, Weixun Wang, Hao Zhu, Weiyan Shi, Diyi Yang, Michael Shieh, Yee Whye Teh, Wee Sun Lee, Min Lin</p><p><b>Upvotes:</b> 87</p><p><b>Summary:</b> The training paradigm for large language models (LLMs) is moving from static datasets to experience-based learning, where agents acquire skills via interacting with complex environments. To facilitate this transition we introduce GEM (General Experience Maker), an open-source environment simulator designed for the age of LLMs. Analogous to OpenAI-Gym for traditional reinforcement learning (RL), GEM provides a standardized framework for the environment-agent interface, including asynchronous vectorized execution for high throughput, and flexible wrappers for easy extensibility. GEM also features a diverse suite of environments, robust integrated tools, and single-file example scripts demonstrating using GEM with five popular RL training frameworks. Along with this, we also provide a set of baselines across 24 environments using REINFORCE with Return Batch Normalization (ReBN), which -- unlike GRPO -- is compatible with the full RL setting of dense per-turn rewards and offers better credit assignment. We further conduct apple-to-apple benchmarking of PPO, GRPO and REINFORCE in both single- and multi-turn settings using GEM to shed light on the algorithmic designs. Lastly, GEM also functions as a convenient evaluation toolkit besides a training environment. We hope this framework can help accelerate future agentic LLM research.</p> + https://arxiv.org/abs/2510.01051 + Wed, 01 Oct 2025 15:55:57 +0000 - UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning - https://arxiv.org/abs/2509.02544 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.02544.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haoming Wang, Haoyang Zou, Huatong Song, Jiazhan Feng, Junjie Fang, Junting Lu, Longxiang Liu, Qinyu Luo, Shihao Liang, Shijue Huang, Wanjun Zhong, Yining Ye, Yujia Qin, Yuwen Xiong, Yuxin Song, Zhiyong Wu, Bo Li, Chen Dun, Chong Liu, Fuxing Leng, Hanbin Wang, Hao Yu, Haobin Chen, Hongyi Guo, Jing Su, Jingjia Huang, Kai Shen, Kaiyu Shi, Lin Yan, Peiyao Zhao, Pengfei Liu, Qinghao Ye, Renjie Zheng, Wayne Xin Zhao, Wen Heng, Wenhao Huang, Wenqian Wang, Xiaobo Qin, Yi Lin, Youbin Wu, Zehui Chen, Zihao Wang, Baoquan Zhong, Xinchun Zhang, Xujing Li, Yuanfan Li, Zhongkai Zhao, Chengquan Jiang, Faming Wu, Haotian Zhou, Jinlin Pang, Li Han, Qianli Ma, Siyao Liu, Songhua Cai, Wenqi Fu, Xin Liu, Zhi Zhang, Bo Zhou, Guoliang Li, Jiajun Shi, Jiale Yang, Jie Tang, Li Li, Taoran Lu, Woyu Lin, Xiaokang Tong, Xinyao Li, Yichi Zhang, Yu Miao, Zhengxuan Jiang, Zili Li, Ziyuan Zhao, Chenxin Li, Dehua Ma, Feng Lin, Ge Zhang, Haihua Yang, Hangyu Guo, Hongda Zhu, Jiaheng Liu, Junda Du, Kai Cai, Kuanye Li, Lichen Yuan, Meilan Han, Minchao Wang, Shuyue Guo, Tianhao Cheng, Xiaobo Ma, Xiaojun Xiao, Xiaolong Huang, Xinjie Chen, Yidi Du, Yilin Chen, Yiwen Wang, Zhaojian Li, Zhenzhu Yang, Zhiyuan Zeng, Chaolin Jin, Chen Li, Hao Chen, Haoli Chen, Jian Chen, Qinghao Zhao, Guang Shi</p><p><b>Upvotes:</b> 120</p><p><b>Summary:</b> The development of autonomous agents for graphical user interfaces (GUIs) presents major challenges in artificial intelligence. While recent advances in native agent models have shown promise by unifying perception, reasoning, action, and memory through end-to-end learning, open problems remain in data scalability, multi-turn reinforcement learning (RL), the limitations of GUI-only operation, and environment stability. In this technical report, we present UI-TARS-2, a native GUI-centered agent model that addresses these challenges through a systematic training methodology: a data flywheel for scalable data generation, a stabilized multi-turn RL framework, a hybrid GUI environment that integrates file systems and terminals, and a unified sandbox platform for large-scale rollouts. Empirical evaluation demonstrates that UI-TARS-2 achieves significant improvements over its predecessor UI-TARS-1.5. On GUI benchmarks, it reaches 88.2 on Online-Mind2Web, 47.5 on OSWorld, 50.6 on WindowsAgentArena, and 73.3 on AndroidWorld, outperforming strong baselines such as Claude and OpenAI agents. In game environments, it attains a mean normalized score of 59.8 across a 15-game suite-roughly 60% of human-level performance-and remains competitive with frontier proprietary models (e.g., OpenAI o3) on LMGame-Bench. Additionally, the model can generalize to long-horizon information-seeking tasks and software engineering benchmarks, highlighting its robustness across diverse agent tasks. Detailed analyses of training dynamics further provide insights into achieving stability and efficiency in large-scale agent RL. These results underscore UI-TARS-2's potential to advance the state of GUI agents and exhibit strong generalization to real-world interactive scenarios.</p> - https://arxiv.org/abs/2509.02544 - Tue, 02 Sep 2025 17:44:45 +0000 + Apriel-1.5-15b-Thinker + https://arxiv.org/abs/2510.01141 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.01141.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shruthan Radhakrishna, Aman Tiwari, Aanjaneya Shukla, Masoud Hashemi, Rishabh Maheshwary, Shiva Krishna Reddy Malay, Jash Mehta, Pulkit Pattnaik, Saloni Mittal, Khalil Slimi, Kelechi Ogueji, Akintunde Oladipo, Soham Parikh, Oluwanifemi Bamgbose, Toby Liang, Ahmed Masry, Khyati Mahajan, Sai Rajeswar Mudumba, Vikas Yadav, Sathwik Tejaswi Madhusudhan, Torsten Scholak, Sagar Davasam, Srinivas Sunkara, Nicholas Chapados</p><p><b>Upvotes:</b> 113</p><p><b>Summary:</b> We present Apriel-1.5-15B-Thinker, a 15-billion parameter open-weights multimodal reasoning model that achieves frontier-level performance through training design rather than sheer scale. Starting from Pixtral-12B, we apply a progressive three-stage methodology: (1) depth upscaling to expand reasoning capacity without pretraining from scratch, (2) staged continual pre-training that first develops foundational text and vision understanding, then enhances visual reasoning through targeted synthetic data generation addressing spatial structure, compositional understanding, and fine-grained perception, and (3) high-quality text-only supervised fine-tuning on curated instruction-response pairs with explicit reasoning traces spanning mathematics, coding, science, and tool use. Notably, our model achieves competitive results without reinforcement learning or preference optimization, isolating the contribution of our data-centric continual pre-training approach. On the Artificial Analysis Intelligence Index, Apriel-1.5-15B-Thinker attains a score of 52, matching DeepSeek-R1-0528 despite requiring significantly fewer computational resources. Across ten image benchmarks, its performance is on average within five points of Gemini-2.5-Flash and Claude Sonnet-3.7, a key achievement for a model operating within single-GPU deployment constraints. Our results demonstrate that thoughtful mid-training 2 design can close substantial capability gaps without massive scale, making frontier-level multimodal reasoning accessible to organizations with limited infrastructure. We release the model checkpoint, all training recipes, and evaluation protocols under the MIT license to to advance open-source research.</p> + https://arxiv.org/abs/2510.01141 + Wed, 01 Oct 2025 17:29:35 +0000 - The Landscape of Agentic Reinforcement Learning for LLMs: A Survey - https://arxiv.org/abs/2509.02547 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.02547.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Guibin Zhang, Hejia Geng, Xiaohang Yu, Zhenfei Yin, Zaibin Zhang, Zelin Tan, Heng Zhou, Zhongzhi Li, Xiangyuan Xue, Yijiang Li, Yifan Zhou, Yang Chen, Chen Zhang, Yutao Fan, Zihu Wang, Songtao Huang, Yue Liao, Hongru Wang, Mengyue Yang, Heng Ji, Michael Littman, Jun Wang, Shuicheng Yan, Philip Torr, Lei Bai</p><p><b>Upvotes:</b> 211</p><p><b>Summary:</b> The emergence of agentic reinforcement learning (Agentic RL) marks a paradigm shift from conventional reinforcement learning applied to large language models (LLM RL), reframing LLMs from passive sequence generators into autonomous, decision-making agents embedded in complex, dynamic worlds. This survey formalizes this conceptual shift by contrasting the degenerate single-step Markov Decision Processes (MDPs) of LLM-RL with the temporally extended, partially observable Markov decision processes (POMDPs) that define Agentic RL. Building on this foundation, we propose a comprehensive twofold taxonomy: one organized around core agentic capabilities, including planning, tool use, memory, reasoning, self-improvement, and perception, and the other around their applications across diverse task domains. Central to our thesis is that reinforcement learning serves as the critical mechanism for transforming these capabilities from static, heuristic modules into adaptive, robust agentic behavior. To support and accelerate future research, we consolidate the landscape of open-source environments, benchmarks, and frameworks into a practical compendium. By synthesizing over five hundred recent works, this survey charts the contours of this rapidly evolving field and highlights the opportunities and challenges that will shape the development of scalable, general-purpose AI agents.</p> - https://arxiv.org/abs/2509.02547 - Tue, 02 Sep 2025 17:46:26 +0000 + StockBench: Can LLM Agents Trade Stocks Profitably In Real-world Markets? + https://arxiv.org/abs/2510.02209 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.02209.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yanxu Chen, Zijun Yao, Yantao Liu, Jin Ye, Jianing Yu, Lei Hou, Juanzi Li</p><p><b>Upvotes:</b> 51</p><p><b>Summary:</b> Large language models (LLMs) have recently demonstrated strong capabilities as autonomous agents, showing promise in reasoning, tool use, and sequential decision-making. While prior benchmarks have evaluated LLM agents in domains such as software engineering and scientific discovery, the finance domain remains underexplored, despite its direct relevance to economic value and high-stakes decision-making. Existing financial benchmarks primarily test static knowledge through question answering, but they fall short of capturing the dynamic and iterative nature of trading. To address this gap, we introduce StockBench, a contamination-free benchmark designed to evaluate LLM agents in realistic, multi-month stock trading environments. Agents receive daily market signals -- including prices, fundamentals, and news -- and must make sequential buy, sell, or hold decisions. Performance is assessed using financial metrics such as cumulative return, maximum drawdown, and the Sortino ratio. Our evaluation of state-of-the-art proprietary (e.g., GPT-5, Claude-4) and open-weight (e.g., Qwen3, Kimi-K2, GLM-4.5) models shows that while most LLM agents struggle to outperform the simple buy-and-hold baseline, several models demonstrate the potential to deliver higher returns and manage risk more effectively. These findings highlight both the challenges and opportunities in developing LLM-powered financial agents, showing that excelling at static financial knowledge tasks does not necessarily translate into successful trading strategies. We release StockBench as an open-source resource to support reproducibility and advance future research in this domain.</p> + https://arxiv.org/abs/2510.02209 + Thu, 02 Oct 2025 16:54:57 +0000 - Drivel-ology: Challenging LLMs with Interpreting Nonsense with Depth - https://arxiv.org/abs/2509.03867 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.03867.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yang Wang, Chenghao Xiao, Chia-Yi Hsiao, Zi Yan Chang, Chi-Li Chen, Tyler Loakman, Chenghua Lin</p><p><b>Upvotes:</b> 206</p><p><b>Summary:</b> We introduce Drivelology, a unique linguistic phenomenon characterised as "nonsense with depth", utterances that are syntactically coherent yet pragmatically paradoxical, emotionally loaded, or rhetorically subversive. While such expressions may resemble surface-level nonsense, they encode implicit meaning requiring contextual inference, moral reasoning, or emotional interpretation. We find that current large language models (LLMs), despite excelling at many natural language processing (NLP) tasks, consistently fail to grasp the layered semantics of Drivelological text. To investigate this, we construct a small but diverse benchmark dataset of over 1,200 meticulously curated examples, with select instances in English, Mandarin, Spanish, French, Japanese, and Korean. Annotation was especially challenging: each of the examples required careful expert review to verify that it truly reflected Drivelological characteristics. The process involved multiple rounds of discussion and adjudication to address disagreements, highlighting the subtle and subjective nature of the Drivelology. We evaluate a range of LLMs on classification, generation, and reasoning tasks. Our results reveal clear limitations of LLMs: models often confuse Drivelology with shallow nonsense, produce incoherent justifications, or miss the implied rhetorical function altogether. These findings highlight a deeper representational gap in LLMs' pragmatic understanding and challenge the assumption that statistical fluency implies cognitive comprehension. We release our dataset and code to facilitate further research in modelling linguistic depth beyond surface-level coherence.</p> - https://arxiv.org/abs/2509.03867 - Thu, 04 Sep 2025 03:58:55 +0000 + ExGRPO: Learning to Reason from Experience + https://arxiv.org/abs/2510.02245 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.02245.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Runzhe Zhan, Yafu Li, Zhi Wang, Xiaoye Qu, Dongrui Liu, Jing Shao, Derek F. Wong, Yu Cheng</p><p><b>Upvotes:</b> 77</p><p><b>Summary:</b> Reinforcement learning from verifiable rewards (RLVR) is an emerging paradigm for improving the reasoning ability of large language models. However, standard on-policy training discards rollout experiences after a single update, leading to computational inefficiency and instability. While prior work on RL has highlighted the benefits of reusing past experience, the role of experience characteristics in shaping learning dynamics of large reasoning models remains underexplored. In this paper, we are the first to investigate what makes a reasoning experience valuable and identify rollout correctness and entropy as effective indicators of experience value. Based on these insights, we propose ExGRPO (Experiential Group Relative Policy Optimization), a framework that organizes and prioritizes valuable experiences, and employs a mixed-policy objective to balance exploration with experience exploitation. Experiments on five backbone models (1.5B-8B parameters) show that ExGRPO consistently improves reasoning performance on mathematical/general benchmarks, with an average gain of +3.5/7.6 points over on-policy RLVR. Moreover, ExGRPO stabilizes training on both stronger and weaker models where on-policy methods fail. These results highlight principled experience management as a key ingredient for efficient and scalable RLVR.</p> + https://arxiv.org/abs/2510.02245 + Thu, 02 Oct 2025 17:31:30 +0000 - Set Block Decoding is a Language Model Inference Accelerator - https://arxiv.org/abs/2509.04185 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.04185.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Itai Gat, Heli Ben-Hamu, Marton Havasi, Daniel Haziza, Jeremy Reizenstein, Gabriel Synnaeve, David Lopez-Paz, Brian Karrer, Yaron Lipman</p><p><b>Upvotes:</b> 52</p><p><b>Summary:</b> Autoregressive next token prediction language models offer powerful capabilities but face significant challenges in practical deployment due to the high computational and memory costs of inference, particularly during the decoding stage. We introduce Set Block Decoding (SBD), a simple and flexible paradigm that accelerates generation by integrating standard next token prediction (NTP) and masked token prediction (MATP) within a single architecture. SBD allows the model to sample multiple, not necessarily consecutive, future tokens in parallel, a key distinction from previous acceleration methods. This flexibility allows the use of advanced solvers from the discrete diffusion literature, offering significant speedups without sacrificing accuracy. SBD requires no architectural changes or extra training hyperparameters, maintains compatibility with exact KV-caching, and can be implemented by fine-tuning existing next token prediction models. By fine-tuning Llama-3.1 8B and Qwen-3 8B, we demonstrate that SBD enables a 3-5x reduction in the number of forward passes required for generation while achieving same performance as equivalent NTP training.</p> - https://arxiv.org/abs/2509.04185 - Thu, 04 Sep 2025 13:02:39 +0000 + Self-Forcing++: Towards Minute-Scale High-Quality Video Generation + https://arxiv.org/abs/2510.02283 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.02283.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Justin Cui, Jie Wu, Ming Li, Tao Yang, Xiaojie Li, Rui Wang, Andrew Bai, Yuanhao Ban, Cho-Jui Hsieh</p><p><b>Upvotes:</b> 91</p><p><b>Summary:</b> Diffusion models have revolutionized image and video generation, achieving unprecedented visual quality. However, their reliance on transformer architectures incurs prohibitively high computational costs, particularly when extending generation to long videos. Recent work has explored autoregressive formulations for long video generation, typically by distilling from short-horizon bidirectional teachers. Nevertheless, given that teacher models cannot synthesize long videos, the extrapolation of student models beyond their training horizon often leads to pronounced quality degradation, arising from the compounding of errors within the continuous latent space. In this paper, we propose a simple yet effective approach to mitigate quality degradation in long-horizon video generation without requiring supervision from long-video teachers or retraining on long video datasets. Our approach centers on exploiting the rich knowledge of teacher models to provide guidance for the student model through sampled segments drawn from self-generated long videos. Our method maintains temporal consistency while scaling video length by up to 20x beyond teacher's capability, avoiding common issues such as over-exposure and error-accumulation without recomputing overlapping frames like previous methods. When scaling up the computation, our method shows the capability of generating videos up to 4 minutes and 15 seconds, equivalent to 99.9% of the maximum span supported by our base model's position embedding and more than 50x longer than that of our baseline model. Experiments on standard benchmarks and our proposed improved benchmark demonstrate that our approach substantially outperforms baseline methods in both fidelity and consistency. Our long-horizon videos demo can be found at https://self-forcing-plus-plus.github.io/</p> + https://arxiv.org/abs/2510.02283 + Thu, 02 Oct 2025 17:55:42 +0000 - Inverse IFEval: Can LLMs Unlearn Stubborn Training Conventions to Follow Real Instructions? - https://arxiv.org/abs/2509.04292 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.04292.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qinyan Zhang, Xinping Lei, Ruijie Miao, Yu Fu, Haojie Fan, Le Chang, Jiafan Hou, Dingling Zhang, Zhongfei Hou, Ziqiang Yang, Changxin Pu, Fei Hu, Jingkai Liu, Mengyun Liu, Yang Liu, Xiang Gao, Jiaheng Liu, Tong Yang, Zaiyuan Wang, Ge Zhang, Wenhao Huang</p><p><b>Upvotes:</b> 57</p><p><b>Summary:</b> Large Language Models (LLMs) achieve strong performance on diverse tasks but often exhibit cognitive inertia, struggling to follow instructions that conflict with the standardized patterns learned during supervised fine-tuning (SFT). To evaluate this limitation, we propose Inverse IFEval, a benchmark that measures models Counter-intuitive Abilitytheir capacity to override training-induced biases and comply with adversarial instructions. Inverse IFEval introduces eight types of such challenges, including Question Correction, Intentional Textual Flaws, Code without Comments, and Counterfactual Answering. Using a human-in-the-loop pipeline, we construct a dataset of 1012 high-quality Chinese and English questions across 23 domains, evaluated under an optimized LLM-as-a-Judge framework. Experiments on existing leading LLMs demonstrate the necessity of our proposed Inverse IFEval benchmark. Our findings emphasize that future alignment efforts should not only pursue fluency and factual correctness but also account for adaptability under unconventional contexts. We hope that Inverse IFEval serves as both a diagnostic tool and a foundation for developing methods that mitigate cognitive inertia, reduce overfitting to narrow patterns, and ultimately enhance the instruction-following reliability of LLMs in diverse and unpredictable real-world scenarios.</p> - https://arxiv.org/abs/2509.04292 - Thu, 04 Sep 2025 15:03:02 +0000 + StealthAttack: Robust 3D Gaussian Splatting Poisoning via Density-Guided Illusions + https://arxiv.org/abs/2510.02314 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.02314.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bo-Hsu Ke, You-Zhe Xie, Yu-Lun Liu, Wei-Chen Chiu</p><p><b>Upvotes:</b> 58</p><p><b>Summary:</b> 3D scene representation methods like Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have significantly advanced novel view synthesis. As these methods become prevalent, addressing their vulnerabilities becomes critical. We analyze 3DGS robustness against image-level poisoning attacks and propose a novel density-guided poisoning method. Our method strategically injects Gaussian points into low-density regions identified via Kernel Density Estimation (KDE), embedding viewpoint-dependent illusory objects clearly visible from poisoned views while minimally affecting innocent views. Additionally, we introduce an adaptive noise strategy to disrupt multi-view consistency, further enhancing attack effectiveness. We propose a KDE-based evaluation protocol to assess attack difficulty systematically, enabling objective benchmarking for future research. Extensive experiments demonstrate our method's superior performance compared to state-of-the-art techniques. Project page: https://hentci.github.io/stealthattack/</p> + https://arxiv.org/abs/2510.02314 + Thu, 02 Oct 2025 17:59:57 +0000 - From Editor to Dense Geometry Estimator - https://arxiv.org/abs/2509.04338 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.04338.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> JiYuan Wang, Chunyu Lin, Lei Sun, Rongying Liu, Lang Nie, Mingxing Li, Kang Liao, Xiangxiang Chu, Yao Zhao</p><p><b>Upvotes:</b> 91</p><p><b>Summary:</b> Leveraging visual priors from pre-trained text-to-image (T2I) generative models has shown success in dense prediction. However, dense prediction is inherently an image-to-image task, suggesting that image editing models, rather than T2I generative models, may be a more suitable foundation for fine-tuning. Motivated by this, we conduct a systematic analysis of the fine-tuning behaviors of both editors and generators for dense geometry estimation. Our findings show that editing models possess inherent structural priors, which enable them to converge more stably by ``refining" their innate features, and ultimately achieve higher performance than their generative counterparts. Based on these findings, we introduce FE2E, a framework that pioneeringly adapts an advanced editing model based on Diffusion Transformer (DiT) architecture for dense geometry prediction. Specifically, to tailor the editor for this deterministic task, we reformulate the editor's original flow matching loss into the ``consistent velocity" training objective. And we use logarithmic quantization to resolve the precision conflict between the editor's native BFloat16 format and the high precision demand of our tasks. Additionally, we leverage the DiT's global attention for a cost-free joint estimation of depth and normals in a single forward pass, enabling their supervisory signals to mutually enhance each other. Without scaling up the training data, FE2E achieves impressive performance improvements in zero-shot monocular depth and normal estimation across multiple datasets. Notably, it achieves over 35\% performance gains on the ETH3D dataset and outperforms the DepthAnything series, which is trained on 100times data. The project page can be accessed https://amap-ml.github.io/FE2E/{here}.</p> - https://arxiv.org/abs/2509.04338 - Thu, 04 Sep 2025 15:58:50 +0000 + Cache-to-Cache: Direct Semantic Communication Between Large Language Models + https://arxiv.org/abs/2510.03215 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.03215.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tianyu Fu, Zihan Min, Hanling Zhang, Jichao Yan, Guohao Dai, Wanli Ouyang, Yu Wang</p><p><b>Upvotes:</b> 93</p><p><b>Summary:</b> Multi-LLM systems harness the complementary strengths of diverse Large Language Models, achieving performance and efficiency gains unattainable by a single model. In existing designs, LLMs communicate through text, forcing internal representations to be transformed into output token sequences. This process both loses rich semantic information and incurs token-by-token generation latency. Motivated by these limitations, we ask: Can LLMs communicate beyond text? Oracle experiments show that enriching the KV-Cache semantics can improve response quality without increasing cache size, supporting KV-Cache as an effective medium for inter-model communication. Thus, we propose Cache-to-Cache (C2C), a new paradigm for direct semantic communication between LLMs. C2C uses a neural network to project and fuse the source model's KV-cache with that of the target model to enable direct semantic transfer. A learnable gating mechanism selects the target layers that benefit from cache communication. Compared with text communication, C2C utilizes the deep, specialized semantics from both models, while avoiding explicit intermediate text generation. Experiments show that C2C achieves 8.5-10.5% higher average accuracy than individual models. It further outperforms the text communication paradigm by approximately 3.0-5.0%, while delivering an average 2.0x speedup in latency. Our code is available at https://github.com/thu-nics/C2C.</p> + https://arxiv.org/abs/2510.03215 + Fri, 03 Oct 2025 17:52:32 +0000 - Towards a Unified View of Large Language Model Post-Training - https://arxiv.org/abs/2509.04419 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.04419.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xingtai Lv, Yuxin Zuo, Youbang Sun, Hongyi Liu, Yuntian Wei, Zhekai Chen, Lixuan He, Xuekai Zhu, Kaiyan Zhang, Bingning Wang, Ning Ding, Bowen Zhou</p><p><b>Upvotes:</b> 73</p><p><b>Summary:</b> Two major sources of training data exist for post-training modern language models: online (model-generated rollouts) data, and offline (human or other-model demonstrations) data. These two types of data are typically used by approaches like Reinforcement Learning (RL) and Supervised Fine-Tuning (SFT), respectively. In this paper, we show that these approaches are not in contradiction, but are instances of a single optimization process. We derive a Unified Policy Gradient Estimator, and present the calculations of a wide spectrum of post-training approaches as the gradient of a common objective under different data distribution assumptions and various bias-variance tradeoffs. The gradient estimator is constructed with four interchangeable parts: stabilization mask, reference policy denominator, advantage estimate, and likelihood gradient. Motivated by our theoretical findings, we propose Hybrid Post-Training (HPT), an algorithm that dynamically selects different training signals. HPT is designed to yield both effective exploitation of demonstration and stable exploration without sacrificing learned reasoning patterns. We provide extensive experiments and ablation studies to verify the effectiveness of our unified theoretical framework and HPT. Across six mathematical reasoning benchmarks and two out-of-distribution suites, HPT consistently surpasses strong baselines across models of varying scales and families.</p> - https://arxiv.org/abs/2509.04419 - Thu, 04 Sep 2025 17:40:33 +0000 + Low-probability Tokens Sustain Exploration in Reinforcement Learning with Verifiable Reward + https://arxiv.org/abs/2510.03222 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.03222.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Guanhua Huang, Tingqiang Xu, Mingze Wang, Qi Yi, Xue Gong, Siheng Li, Ruibin Xiong, Kejiao Li, Yuhao Jiang, Bo Zhou</p><p><b>Upvotes:</b> 45</p><p><b>Summary:</b> Reinforcement Learning with Verifiable Rewards (RLVR) has propelled Large Language Models in complex reasoning, yet its scalability is often hindered by a training bottleneck where performance plateaus as policy entropy collapses, signaling a loss of exploration. Previous methods typically address this by maintaining high policy entropy, yet the precise mechanisms that govern meaningful exploration have remained underexplored. Our analysis suggests that an unselective focus on entropy risks amplifying irrelevant tokens and destabilizing training. This paper investigates the exploration dynamics within RLVR and identifies a key issue: the gradual elimination of valuable low-probability exploratory tokens, which we term \textit{reasoning sparks}. We find that while abundant in pre-trained models, these sparks are systematically extinguished during RLVR due to over-penalization, leading to a degeneracy in exploration. To address this, we introduce Low-probability Regularization (Lp-Reg). Its core mechanism regularizes the policy towards a heuristic proxy distribution. This proxy is constructed by filtering out presumed noise tokens and re-normalizing the distribution over the remaining candidates. The result is a less-noisy proxy where the probability of reasoning sparks is amplified, which then serves as a soft regularization target to shield these valuable tokens from elimination via KL divergence. Experiments show that Lp-Reg enables stable on-policy training for around 1,000 steps, a regime where baseline entropy-control methods collapse. This sustained exploration leads to state-of-the-art performance, achieving a 60.17% average accuracy on five math benchmarks, an improvement of 2.66% over prior methods. Code is available at https://github.com/CarlanLark/Lp-Reg.</p> + https://arxiv.org/abs/2510.03222 + Fri, 03 Oct 2025 17:56:13 +0000 - 3D and 4D World Modeling: A Survey - https://arxiv.org/abs/2509.07996 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.07996.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lingdong Kong, Wesley Yang, Jianbiao Mei, Youquan Liu, Ao Liang, Dekai Zhu, Dongyue Lu, Wei Yin, Xiaotao Hu, Mingkai Jia, Junyuan Deng, Kaiwen Zhang, Yang Wu, Tianyi Yan, Shenyuan Gao, Song Wang, Linfeng Li, Liang Pan, Yong Liu, Jianke Zhu, Wei Tsang Ooi, Steven C. H. Hoi, Ziwei Liu</p><p><b>Upvotes:</b> 57</p><p><b>Summary:</b> World modeling has become a cornerstone in AI research, enabling agents to understand, represent, and predict the dynamic environments they inhabit. While prior work largely emphasizes generative methods for 2D image and video data, they overlook the rapidly growing body of work that leverages native 3D and 4D representations such as RGB-D imagery, occupancy grids, and LiDAR point clouds for large-scale scene modeling. At the same time, the absence of a standardized definition and taxonomy for ``world models'' has led to fragmented and sometimes inconsistent claims in the literature. This survey addresses these gaps by presenting the first comprehensive review explicitly dedicated to 3D and 4D world modeling and generation. We establish precise definitions, introduce a structured taxonomy spanning video-based (VideoGen), occupancy-based (OccGen), and LiDAR-based (LiDARGen) approaches, and systematically summarize datasets and evaluation metrics tailored to 3D/4D settings. We further discuss practical applications, identify open challenges, and highlight promising research directions, aiming to provide a coherent and foundational reference for advancing the field. A systematic summary of existing literature is available at https://github.com/worldbench/survey</p> - https://arxiv.org/abs/2509.07996 - Thu, 04 Sep 2025 17:59:58 +0000 + Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models + https://arxiv.org/abs/2510.04618 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.04618.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qizheng Zhang, Changran Hu, Shubhangi Upasani, Boyuan Ma, Fenglu Hong, Vamsidhar Kamanuru, Jay Rainton, Chen Wu, Mengmeng Ji, Hanchen Li, Urmish Thakker, James Zou, Kunle Olukotun</p><p><b>Upvotes:</b> 111</p><p><b>Summary:</b> Large language model (LLM) applications such as agents and domain-specific reasoning increasingly rely on context adaptation -- modifying inputs with instructions, strategies, or evidence, rather than weight updates. Prior approaches improve usability but often suffer from brevity bias, which drops domain insights for concise summaries, and from context collapse, where iterative rewriting erodes details over time. Building on the adaptive memory introduced by Dynamic Cheatsheet, we introduce ACE (Agentic Context Engineering), a framework that treats contexts as evolving playbooks that accumulate, refine, and organize strategies through a modular process of generation, reflection, and curation. ACE prevents collapse with structured, incremental updates that preserve detailed knowledge and scale with long-context models. Across agent and domain-specific benchmarks, ACE optimizes contexts both offline (e.g., system prompts) and online (e.g., agent memory), consistently outperforming strong baselines: +10.6% on agents and +8.6% on finance, while significantly reducing adaptation latency and rollout cost. Notably, ACE could adapt effectively without labeled supervision and instead by leveraging natural execution feedback. On the AppWorld leaderboard, ACE matches the top-ranked production-level agent on the overall average and surpasses it on the harder test-challenge split, despite using a smaller open-source model. These results show that comprehensive, evolving contexts enable scalable, efficient, and self-improving LLM systems with low overhead.</p> + https://arxiv.org/abs/2510.04618 + Mon, 06 Oct 2025 09:30:18 +0000 - Why Language Models Hallucinate - https://arxiv.org/abs/2509.04664 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.04664.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Adam Tauman Kalai, Ofir Nachum, Santosh S. Vempala, Edwin Zhang</p><p><b>Upvotes:</b> 181</p><p><b>Summary:</b> Like students facing hard exam questions, large language models sometimes guess when uncertain, producing plausible yet incorrect statements instead of admitting uncertainty. Such "hallucinations" persist even in state-of-the-art systems and undermine trust. We argue that language models hallucinate because the training and evaluation procedures reward guessing over acknowledging uncertainty, and we analyze the statistical causes of hallucinations in the modern training pipeline. Hallucinations need not be mysterious -- they originate simply as errors in binary classification. If incorrect statements cannot be distinguished from facts, then hallucinations in pretrained language models will arise through natural statistical pressures. We then argue that hallucinations persist due to the way most evaluations are graded -- language models are optimized to be good test-takers, and guessing when uncertain improves test performance. This "epidemic" of penalizing uncertain responses can only be addressed through a socio-technical mitigation: modifying the scoring of existing benchmarks that are misaligned but dominate leaderboards, rather than introducing additional hallucination evaluations. This change may steer the field toward more trustworthy AI systems.</p> - https://arxiv.org/abs/2509.04664 - Thu, 04 Sep 2025 21:26:31 +0000 + When Models Lie, We Learn: Multilingual Span-Level Hallucination Detection with PsiloQA + https://arxiv.org/abs/2510.04849 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.04849.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Elisei Rykov, Kseniia Petrushina, Maksim Savkin, Valerii Olisov, Artem Vazhentsev, Kseniia Titova, Alexander Panchenko, Vasily Konovalov, Julia Belikova</p><p><b>Upvotes:</b> 109</p><p><b>Summary:</b> Hallucination detection remains a fundamental challenge for the safe and reliable deployment of large language models (LLMs), especially in applications requiring factual accuracy. Existing hallucination benchmarks often operate at the sequence level and are limited to English, lacking the fine-grained, multilingual supervision needed for a comprehensive evaluation. In this work, we introduce PsiloQA, a large-scale, multilingual dataset annotated with span-level hallucinations across 14 languages. PsiloQA is constructed through an automated three-stage pipeline: generating question-answer pairs from Wikipedia using GPT-4o, eliciting potentially hallucinated answers from diverse LLMs in a no-context setting, and automatically annotating hallucinated spans using GPT-4o by comparing against golden answers and retrieved context. We evaluate a wide range of hallucination detection methods -- including uncertainty quantification, LLM-based tagging, and fine-tuned encoder models -- and show that encoder-based models achieve the strongest performance across languages. Furthermore, PsiloQA demonstrates effective cross-lingual generalization and supports robust knowledge transfer to other benchmarks, all while being significantly more cost-efficient than human-annotated datasets. Our dataset and results advance the development of scalable, fine-grained hallucination detection in multilingual settings.</p> + https://arxiv.org/abs/2510.04849 + Mon, 06 Oct 2025 14:36:30 +0000 - Symbolic Graphics Programming with Large Language Models - https://arxiv.org/abs/2509.05208 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.05208.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yamei Chen, Haoquan Zhang, Yangyi Huang, Zeju Qiu, Kaipeng Zhang, Yandong Wen, Weiyang Liu</p><p><b>Upvotes:</b> 45</p><p><b>Summary:</b> Large language models (LLMs) excel at program synthesis, yet their ability to produce symbolic graphics programs (SGPs) that render into precise visual content remains underexplored. We study symbolic graphics programming, where the goal is to generate an SGP from a natural-language description. This task also serves as a lens into how LLMs understand the visual world by prompting them to generate images rendered from SGPs. Among various SGPs, our paper sticks to scalable vector graphics (SVGs). We begin by examining the extent to which LLMs can generate SGPs. To this end, we introduce SGP-GenBench, a comprehensive benchmark covering object fidelity, scene fidelity, and compositionality (attribute binding, spatial relations, numeracy). On SGP-GenBench, we discover that frontier proprietary models substantially outperform open-source models, and performance correlates well with general coding capabilities. Motivated by this gap, we aim to improve LLMs' ability to generate SGPs. We propose a reinforcement learning (RL) with verifiable rewards approach, where a format-validity gate ensures renderable SVG, and a cross-modal reward aligns text and the rendered image via strong vision encoders (e.g., SigLIP for text-image and DINO for image-image). Applied to Qwen-2.5-7B, our method substantially improves SVG generation quality and semantics, achieving performance on par with frontier systems. We further analyze training dynamics, showing that RL induces (i) finer decomposition of objects into controllable primitives and (ii) contextual details that improve scene coherence. Our results demonstrate that symbolic graphics programming offers a precise and interpretable lens on cross-modal grounding.</p> - https://arxiv.org/abs/2509.05208 - Fri, 05 Sep 2025 16:10:53 +0000 + Less is More: Recursive Reasoning with Tiny Networks + https://arxiv.org/abs/2510.04871 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.04871.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Alexia Jolicoeur-Martineau</p><p><b>Upvotes:</b> 460</p><p><b>Summary:</b> Hierarchical Reasoning Model (HRM) is a novel approach using two small neural networks recursing at different frequencies. This biologically inspired method beats Large Language models (LLMs) on hard puzzle tasks such as Sudoku, Maze, and ARC-AGI while trained with small models (27M parameters) on small data (around 1000 examples). HRM holds great promise for solving hard problems with small networks, but it is not yet well understood and may be suboptimal. We propose Tiny Recursive Model (TRM), a much simpler recursive reasoning approach that achieves significantly higher generalization than HRM, while using a single tiny network with only 2 layers. With only 7M parameters, TRM obtains 45% test-accuracy on ARC-AGI-1 and 8% on ARC-AGI-2, higher than most LLMs (e.g., Deepseek R1, o3-mini, Gemini 2.5 Pro) with less than 0.01% of the parameters.</p> + https://arxiv.org/abs/2510.04871 + Mon, 06 Oct 2025 14:58:08 +0000 - Reverse-Engineered Reasoning for Open-Ended Generation - https://arxiv.org/abs/2509.06160 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.06160.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haozhe Wang, Haoran Que, Qixin Xu, Minghao Liu, Wangchunshu Zhou, Jiazhan Feng, Wanjun Zhong, Wei Ye, Tong Yang, Wenhao Huang, Ge Zhang, Fangzhen Lin</p><p><b>Upvotes:</b> 145</p><p><b>Summary:</b> While the ``deep reasoning'' paradigm has spurred significant advances in verifiable domains like mathematics, its application to open-ended, creative generation remains a critical challenge. The two dominant methods for instilling reasoning -- reinforcement learning (RL) and instruction distillation -- falter in this area; RL struggles with the absence of clear reward signals and high-quality reward models, while distillation is prohibitively expensive and capped by the teacher model's capabilities. To overcome these limitations, we introduce REverse-Engineered Reasoning (REER), a new paradigm that fundamentally shifts the approach. Instead of building a reasoning process ``forwards'' through trial-and-error or imitation, REER works ``backwards'' from known-good solutions to computationally discover the latent, step-by-step deep reasoning process that could have produced them. Using this scalable, gradient-free approach, we curate and open-source DeepWriting-20K, a large-scale dataset of 20,000 deep reasoning trajectories for open-ended tasks. Our model, DeepWriter-8B, trained on this data, not only surpasses strong open-source baselines but also achieves performance competitive with, and at times superior to, leading proprietary models like GPT-4o and Claude 3.5.</p> - https://arxiv.org/abs/2509.06160 - Sun, 07 Sep 2025 18:07:58 +0000 + Video-LMM Post-Training: A Deep Dive into Video Reasoning with Large Multimodal Models + https://arxiv.org/abs/2510.05034 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.05034.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yunlong Tang, Jing Bi, Pinxin Liu, Zhenyu Pan, Zhangyun Tan, Qianxiang Shen, Jiani Liu, Hang Hua, Junjia Guo, Yunzhong Xiao, Chao Huang, Zhiyuan Wang, Susan Liang, Xinyi Liu, Yizhi Song, Yuhe Nie, Jia-Xing Zhong, Bozheng Li, Daiqing Qi, Ziyun Zeng, Ali Vosoughi, Luchuan Song, Zeliang Zhang, Daiki Shimada, Han Liu, Jiebo Luo, Chenliang Xu</p><p><b>Upvotes:</b> 46</p><p><b>Summary:</b> Video understanding represents the most challenging frontier in computer vision, requiring models to reason about complex spatiotemporal relationships, long-term dependencies, and multimodal evidence. The recent emergence of Video-Large Multimodal Models (Video-LMMs), which integrate visual encoders with powerful decoder-based language models, has demonstrated remarkable capabilities in video understanding tasks. However, the critical phase that transforms these models from basic perception systems into sophisticated reasoning engines, post-training, remains fragmented across the literature. This survey provides the first comprehensive examination of post-training methodologies for Video-LMMs, encompassing three fundamental pillars: supervised fine-tuning (SFT) with chain-of-thought, reinforcement learning (RL) from verifiable objectives, and test-time scaling (TTS) through enhanced inference computation. We present a structured taxonomy that clarifies the roles, interconnections, and video-specific adaptations of these techniques, addressing unique challenges such as temporal localization, spatiotemporal grounding, long video efficiency, and multimodal evidence integration. Through systematic analysis of representative methods, we synthesize key design principles, insights, and evaluation protocols while identifying critical open challenges in reward design, scalability, and cost-performance optimization. We further curate essential benchmarks, datasets, and metrics to facilitate rigorous assessment of post-training effectiveness. This survey aims to provide researchers and practitioners with a unified framework for advancing Video-LMM capabilities. Additional resources and updates are maintained at: https://github.com/yunlong10/Awesome-Video-LMM-Post-Training</p> + https://arxiv.org/abs/2510.05034 + Mon, 06 Oct 2025 17:10:44 +0000 - Does DINOv3 Set a New Medical Vision Standard? - https://arxiv.org/abs/2509.06467 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.06467.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Che Liu, Yinda Chen, Haoyuan Shi, Jinpeng Lu, Bailiang Jian, Jiazhen Pan, Linghan Cai, Jiayi Wang, Yundi Zhang, Jun Li, Cosmin I. Bercea, Cheng Ouyang, Chen Chen, Zhiwei Xiong, Benedikt Wiestler, Christian Wachinger, Daniel Rueckert, Wenjia Bai, Rossella Arcucci</p><p><b>Upvotes:</b> 36</p><p><b>Summary:</b> The advent of large-scale vision foundation models, pre-trained on diverse natural images, has marked a paradigm shift in computer vision. However, how the frontier vision foundation models' efficacies transfer to specialized domains remains such as medical imaging remains an open question. This report investigates whether DINOv3, a state-of-the-art self-supervised vision transformer (ViT) that features strong capability in dense prediction tasks, can directly serve as a powerful, unified encoder for medical vision tasks without domain-specific pre-training. To answer this, we benchmark DINOv3 across common medical vision tasks, including 2D/3D classification and segmentation on a wide range of medical imaging modalities. We systematically analyze its scalability by varying model sizes and input image resolutions. Our findings reveal that DINOv3 shows impressive performance and establishes a formidable new baseline. Remarkably, it can even outperform medical-specific foundation models like BiomedCLIP and CT-Net on several tasks, despite being trained solely on natural images. However, we identify clear limitations: The model's features degrade in scenarios requiring deep domain specialization, such as in Whole-Slide Pathological Images (WSIs), Electron Microscopy (EM), and Positron Emission Tomography (PET). Furthermore, we observe that DINOv3 does not consistently obey scaling law in the medical domain; performance does not reliably increase with larger models or finer feature resolutions, showing diverse scaling behaviors across tasks. Ultimately, our work establishes DINOv3 as a strong baseline, whose powerful visual features can serve as a robust prior for multiple complex medical tasks. This opens promising future directions, such as leveraging its features to enforce multiview consistency in 3D reconstruction.</p> - https://arxiv.org/abs/2509.06467 - Mon, 08 Sep 2025 09:28:57 +0000 + Paper2Video: Automatic Video Generation from Scientific Papers + https://arxiv.org/abs/2510.05096 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.05096.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zeyu Zhu, Kevin Qinghong Lin, Mike Zheng Shou</p><p><b>Upvotes:</b> 109</p><p><b>Summary:</b> Academic presentation videos have become an essential medium for research communication, yet producing them remains highly labor-intensive, often requiring hours of slide design, recording, and editing for a short 2 to 10 minutes video. Unlike natural video, presentation video generation involves distinctive challenges: inputs from research papers, dense multi-modal information (text, figures, tables), and the need to coordinate multiple aligned channels such as slides, subtitles, speech, and human talker. To address these challenges, we introduce PaperTalker, the first benchmark of 101 research papers paired with author-created presentation videos, slides, and speaker metadata. We further design four tailored evaluation metrics--Meta Similarity, PresentArena, PresentQuiz, and IP Memory--to measure how videos convey the paper's information to the audience. Building on this foundation, we propose PaperTalker, the first multi-agent framework for academic presentation video generation. It integrates slide generation with effective layout refinement by a novel effective tree search visual choice, cursor grounding, subtitling, speech synthesis, and talking-head rendering, while parallelizing slide-wise generation for efficiency. Experiments on Paper2Video demonstrate that the presentation videos produced by our approach are more faithful and informative than existing baselines, establishing a practical step toward automated and ready-to-use academic video generation. Our dataset, agent, and code are available at https://github.com/showlab/Paper2Video.</p> + https://arxiv.org/abs/2510.05096 + Mon, 06 Oct 2025 17:58:02 +0000 - WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents - https://arxiv.org/abs/2509.06501 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.06501.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junteng Liu, Yunji Li, Chi Zhang, Jingyang Li, Aili Chen, Ke Ji, Weiyu Cheng, Zijia Wu, Chengyu Du, Qidi Xu, Jiayuan Song, Zhengmao Zhu, Wenhu Chen, Pengyu Zhao, Junxian He</p><p><b>Upvotes:</b> 77</p><p><b>Summary:</b> The paradigm of Large Language Models (LLMs) has increasingly shifted toward agentic applications, where web browsing capabilities are fundamental for retrieving information from diverse online sources. However, existing open-source web agents either demonstrate limited information-seeking abilities on complex tasks or lack transparent implementations. In this work, we identify that the key challenge lies in the scarcity of challenging data for information seeking. To address this limitation, we introduce WebExplorer: a systematic data generation approach using model-based exploration and iterative, long-to-short query evolution. This method creates challenging query-answer pairs that require multi-step reasoning and complex web navigation. By leveraging our curated high-quality dataset, we successfully develop advanced web agent WebExplorer-8B through supervised fine-tuning followed by reinforcement learning. Our model supports 128K context length and up to 100 tool calling turns, enabling long-horizon problem solving. Across diverse information-seeking benchmarks, WebExplorer-8B achieves the state-of-the-art performance at its scale. Notably, as an 8B-sized model, WebExplorer-8B is able to effectively search over an average of 16 turns after RL training, achieving higher accuracy than WebSailor-72B on BrowseComp-en/zh and attaining the best performance among models up to 100B parameters on WebWalkerQA and FRAMES. Beyond these information-seeking tasks, our model also achieves strong generalization on the HLE benchmark even though it is only trained on knowledge-intensive QA data. These results highlight our approach as a practical path toward long-horizon web agents.</p> - https://arxiv.org/abs/2509.06501 - Mon, 08 Sep 2025 10:07:03 +0000 + In-the-Flow Agentic System Optimization for Effective Planning and Tool Use + https://arxiv.org/abs/2510.05592 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.05592.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhuofeng Li, Haoxiang Zhang, Seungju Han, Sheng Liu, Jianwen Xie, Yu Zhang, Yejin Choi, James Zou, Pan Lu</p><p><b>Upvotes:</b> 94</p><p><b>Summary:</b> Outcome-driven reinforcement learning has advanced reasoning in large language models (LLMs), but prevailing tool-augmented approaches train a single, monolithic policy that interleaves thoughts and tool calls under full context; this scales poorly with long horizons and diverse tools and generalizes weakly to new scenarios. Agentic systems offer a promising alternative by decomposing work across specialized modules, yet most remain training-free or rely on offline training decoupled from the live dynamics of multi-turn interaction. We introduce AgentFlow, a trainable, in-the-flow agentic framework that coordinates four modules (planner, executor, verifier, generator) through an evolving memory and directly optimizes its planner inside the multi-turn loop. To train on-policy in live environments, we propose Flow-based Group Refined Policy Optimization (Flow-GRPO), which tackles long-horizon, sparse-reward credit assignment by converting multi-turn optimization into a sequence of tractable single-turn policy updates. It broadcasts a single, verifiable trajectory-level outcome to every turn to align local planner decisions with global success and stabilizes learning with group-normalized advantages. Across ten benchmarks, AgentFlow with a 7B-scale backbone outperforms top-performing baselines with average accuracy gains of 14.9% on search, 14.0% on agentic, 14.5% on mathematical, and 4.1% on scientific tasks, even surpassing larger proprietary models like GPT-4o. Further analyses confirm the benefits of in-the-flow optimization, showing improved planning, enhanced tool-calling reliability, and positive scaling with model size and reasoning turns.</p> + https://arxiv.org/abs/2510.05592 + Tue, 07 Oct 2025 05:32:44 +0000 - Reinforcement Learning Foundations for Deep Research Systems: A Survey - https://arxiv.org/abs/2509.06733 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.06733.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wenjun Li, Zhi Chen, Jingru Lin, Hannan Cao, Wei Han, Sheng Liang, Zhi Zhang, Kuicai Dong, Dexun Li, Chen Zhang, Yong Liu</p><p><b>Upvotes:</b> 31</p><p><b>Summary:</b> Deep research systems, agentic AI that solve complex, multi-step tasks by coordinating reasoning, search across the open web and user files, and tool use, are moving toward hierarchical deployments with a Planner, Coordinator, and Executors. In practice, training entire stacks end-to-end remains impractical, so most work trains a single planner connected to core tools such as search, browsing, and code. While SFT imparts protocol fidelity, it suffers from imitation and exposure biases and underuses environment feedback. Preference alignment methods such as DPO are schema and proxy-dependent, off-policy, and weak for long-horizon credit assignment and multi-objective trade-offs. A further limitation of SFT and DPO is their reliance on human defined decision points and subskills through schema design and labeled comparisons. Reinforcement learning aligns with closed-loop, tool-interaction research by optimizing trajectory-level policies, enabling exploration, recovery behaviors, and principled credit assignment, and it reduces dependence on such human priors and rater biases. This survey is, to our knowledge, the first dedicated to the RL foundations of deep research systems. It systematizes work after DeepSeek-R1 along three axes: (i) data synthesis and curation; (ii) RL methods for agentic research covering stability, sample efficiency, long context handling, reward and credit design, multi-objective optimization, and multimodal integration; and (iii) agentic RL training systems and frameworks. We also cover agent architecture and coordination, as well as evaluation and benchmarks, including recent QA, VQA, long-form synthesis, and domain-grounded, tool-interaction tasks. We distill recurring patterns, surface infrastructure bottlenecks, and offer practical guidance for training robust, transparent deep research agents with RL.</p> - https://arxiv.org/abs/2509.06733 - Mon, 08 Sep 2025 14:27:23 +0000 + D2E: Scaling Vision-Action Pretraining on Desktop Data for Transfer to Embodied AI + https://arxiv.org/abs/2510.05684 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.05684.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Suwhan Choi, Jaeyoon Jung, Haebin Seong, Minchan Kim, Minyeong Kim, Yongjun Cho, Yoonshik Kim, Yubeen Park, Youngjae Yu, Yunsung Lee</p><p><b>Upvotes:</b> 134</p><p><b>Summary:</b> Large language models leverage internet-scale text data, yet embodied AI remains constrained by the prohibitive costs of physical trajectory collection. Desktop environments -- particularly gaming -- offer a compelling alternative: they provide rich sensorimotor interactions at scale while maintaining the structured observation-action coupling essential for embodied learning. We present D2E (Desktop to Embodied AI), a framework that demonstrates desktop interactions can serve as an effective pretraining substrate for robotics embodied AI tasks. Unlike prior work that remained domain-specific (e.g., VPT for Minecraft) or kept data proprietary (e.g., SIMA), D2E establishes a complete pipeline from scalable desktop data collection to verified transfer in embodied domains. Our framework comprises three components: (1) the OWA Toolkit that unifies diverse desktop interactions into a standardized format with 152x compression, (2) the Generalist-IDM that achieves strong zero-shot generalization across unseen games through timestamp-based event prediction, enabling internet-scale pseudo-labeling, and (3) VAPT that transfers desktop-pretrained representations to physical manipulation and navigation. Using 1.3K+ hours of data (259 hours of human demonstrations, and 1K+ hours of pseudo-labeled gameplay), we achieve a total of 96.6% success rate on LIBERO manipulation and 83.3% on CANVAS navigation benchmarks. This validates that sensorimotor primitives in digital interactions exhibit sufficient invariance to transfer meaningfully to physical embodied tasks, establishing desktop pretraining as a practical paradigm for robotics. We will make all our work public, including the OWA toolkit, datasets of human-collected and pseudo-labeled, and VAPT-trained models available at https://worv-ai.github.io/d2e/</p> + https://arxiv.org/abs/2510.05684 + Tue, 07 Oct 2025 08:40:33 +0000 - MachineLearningLM: Continued Pretraining Language Models on Millions of Synthetic Tabular Prediction Tasks Scales In-Context ML - https://arxiv.org/abs/2509.06806 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.06806.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haoyu Dong, Pengkun Zhang, Mingzhe Lu, Yanzhen Shen, Guolin Ke</p><p><b>Upvotes:</b> 63</p><p><b>Summary:</b> Large language models (LLMs) possess broad world knowledge and strong general-purpose reasoning ability, yet they struggle to learn from many in-context examples on standard machine learning (ML) tasks, that is, to leverage many-shot demonstrations purely via in-context learning (ICL) without gradient descent. We introduce MachineLearningLM, a portable continued-pretraining framework that equips a general-purpose LLM with robust in-context ML capability while preserving its general knowledge and reasoning for broader chat workflows. Our pretraining procedure synthesizes ML tasks from millions of structural causal models (SCMs), spanning shot counts up to 1,024. We begin with a random-forest teacher, distilling tree-based decision strategies into the LLM to strengthen robustness in numerical modeling. All tasks are serialized with a token-efficient prompt, enabling 3x to 6x more examples per context window and delivering up to 50x amortized throughput via batch inference. Despite a modest setup (Qwen-2.5-7B-Instruct with LoRA rank 8), MachineLearningLM outperforms strong LLM baselines (e.g., GPT-5-mini) by an average of about 15% on out-of-distribution tabular classification across finance, physics, biology, and healthcare domains. It exhibits a striking many-shot scaling law: accuracy increases monotonically as in-context demonstrations grow from 8 to 1,024. Without any task-specific training, it attains random-forest-level accuracy across hundreds of shots. General chat capabilities, including knowledge and reasoning, are preserved: it achieves 75.4% on MMLU.</p> - https://arxiv.org/abs/2509.06806 - Mon, 08 Sep 2025 15:38:31 +0000 + Lumina-DiMOO: An Omni Diffusion Large Language Model for Multi-Modal Generation and Understanding + https://arxiv.org/abs/2510.06308 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.06308.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yi Xin, Qi Qin, Siqi Luo, Kaiwen Zhu, Juncheng Yan, Yan Tai, Jiayi Lei, Yuewen Cao, Keqi Wang, Yibin Wang, Jinbin Bai, Qian Yu, Dengyang Jiang, Yuandong Pu, Haoxing Chen, Le Zhuo, Junjun He, Gen Luo, Tianbin Li, Ming Hu, Jin Ye, Shenglong Ye, Bo Zhang, Chang Xu, Wenhai Wang, Hongsheng Li, Guangtao Zhai, Tianfan Xue, Bin Fu, Xiaohong Liu, Yu Qiao, Yihao Liu</p><p><b>Upvotes:</b> 52</p><p><b>Summary:</b> We introduce Lumina-DiMOO, an open-source foundational model for seamless multi-modal generation and understanding. Lumina-DiMOO sets itself apart from prior unified models by utilizing a fully discrete diffusion modeling to handle inputs and outputs across various modalities. This innovative approach allows Lumina-DiMOO to achieve higher sampling efficiency compared to previous autoregressive (AR) or hybrid AR-Diffusion paradigms and adeptly support a broad spectrum of multi-modal tasks, including text-to-image generation, image-to-image generation (e.g., image editing, subject-driven generation, and image inpainting, etc.), as well as image understanding. Lumina-DiMOO achieves state-of-the-art performance on multiple benchmarks, surpassing existing open-source unified multi-modal models. To foster further advancements in multi-modal and discrete diffusion model research, we release our code and checkpoints to the community. Project Page: https://synbol.github.io/Lumina-DiMOO.</p> + https://arxiv.org/abs/2510.06308 + Tue, 07 Oct 2025 17:59:20 +0000 - Paper2Agent: Reimagining Research Papers As Interactive and Reliable AI Agents - https://arxiv.org/abs/2509.06917 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.06917.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiacheng Miao, Joe R. Davis, Jonathan K. Pritchard, James Zou</p><p><b>Upvotes:</b> 32</p><p><b>Summary:</b> We introduce Paper2Agent, an automated framework that converts research papers into AI agents. Paper2Agent transforms research output from passive artifacts into active systems that can accelerate downstream use, adoption, and discovery. Conventional research papers require readers to invest substantial effort to understand and adapt a paper's code, data, and methods to their own work, creating barriers to dissemination and reuse. Paper2Agent addresses this challenge by automatically converting a paper into an AI agent that acts as a knowledgeable research assistant. It systematically analyzes the paper and the associated codebase using multiple agents to construct a Model Context Protocol (MCP) server, then iteratively generates and runs tests to refine and robustify the resulting MCP. These paper MCPs can then be flexibly connected to a chat agent (e.g. Claude Code) to carry out complex scientific queries through natural language while invoking tools and workflows from the original paper. We demonstrate Paper2Agent's effectiveness in creating reliable and capable paper agents through in-depth case studies. Paper2Agent created an agent that leverages AlphaGenome to interpret genomic variants and agents based on ScanPy and TISSUE to carry out single-cell and spatial transcriptomics analyses. We validate that these paper agents can reproduce the original paper's results and can correctly carry out novel user queries. By turning static papers into dynamic, interactive AI agents, Paper2Agent introduces a new paradigm for knowledge dissemination and a foundation for the collaborative ecosystem of AI co-scientists.</p> - https://arxiv.org/abs/2509.06917 - Mon, 08 Sep 2025 17:28:42 +0000 + TaTToo: Tool-Grounded Thinking PRM for Test-Time Scaling in Tabular Reasoning + https://arxiv.org/abs/2510.06217 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.06217.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiaru Zou, Soumya Roy, Vinay Kumar Verma, Ziyi Wang, David Wipf, Pan Lu, Sumit Negi, James Zou, Jingrui He</p><p><b>Upvotes:</b> 62</p><p><b>Summary:</b> Process Reward Models (PRMs) have recently emerged as a powerful framework for enhancing the reasoning capabilities of large reasoning models (LRMs), particularly in the context of test-time scaling (TTS). However, their potential for supervising LRMs on tabular reasoning domains remains underexplored. Through detailed empirical analyses, we identify that existing PRMs, though widely adopted for supervising text-only reasoning steps, struggle with table-specific operations such as sub-table retrieval and schema interaction, leading to critical performance bottlenecks. To address this limitation, we propose TaTToo, a novel table-grounded PRM framework that (i) reasons explicitly over tabular reasoning steps and (ii) integrates tool-based verification to provide precise reward supervision. Concretely, we first design a scalable data curation pipeline that constructs over 60k high-quality step-level annotations by integrating table verification rationales with tool-based executions. Building on the collected data, we train TaTToo with a dual-stage paradigm: cold-start supervised fine-tuning to capture tool-use reasoning patterns, followed by reinforcement learning with tool-grounded reward shaping to align our model with table-based verification. We provide a comprehensive evaluation of the policy improvement induced by our newly designed PRM. Across 5 challenging tabular reasoning benchmarks covering numerical reasoning, fact-checking, and data analysis, TaTToo improves downstream policy LRMs by 30.9% at inference, surpasses strong PRM baselines such as Qwen-2.5-Math-PRM-72B with only 8B parameters, and demonstrates strong generalizability across diverse TTS strategies.</p> + https://arxiv.org/abs/2510.06217 + Tue, 07 Oct 2025 17:59:41 +0000 - Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models - https://arxiv.org/abs/2509.06949 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.06949.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yinjie Wang, Ling Yang, Bowen Li, Ye Tian, Ke Shen, Mengdi Wang</p><p><b>Upvotes:</b> 55</p><p><b>Summary:</b> We propose TraceRL, a trajectory-aware reinforcement learning framework for diffusion language models (DLMs) that incorporates preferred inference trajectory into post-training, and is applicable across different architectures. Equipped with a diffusion-based value model that enhances training stability, we demonstrate improved reasoning performance on complex math and coding tasks. Besides, it can also be applied to adapt block-specific models to larger blocks, which improves sampling flexibility. Employing TraceRL, we derive a series of state-of-the-art diffusion language models, namely TraDo. Although smaller than 7B-scale AR models, TraDo-4B-Instruct still consistently outperforms them across complex math reasoning tasks. TraDo-8B-Instruct achieves relative accuracy improvements of 6.1% over Qwen2.5-7B-Instruct and 51.3% over Llama3.1-8B-Instruct on mathematical reasoning benchmarks. Through curriculum learning, we also derive the first long-CoT DLM, outperforming Qwen2.5-7B-Instruct on MATH500 with an 18.1% relative accuracy gain. To facilitate reproducible research and practical applications, we release a comprehensive open-source framework for building, training, and deploying diffusion LLMs across diverse architectures. The framework integrates accelerated KV-cache techniques and inference engines for both inference and reinforcement learning, and includes implementations of various supervised fine-tuning and RL methods for mathematics, coding, and general tasks. Code and Models: https://github.com/Gen-Verse/dLLM-RL</p> - https://arxiv.org/abs/2509.06949 - Mon, 08 Sep 2025 17:58:06 +0000 + Ming-UniVision: Joint Image Understanding and Generation with a Unified Continuous Tokenizer + https://arxiv.org/abs/2510.06590 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.06590.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ziyuan Huang, DanDan Zheng, Cheng Zou, Rui Liu, Xiaolong Wang, Kaixiang Ji, Weilong Chai, Jianxin Sun, Libin Wang, Yongjie Lv, Taozhi Huang, Jiajia Liu, Qingpei Guo, Ming Yang, Jingdong Chen, Jun Zhou</p><p><b>Upvotes:</b> 70</p><p><b>Summary:</b> Visual tokenization remains a core challenge in unifying visual understanding and generation within the autoregressive paradigm. Existing methods typically employ tokenizers in discrete latent spaces to align with the tokens from large language models, where the quantization errors can limit semantic expressiveness and degrade the capability of vision-language understanding. To address this, we introduce MingTok, a new family of visual tokenizers with a continuous latent space, for unified autoregressive generation and understanding. While understanding tasks favor discriminative high-dimensional features, generation tasks prefer compact low-level codes. Thus, to reconcile these competing demands, MingTok adopts a three-stage sequential architecture involving low-level encoding, semantic expansion, and visual reconstruction. Built on top of it, Ming-UniVision eliminates the need for task-specific visual representations, and unifies diverse vision-language tasks under a single autoregrsssive prediction paradigm. By formulating both understanding and generation as next-token prediction in a shared continuous space, it seamlessly supports multi-round, in-context tasks such as iterative understanding, generation and editing. Empirically, we find that using a unified continuous visual representation reconciles the competing requirements on the tokenizers by the understanding and generation tasks, thereby leading to state-of-the-art level performance across both domains. We hope our findings will facilitate unified visual tokenization in the continuous domain. Inference code and model weights are released to benefit community.</p> + https://arxiv.org/abs/2510.06590 + Wed, 08 Oct 2025 02:50:14 +0000 - Reconstruction Alignment Improves Unified Multimodal Models - https://arxiv.org/abs/2509.07295 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.07295.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ji Xie, Trevor Darrell, Luke Zettlemoyer, XuDong Wang</p><p><b>Upvotes:</b> 39</p><p><b>Summary:</b> Unified multimodal models (UMMs) unify visual understanding and generation within a single architecture. However, conventional training relies on image-text pairs (or sequences) whose captions are typically sparse and miss fine-grained visual details--even when they use hundreds of words to describe a simple image. We introduce Reconstruction Alignment (RecA), a resource-efficient post-training method that leverages visual understanding encoder embeddings as dense "text prompts," providing rich supervision without captions. Concretely, RecA conditions a UMM on its own visual understanding embeddings and optimizes it to reconstruct the input image with a self-supervised reconstruction loss, thereby realigning understanding and generation. Despite its simplicity, RecA is broadly applicable: across autoregressive, masked-autoregressive, and diffusion-based UMMs, it consistently improves generation and editing fidelity. With only 27 GPU-hours, post-training with RecA substantially improves image generation performance on GenEval (0.73rightarrow0.90) and DPGBench (80.93rightarrow88.15), while also boosting editing benchmarks (ImgEdit 3.38rightarrow3.75, GEdit 6.94rightarrow7.25). Notably, RecA surpasses much larger open-source models and applies broadly across diverse UMM architectures, establishing it as an efficient and general post-training alignment strategy for UMMs</p> - https://arxiv.org/abs/2509.07295 - Mon, 08 Sep 2025 23:59:32 +0000 + DreamOmni2: Multimodal Instruction-based Editing and Generation + https://arxiv.org/abs/2510.06679 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.06679.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bin Xia, Bohao Peng, Yuechen Zhang, Junjia Huang, Jiyang Liu, Jingyao Li, Haoru Tan, Sitong Wu, Chengyao Wang, Yitong Wang, Xinglong Wu, Bei Yu, Jiaya Jia</p><p><b>Upvotes:</b> 74</p><p><b>Summary:</b> Recent advancements in instruction-based image editing and subject-driven generation have garnered significant attention, yet both tasks still face limitations in meeting practical user needs. Instruction-based editing relies solely on language instructions, which often fail to capture specific editing details, making reference images necessary. Meanwhile, subject-driven generation is limited to combining concrete objects or people, overlooking broader, abstract concepts. To address these challenges, we propose two novel tasks: multimodal instruction-based editing and generation. These tasks support both text and image instructions and extend the scope to include both concrete and abstract concepts, greatly enhancing their practical applications. We introduce DreamOmni2, tackling two primary challenges: data creation and model framework design. Our data synthesis pipeline consists of three steps: (1) using a feature mixing method to create extraction data for both abstract and concrete concepts, (2) generating multimodal instruction-based editing training data using the editing and extraction models, and (3) further applying the extraction model to create training data for multimodal instruction-based editing. For the framework, to handle multi-image input, we propose an index encoding and position encoding shift scheme, which helps the model distinguish images and avoid pixel confusion. Additionally, we introduce joint training with the VLM and our generation/editing model to better process complex instructions. In addition, we have proposed comprehensive benchmarks for these two new tasks to drive their development. Experiments show that DreamOmni2 has achieved impressive results. Models and codes will be released.</p> + https://arxiv.org/abs/2510.06679 + Wed, 08 Oct 2025 06:07:14 +0000 - Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search - https://arxiv.org/abs/2509.07969 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.07969.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xin Lai, Junyi Li, Wei Li, Tao Liu, Tianjian Li, Hengshuang Zhao</p><p><b>Upvotes:</b> 59</p><p><b>Summary:</b> Recent advances in large multimodal models have leveraged image-based tools with reinforcement learning to tackle visual problems. However, existing open-source approaches often exhibit monotonous reasoning patterns and allow only a limited number of interaction turns, making them inadequate for difficult tasks that require trial-and-error exploration. In this work, we address this limitation by scaling up tool-based interactions and introduce Mini-o3, a system that executes deep, multi-turn reasoning -- spanning tens of steps -- and achieves state-of-the-art performance on challenging visual search tasks. Our recipe for reproducing OpenAI o3-style behaviors comprises three key components. First, we construct the Visual Probe Dataset, a collection of thousands of challenging visual search problems designed for exploratory reasoning. Second, we develop an iterative data collection pipeline to obtain cold-start trajectories that exhibit diverse reasoning patterns, including depth-first search, trial-and-error, and goal maintenance. Third, we propose an over-turn masking strategy that prevents penalization of over-turn responses (those that hit the maximum number of turns) during reinforcement learning, thereby balancing training-time efficiency with test-time scalability. Despite training with an upper bound of only six interaction turns, our model generates trajectories that naturally scale to tens of turns at inference time, with accuracy improving as the number of turns increases. Extensive experiments demonstrate that Mini-o3 produces rich reasoning patterns and deep thinking paths, effectively solving challenging visual search problems.</p> - https://arxiv.org/abs/2509.07969 - Tue, 09 Sep 2025 17:54:21 +0000 + When Thoughts Meet Facts: Reusable Reasoning for Long-Context LMs + https://arxiv.org/abs/2510.07499 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.07499.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Soyeong Jeong, Taehee Jung, Sung Ju Hwang, Joo-Kyung Kim, Dongyeop Kang</p><p><b>Upvotes:</b> 47</p><p><b>Summary:</b> Recent Long-Context Language Models (LCLMs) can process hundreds of thousands of tokens in a single prompt, enabling new opportunities for knowledge-intensive multi-hop reasoning by integrating large sets of retrieved documents or, in some cases, directly all necessary information. However, simply feeding more documents into the context window fails to capture how evidence should be connected. We address this gap with thought templates, which recast reasoning as reusable thought caches, derived from prior problem solving traces, structuring how evidence is combined and guiding multi-hop inference with factual documents. To keep these templates effective, we propose an update strategy that iteratively refines templates derived from training data through natural-language feedback. Across diverse benchmarks and LCLM families, our approach delivers consistent gains over strong baselines in both retrieval-based and retrieval-free settings. Furthermore, we show that optimized templates can be distilled into smaller open-source models, demonstrating its broad applicability and transparent reasoning reuse. We refer to our framework as Thought Template Augmented LCLMs (ToTAL).</p> + https://arxiv.org/abs/2510.07499 + Wed, 08 Oct 2025 19:52:35 +0000 - Visual Representation Alignment for Multimodal Large Language Models - https://arxiv.org/abs/2509.07979 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.07979.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Heeji Yoon, Jaewoo Jung, Junwan Kim, Hyungyu Choi, Heeseong Shin, Sangbeom Lim, Honggyu An, Chaehyun Kim, Jisang Han, Donghyun Kim, Chanho Eom, Sunghwan Hong, Seungryong Kim</p><p><b>Upvotes:</b> 81</p><p><b>Summary:</b> Multimodal large language models (MLLMs) trained with visual instruction tuning have achieved strong performance across diverse tasks, yet they remain limited in vision-centric tasks such as object counting or spatial reasoning. We attribute this gap to the prevailing text-only supervision paradigm, which provides only indirect guidance for the visual pathway and often leads MLLMs to discard fine-grained visual details during training. In this paper, we present VIsual Representation ALignment (VIRAL), a simple yet effective regularization strategy that aligns the internal visual representations of MLLMs with those of pre-trained vision foundation models (VFMs). By explicitly enforcing this alignment, VIRAL enables the model not only to retain critical visual details from the input vision encoder but also to complement additional visual knowledge from VFMs, thereby enhancing its ability to reason over complex visual inputs. Our experiments demonstrate consistent improvements across all tasks on widely adopted multimodal benchmarks. Furthermore, we conduct comprehensive ablation studies to validate the key design choices underlying our framework. We believe this simple finding opens up an important direction for the effective integration of visual information in training MLLMs.</p> - https://arxiv.org/abs/2509.07979 - Tue, 09 Sep 2025 17:59:14 +0000 + UniVideo: Unified Understanding, Generation, and Editing for Videos + https://arxiv.org/abs/2510.08377 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.08377.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Cong Wei, Quande Liu, Zixuan Ye, Qiulin Wang, Xintao Wang, Pengfei Wan, Kun Gai, Wenhu Chen</p><p><b>Upvotes:</b> 67</p><p><b>Summary:</b> Unified multimodal models have shown promising results in multimodal content generation and editing but remain largely limited to the image domain. In this work, we present UniVideo, a versatile framework that extends unified modeling to the video domain. UniVideo adopts a dual-stream design, combining a Multimodal Large Language Model (MLLM) for instruction understanding with a Multimodal DiT (MMDiT) for video generation. This design enables accurate interpretation of complex multimodal instructions while preserving visual consistency. Built on this architecture, UniVideo unifies diverse video generation and editing tasks under a single multimodal instruction paradigm and is jointly trained across them. Extensive experiments demonstrate that UniVideo matches or surpasses state-of-the-art task-specific baselines in text/image-to-video generation, in-context video generation and in-context video editing. Notably, the unified design of UniVideo enables two forms of generalization. First, UniVideo supports task composition, such as combining editing with style transfer, by integrating multiple capabilities within a single instruction. Second, even without explicit training on free-form video editing, UniVideo transfers its editing capability from large-scale image editing data to this setting, handling unseen instructions such as green-screening characters or changing materials within a video. Beyond these core capabilities, UniVideo also supports visual-prompt-based video generation, where the MLLM interprets visual prompts and guides the MMDiT during synthesis. To foster future research, we will release our model and code.</p> + https://arxiv.org/abs/2510.08377 + Thu, 09 Oct 2025 16:01:30 +0000 - Parallel-R1: Towards Parallel Thinking via Reinforcement Learning - https://arxiv.org/abs/2509.07980 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.07980.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tong Zheng, Hongming Zhang, Wenhao Yu, Xiaoyang Wang, Xinyu Yang, Runpeng Dai, Rui Liu, Huiwen Bao, Chengsong Huang, Heng Huang, Dong Yu</p><p><b>Upvotes:</b> 96</p><p><b>Summary:</b> Parallel thinking has emerged as a novel approach for enhancing the reasoning capabilities of large language models (LLMs) by exploring multiple reasoning paths concurrently. However, activating such capabilities through training remains challenging, as existing methods predominantly rely on supervised fine-tuning (SFT) over synthetic data, which encourages teacher-forced imitation rather than exploration and generalization. Different from them, we propose Parallel-R1, the first reinforcement learning (RL) framework that enables parallel thinking behaviors for complex real-world reasoning tasks. Our framework employs a progressive curriculum that explicitly addresses the cold-start problem in training parallel thinking with RL. We first use SFT on prompt-generated trajectories from easier tasks to instill the parallel thinking ability, then transition to RL to explore and generalize this skill on harder problems. Experiments on various math benchmarks, including MATH, AMC23, and AIME, show that Parallel-R1 successfully instills parallel thinking, leading to 8.4% accuracy improvements over the sequential thinking model trained directly on challenging tasks with RL. Further analysis reveals a clear shift in the model's thinking behavior: at an early stage, it uses parallel thinking as an exploration strategy, while in a later stage, it uses the same capability for multi-perspective verification. Most significantly, we validate parallel thinking as a mid-training exploration scaffold, where this temporary exploratory phase unlocks a higher performance ceiling after RL, yielding a 42.9% improvement over the baseline on AIME25. Our model, data, and code will be open-source at https://github.com/zhengkid/Parallel-R1.</p> - https://arxiv.org/abs/2509.07980 - Tue, 09 Sep 2025 17:59:35 +0000 + MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization + https://arxiv.org/abs/2510.08540 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.08540.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiangyu Zhao, Junming Lin, Tianhao Liang, Yifan Zhou, Wenhao Chai, Yuzhe Gu, Weiyun Wang, Kai Chen, Gen Luo, Wenwei Zhang, Junchi Yan, Hua Yang, Haodong Duan, Xue Yang</p><p><b>Upvotes:</b> 108</p><p><b>Summary:</b> While current Multimodal Large Language Models (MLLMs) have demonstrated proficiency in reasoning tasks such as mathematics and logic, their capacity for long-chain reflective reasoning, a prerequisite for solving complex real-world problems, remains largely underexplored. In this work, we first conduct an extensive empirical investigation to evaluate this capability. Leveraging a carefully designed data synthesis engine, we construct MM-HELIX, a multimodal benchmark consisting 1,260 samples of 42 challenging synthetic tasks that require iterative thinking and backtracking. Empirical results on this benchmark reveal that existing MLLMs exhibit significant performance deficits in long-chain reflective reasoning. To address this limitation, we generate post-training data and further explore learning paradigms for exploiting such data. We first develop the Step-Elicited Response Generation pipeline to create MM-HELIX-100K, a large-scale dataset of 100k high-quality, reflective reasoning traces for instruction-tuning stage. Given that standard Reinforcement Learning fails on complex tasks due to sparse reward signals and catastrophic forgetting after Supervised Fine-Tuning, we propose Adaptive Hybrid Policy Optimization (AHPO), a novel training strategy that dynamically unifies offline supervision and online optimization into a single stage. This strategy enables the model to learn from expert data when rewards are sparse and conduct independent exploration once proficient. When applied to the Qwen2.5-VL-7B baseline, our method achieves a +18.6\% accuracy improvement on MM-HELIX benchmark and demonstrates strong generalization with a +5.7\% average performance gain on general mathematic and logic tasks. Our work demonstrate that reflective reasoning in MLLMs can be effectively learned and generalized, paving the way for developing more capable MLLMs.</p> + https://arxiv.org/abs/2510.08540 + Thu, 09 Oct 2025 17:53:58 +0000 - HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning - https://arxiv.org/abs/2509.08519 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.08519.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Liyang Chen, Tianxiang Ma, Jiawei Liu, Bingchuan Li, Zhuowei Chen, Lijie Liu, Xu He, Gen Li, Qian He, Zhiyong Wu</p><p><b>Upvotes:</b> 123</p><p><b>Summary:</b> Human-Centric Video Generation (HCVG) methods seek to synthesize human videos from multimodal inputs, including text, image, and audio. Existing methods struggle to effectively coordinate these heterogeneous modalities due to two challenges: the scarcity of training data with paired triplet conditions and the difficulty of collaborating the sub-tasks of subject preservation and audio-visual sync with multimodal inputs. In this work, we present HuMo, a unified HCVG framework for collaborative multimodal control. For the first challenge, we construct a high-quality dataset with diverse and paired text, reference images, and audio. For the second challenge, we propose a two-stage progressive multimodal training paradigm with task-specific strategies. For the subject preservation task, to maintain the prompt following and visual generation abilities of the foundation model, we adopt the minimal-invasive image injection strategy. For the audio-visual sync task, besides the commonly adopted audio cross-attention layer, we propose a focus-by-predicting strategy that implicitly guides the model to associate audio with facial regions. For joint learning of controllabilities across multimodal inputs, building on previously acquired capabilities, we progressively incorporate the audio-visual sync task. During inference, for flexible and fine-grained multimodal control, we design a time-adaptive Classifier-Free Guidance strategy that dynamically adjusts guidance weights across denoising steps. Extensive experimental results demonstrate that HuMo surpasses specialized state-of-the-art methods in sub-tasks, establishing a unified framework for collaborative multimodal-conditioned HCVG. Project Page: https://phantom-video.github.io/HuMo.</p> - https://arxiv.org/abs/2509.08519 - Wed, 10 Sep 2025 11:54:29 +0000 + VideoCanvas: Unified Video Completion from Arbitrary Spatiotemporal Patches via In-Context Conditioning + https://arxiv.org/abs/2510.08555 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.08555.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Minghong Cai, Qiulin Wang, Zongli Ye, Wenze Liu, Quande Liu, Weicai Ye, Xintao Wang, Pengfei Wan, Kun Gai, Xiangyu Yue</p><p><b>Upvotes:</b> 62</p><p><b>Summary:</b> We introduce the task of arbitrary spatio-temporal video completion, where a video is generated from arbitrary, user-specified patches placed at any spatial location and timestamp, akin to painting on a video canvas. This flexible formulation naturally unifies many existing controllable video generation tasks--including first-frame image-to-video, inpainting, extension, and interpolation--under a single, cohesive paradigm. Realizing this vision, however, faces a fundamental obstacle in modern latent video diffusion models: the temporal ambiguity introduced by causal VAEs, where multiple pixel frames are compressed into a single latent representation, making precise frame-level conditioning structurally difficult. We address this challenge with VideoCanvas, a novel framework that adapts the In-Context Conditioning (ICC) paradigm to this fine-grained control task with zero new parameters. We propose a hybrid conditioning strategy that decouples spatial and temporal control: spatial placement is handled via zero-padding, while temporal alignment is achieved through Temporal RoPE Interpolation, which assigns each condition a continuous fractional position within the latent sequence. This resolves the VAE's temporal ambiguity and enables pixel-frame-aware control on a frozen backbone. To evaluate this new capability, we develop VideoCanvasBench, the first benchmark for arbitrary spatio-temporal video completion, covering both intra-scene fidelity and inter-scene creativity. Experiments demonstrate that VideoCanvas significantly outperforms existing conditioning paradigms, establishing a new state of the art in flexible and unified video generation.</p> + https://arxiv.org/abs/2510.08555 + Thu, 09 Oct 2025 17:58:59 +0000 - Sharing is Caring: Efficient LM Post-Training with Collective RL Experience Sharing - https://arxiv.org/abs/2509.08721 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.08721.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jeffrey Amico, Gabriel Passamani Andrade, John Donaghy, Ben Fielding, Tristin Forbus, Harry Grieve, Semih Kara, Jari Kolehmainen, Yihua Lou, Christopher Nies, Edward Phillip Flores Nuño, Diogo Ortega, Shikhar Rastogi, Austin Virts, Matthew J. Wright</p><p><b>Upvotes:</b> 637</p><p><b>Summary:</b> Post-training language models (LMs) with reinforcement learning (RL) can enhance their complex reasoning capabilities without supervised fine-tuning, as demonstrated by DeepSeek-R1-Zero. However, effectively utilizing RL for LMs requires significant parallelization to scale-up inference, which introduces non-trivial technical challenges (e.g. latency, memory, and reliability) alongside ever-growing financial costs. We present Swarm sAmpling Policy Optimization (SAPO), a fully decentralized and asynchronous RL post-training algorithm. SAPO is designed for decentralized networks of heterogenous compute nodes, where each node manages its own policy model(s) while "sharing" rollouts with others in the network; no explicit assumptions about latency, model homogeneity, or hardware are required and nodes can operate in silo if desired. As a result, the algorithm avoids common bottlenecks in scaling RL post-training while also allowing (and even encouraging) new possibilities. By sampling rollouts "shared" across the network, it enables "Aha moments" to propagate, thereby bootstrapping the learning process. In this paper we show SAPO achieved cumulative reward gains of up to 94% in controlled experiments. We also share insights from tests on a network with thousands of nodes contributed by Gensyn community members running the algorithm on diverse hardware and models during an open-source demo.</p> - https://arxiv.org/abs/2509.08721 - Wed, 10 Sep 2025 16:14:20 +0000 + Agent Learning via Early Experience + https://arxiv.org/abs/2510.08558 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.08558.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kai Zhang, Xiangchao Chen, Bo Liu, Tianci Xue, Zeyi Liao, Zhihan Liu, Xiyao Wang, Yuting Ning, Zhaorun Chen, Xiaohan Fu, Jian Xie, Yuxuan Sun, Boyu Gou, Qi Qi, Zihang Meng, Jianwei Yang, Ning Zhang, Xian Li, Ashish Shah, Dat Huynh, Hengduo Li, Zi Yang, Sara Cao, Lawrence Jang, Shuyan Zhou, Jiacheng Zhu, Huan Sun, Jason Weston, Yu Su, Yifan Wu</p><p><b>Upvotes:</b> 255</p><p><b>Summary:</b> A long-term goal of language agents is to learn and improve through their own experience, ultimately outperforming humans in complex, real-world tasks. However, training agents from experience data with reinforcement learning remains difficult in many environments, which either lack verifiable rewards (e.g., websites) or require inefficient long-horizon rollouts (e.g., multi-turn tool use). As a result, most current agents rely on supervised fine-tuning on expert data, which is challenging to scale and generalizes poorly. This limitation stems from the nature of expert demonstrations: they capture only a narrow range of scenarios and expose the agent to limited environment diversity. We address this limitation with a middle-ground paradigm we call early experience: interaction data generated by the agent's own actions, where the resulting future states serve as supervision without reward signals. Within this paradigm we study two strategies of using such data: (1) Implicit world modeling, which uses collected states to ground the policy in environment dynamics; and (2) Self-reflection, where the agent learns from its suboptimal actions to improve reasoning and decision-making. We evaluate across eight diverse environments and multiple model families. Our approaches consistently improve effectiveness and out-of-domain generalization, highlighting the value of early experience. Moreover, in environments with verifiable rewards, our results provide promising signals that early experience offers a strong foundation for subsequent reinforcement learning, positioning it as a practical bridge between imitation learning and fully experience-driven agents.</p> + https://arxiv.org/abs/2510.08558 + Thu, 09 Oct 2025 17:59:17 +0000 - AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning - https://arxiv.org/abs/2509.08755 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.08755.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhiheng Xi, Jixuan Huang, Chenyang Liao, Baodai Huang, Honglin Guo, Jiaqi Liu, Rui Zheng, Junjie Ye, Jiazheng Zhang, Wenxiang Chen, Wei He, Yiwen Ding, Guanyu Li, Zehui Chen, Zhengyin Du, Xuesong Yao, Yufei Xu, Jiecao Chen, Tao Gui, Zuxuan Wu, Qi Zhang, Xuanjing Huang, Yu-Gang Jiang</p><p><b>Upvotes:</b> 54</p><p><b>Summary:</b> Developing autonomous LLM agents capable of making a series of intelligent decisions to solve complex, real-world tasks is a fast-evolving frontier. Like human cognitive development, agents are expected to acquire knowledge and skills through exploration and interaction with the environment. Despite advances, the community still lacks a unified, interactive reinforcement learning (RL) framework that can effectively train such agents from scratch -- without relying on supervised fine-tuning (SFT) -- across diverse and realistic environments. To bridge this gap, we introduce AgentGym-RL, a new framework to train LLM agents for multi-turn interactive decision-making through RL. The framework features a modular and decoupled architecture, ensuring high flexibility and extensibility. It encompasses a wide variety of real-world scenarios, and supports mainstream RL algorithms. Furthermore, we propose ScalingInter-RL, a training approach designed for exploration-exploitation balance and stable RL optimization. In early stages, it emphasizes exploitation by restricting the number of interactions, and gradually shifts towards exploration with larger horizons to encourage diverse problem-solving strategies. In this way, the agent develops more diverse behaviors and is less prone to collapse under long horizons. We perform extensive experiments to validate the stability and effectiveness of both the AgentGym-RL framework and the ScalingInter-RL approach. Our agents match or surpass commercial models on 27 tasks across diverse environments. We offer key insights and will open-source the complete AgentGym-RL framework -- including code and datasets -- to empower the research community in developing the next generation of intelligent agents.</p> - https://arxiv.org/abs/2509.08755 - Wed, 10 Sep 2025 16:46:11 +0000 + Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generation + https://arxiv.org/abs/2510.08673 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.08673.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kang Liao, Size Wu, Zhonghua Wu, Linyi Jin, Chao Wang, Yikai Wang, Fei Wang, Wei Li, Chen Change Loy</p><p><b>Upvotes:</b> 120</p><p><b>Summary:</b> Camera-centric understanding and generation are two cornerstones of spatial intelligence, yet they are typically studied in isolation. We present Puffin, a unified camera-centric multimodal model that extends spatial awareness along the camera dimension. Puffin integrates language regression and diffusion-based generation to interpret and create scenes from arbitrary viewpoints. To bridge the modality gap between cameras and vision-language, we introduce a novel paradigm that treats camera as language, enabling thinking with camera. This guides the model to align spatially grounded visual cues with photographic terminology while reasoning across geometric context. Puffin is trained on Puffin-4M, a large-scale dataset of 4 million vision-language-camera triplets. We incorporate both global camera parameters and pixel-wise camera maps, yielding flexible and reliable spatial generation. Experiments demonstrate Puffin superior performance over specialized models for camera-centric generation and understanding. With instruction tuning, Puffin generalizes to diverse cross-view tasks such as spatial imagination, world exploration, and photography guidance. We will release the code, models, dataset pipeline, and benchmark to advance multimodal spatial intelligence research.</p> + https://arxiv.org/abs/2510.08673 + Thu, 09 Oct 2025 17:59:29 +0000 - RewardDance: Reward Scaling in Visual Generation - https://arxiv.org/abs/2509.08826 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.08826.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jie Wu, Yu Gao, Zilyu Ye, Ming Li, Liang Li, Hanzhong Guo, Jie Liu, Zeyue Xue, Xiaoxia Hou, Wei Liu, Yan Zeng, Weilin Huang</p><p><b>Upvotes:</b> 69</p><p><b>Summary:</b> Reward Models (RMs) are critical for improving generation models via Reinforcement Learning (RL), yet the RM scaling paradigm in visual generation remains largely unexplored. It primarily due to fundamental limitations in existing approaches: CLIP-based RMs suffer from architectural and input modality constraints, while prevalent Bradley-Terry losses are fundamentally misaligned with the next-token prediction mechanism of Vision-Language Models (VLMs), hindering effective scaling. More critically, the RLHF optimization process is plagued by Reward Hacking issue, where models exploit flaws in the reward signal without improving true quality. To address these challenges, we introduce RewardDance, a scalable reward modeling framework that overcomes these barriers through a novel generative reward paradigm. By reformulating the reward score as the model's probability of predicting a "yes" token, indicating that the generated image outperforms a reference image according to specific criteria, RewardDance intrinsically aligns reward objectives with VLM architectures. This alignment unlocks scaling across two dimensions: (1) Model Scaling: Systematic scaling of RMs up to 26 billion parameters; (2) Context Scaling: Integration of task-specific instructions, reference examples, and chain-of-thought (CoT) reasoning. Extensive experiments demonstrate that RewardDance significantly surpasses state-of-the-art methods in text-to-image, text-to-video, and image-to-video generation. Crucially, we resolve the persistent challenge of "reward hacking": Our large-scale RMs exhibit and maintain high reward variance during RL fine-tuning, proving their resistance to hacking and ability to produce diverse, high-quality outputs. It greatly relieves the mode collapse problem that plagues smaller models.</p> - https://arxiv.org/abs/2509.08826 - Wed, 10 Sep 2025 17:59:31 +0000 + DITING: A Multi-Agent Evaluation Framework for Benchmarking Web Novel Translation + https://arxiv.org/abs/2510.09116 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.09116.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Enze Zhang, Jiaying Wang, Mengxi Xiao, Jifei Liu, Ziyan Kuang, Rui Dong, Eric Dong, Sophia Ananiadou, Min Peng, Qianqian Xie</p><p><b>Upvotes:</b> 95</p><p><b>Summary:</b> Large language models (LLMs) have substantially advanced machine translation (MT), yet their effectiveness in translating web novels remains unclear. Existing benchmarks rely on surface-level metrics that fail to capture the distinctive traits of this genre. To address these gaps, we introduce DITING, the first comprehensive evaluation framework for web novel translation, assessing narrative and cultural fidelity across six dimensions: idiom translation, lexical ambiguity, terminology localization, tense consistency, zero-pronoun resolution, and cultural safety, supported by over 18K expert-annotated Chinese-English sentence pairs. We further propose AgentEval, a reasoning-driven multi-agent evaluation framework that simulates expert deliberation to assess translation quality beyond lexical overlap, achieving the highest correlation with human judgments among seven tested automatic metrics. To enable metric comparison, we develop MetricAlign, a meta-evaluation dataset of 300 sentence pairs annotated with error labels and scalar quality scores. Comprehensive evaluation of fourteen open, closed, and commercial models reveals that Chinese-trained LLMs surpass larger foreign counterparts, and that DeepSeek-V3 delivers the most faithful and stylistically coherent translations. Our work establishes a new paradigm for exploring LLM-based web novel translation and provides public resources to advance future research.</p> + https://arxiv.org/abs/2510.09116 + Fri, 10 Oct 2025 08:10:10 +0000 - A Survey of Reinforcement Learning for Large Reasoning Models - https://arxiv.org/abs/2509.08827 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.08827.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kaiyan Zhang, Yuxin Zuo, Bingxiang He, Youbang Sun, Runze Liu, Che Jiang, Yuchen Fan, Kai Tian, Guoli Jia, Pengfei Li, Yu Fu, Xingtai Lv, Yuchen Zhang, Sihang Zeng, Shang Qu, Haozhan Li, Shijie Wang, Yuru Wang, Xinwei Long, Fangfu Liu, Xiang Xu, Jiaze Ma, Xuekai Zhu, Ermo Hua, Yihao Liu, Zonglin Li, Huayu Chen, Xiaoye Qu, Yafu Li, Weize Chen, Zhenzhao Yuan, Junqi Gao, Dong Li, Zhiyuan Ma, Ganqu Cui, Zhiyuan Liu, Biqing Qi, Ning Ding, Bowen Zhou</p><p><b>Upvotes:</b> 174</p><p><b>Summary:</b> In this paper, we survey recent advances in Reinforcement Learning (RL) for reasoning with Large Language Models (LLMs). RL has achieved remarkable success in advancing the frontier of LLM capabilities, particularly in addressing complex logical tasks such as mathematics and coding. As a result, RL has emerged as a foundational methodology for transforming LLMs into LRMs. With the rapid progress of the field, further scaling of RL for LRMs now faces foundational challenges not only in computational resources but also in algorithm design, training data, and infrastructure. To this end, it is timely to revisit the development of this domain, reassess its trajectory, and explore strategies to enhance the scalability of RL toward Artificial SuperIntelligence (ASI). In particular, we examine research applying RL to LLMs and LRMs for reasoning abilities, especially since the release of DeepSeek-R1, including foundational components, core problems, training resources, and downstream applications, to identify future opportunities and directions for this rapidly evolving area. We hope this review will promote future research on RL for broader reasoning models. Github: https://github.com/TsinghuaC3I/Awesome-RL-for-LRMs</p> - https://arxiv.org/abs/2509.08827 - Wed, 10 Sep 2025 17:59:43 +0000 + Multimodal Prompt Optimization: Why Not Leverage Multiple Modalities for MLLMs + https://arxiv.org/abs/2510.09201 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.09201.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yumin Choi, Dongki Kim, Jinheon Baek, Sung Ju Hwang</p><p><b>Upvotes:</b> 47</p><p><b>Summary:</b> Large Language Models (LLMs) have shown remarkable success, and their multimodal expansions (MLLMs) further unlock capabilities spanning images, videos, and other modalities beyond text. However, despite this shift, prompt optimization approaches, designed to reduce the burden of manual prompt crafting while maximizing performance, remain confined to text, ultimately limiting the full potential of MLLMs. Motivated by this gap, we introduce the new problem of multimodal prompt optimization, which expands the prior definition of prompt optimization to the multimodal space defined by the pairs of textual and non-textual prompts. To tackle this problem, we then propose the Multimodal Prompt Optimizer (MPO), a unified framework that not only performs the joint optimization of multimodal prompts through alignment-preserving updates but also guides the selection process of candidate prompts by leveraging earlier evaluations as priors in a Bayesian-based selection strategy. Through extensive experiments across diverse modalities that go beyond text, such as images, videos, and even molecules, we demonstrate that MPO outperforms leading text-only optimization methods, establishing multimodal prompt optimization as a crucial step to realizing the potential of MLLMs.</p> + https://arxiv.org/abs/2510.09201 + Fri, 10 Oct 2025 09:41:25 +0000 - EchoX: Towards Mitigating Acoustic-Semantic Gap via Echo Training for Speech-to-Speech LLMs - https://arxiv.org/abs/2509.09174 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.09174.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuhao Zhang, Yuhao Du, Zhanchen Dai, Xiangnan Ma, Kaiqi Kou, Benyou Wang, Haizhou Li</p><p><b>Upvotes:</b> 57</p><p><b>Summary:</b> Speech-to-speech large language models (SLLMs) are attracting increasing attention. Derived from text-based large language models (LLMs), SLLMs often exhibit degradation in knowledge and reasoning capabilities. We hypothesize that this limitation arises because current training paradigms for SLLMs fail to bridge the acoustic-semantic gap in the feature representation space. To address this issue, we propose EchoX, which leverages semantic representations and dynamically generates speech training targets. This approach integrates both acoustic and semantic learning, enabling EchoX to preserve strong reasoning abilities as a speech LLM. Experimental results demonstrate that EchoX, with about six thousand hours of training data, achieves advanced performance on multiple knowledge-based question-answering benchmarks. The project is available at https://github.com/FreedomIntelligence/EchoX.</p> - https://arxiv.org/abs/2509.09174 - Thu, 11 Sep 2025 06:17:59 +0000 + KORMo: Korean Open Reasoning Model for Everyone + https://arxiv.org/abs/2510.09426 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.09426.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Minjun Kim, Hyeonseok Lim, Hangyeol Yoo, Inho Won, Seungwoo Song, Minkyung Cho, Junhun Yuk, Changsu Choi, Dongjae Shin, Huige Lee, Hoyun Song, Alice Oh, Kyungtae Lim</p><p><b>Upvotes:</b> 74</p><p><b>Summary:</b> This work presents the first large-scale investigation into constructing a fully open bilingual large language model (LLM) for a non-English language, specifically Korean, trained predominantly on synthetic data. We introduce KORMo-10B, a 10.8B-parameter model trained from scratch on a Korean-English corpus in which 68.74% of the Korean portion is synthetic. Through systematic experimentation, we demonstrate that synthetic data, when carefully curated with balanced linguistic coverage and diverse instruction styles, does not cause instability or degradation during large-scale pretraining. Furthermore, the model achieves performance comparable to that of contemporary open-weight multilingual baselines across a wide range of reasoning, knowledge, and instruction-following benchmarks. Our experiments reveal two key findings: (1) synthetic data can reliably sustain long-horizon pretraining without model collapse, and (2) bilingual instruction tuning enables near-native reasoning and discourse coherence in Korean. By fully releasing all components including data, code, training recipes, and logs, this work establishes a transparent framework for developing synthetic data-driven fully open models (FOMs) in low-resource settings and sets a reproducible precedent for future multilingual LLM research.</p> + https://arxiv.org/abs/2510.09426 + Fri, 10 Oct 2025 14:31:25 +0000 - Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents - https://arxiv.org/abs/2509.09265 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.09265.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiawei Wang, Jiacai Liu, Yuqian Fu, Yingru Li, Xintao Wang, Yuan Lin, Yu Yue, Lin Zhang, Yang Wang, Ke Wang</p><p><b>Upvotes:</b> 45</p><p><b>Summary:</b> In long-horizon tasks, recent agents based on Large Language Models (LLMs) face a significant challenge that sparse, outcome-based rewards make it difficult to assign credit to intermediate steps. Previous methods mainly focus on creating dense reward signals to guide learning, either through traditional reinforcement learning techniques like inverse reinforcement learning or by using Process Reward Models for step-by-step feedback. In this paper, we identify a fundamental problem in the learning dynamics of LLMs: the magnitude of policy gradients is inherently coupled with the entropy, which leads to inefficient small updates for confident correct actions and potentially destabilizes large updates for uncertain ones. To resolve this, we propose Entropy-Modulated Policy Gradients (EMPG), a framework that re-calibrates the learning signal based on step-wise uncertainty and the final task outcome. EMPG amplifies updates for confident correct actions, penalizes confident errors, and attenuates updates from uncertain steps to stabilize exploration. We further introduce a bonus term for future clarity that encourages agents to find more predictable solution paths. Through comprehensive experiments on three challenging agent tasks, WebShop, ALFWorld, and Deep Search, we demonstrate that EMPG achieves substantial performance gains and significantly outperforms strong policy gradient baselines. Project page is at https://empgseed-seed.github.io/</p> - https://arxiv.org/abs/2509.09265 - Thu, 11 Sep 2025 08:50:01 +0000 + AutoPR: Let's Automate Your Academic Promotion! + https://arxiv.org/abs/2510.09558 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.09558.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qiguang Chen, Zheng Yan, Mingda Yang, Libo Qin, Yixin Yuan, Hanjing Li, Jinhao Liu, Yiyan Ji, Dengyun Peng, Jiannan Guan, Mengkang Hu, Yantao Du, Wanxiang Che</p><p><b>Upvotes:</b> 50</p><p><b>Summary:</b> As the volume of peer-reviewed research surges, scholars increasingly rely on social platforms for discovery, while authors invest considerable effort in promoting their work to ensure visibility and citations. To streamline this process and reduce the reliance on human effort, we introduce Automatic Promotion (AutoPR), a novel task that transforms research papers into accurate, engaging, and timely public content. To enable rigorous evaluation, we release PRBench, a multimodal benchmark that links 512 peer-reviewed articles to high-quality promotional posts, assessing systems along three axes: Fidelity (accuracy and tone), Engagement (audience targeting and appeal), and Alignment (timing and channel optimization). We also introduce PRAgent, a multi-agent framework that automates AutoPR in three stages: content extraction with multimodal preparation, collaborative synthesis for polished outputs, and platform-specific adaptation to optimize norms, tone, and tagging for maximum reach. When compared to direct LLM pipelines on PRBench, PRAgent demonstrates substantial improvements, including a 604% increase in total watch time, a 438% rise in likes, and at least a 2.9x boost in overall engagement. Ablation studies show that platform modeling and targeted promotion contribute the most to these gains. Our results position AutoPR as a tractable, measurable research problem and provide a roadmap for scalable, impactful automated scholarly communication.</p> + https://arxiv.org/abs/2510.09558 + Fri, 10 Oct 2025 17:08:36 +0000 - VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model - https://arxiv.org/abs/2509.09372 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.09372.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yihao Wang, Pengxiang Ding, Lingxiao Li, Can Cui, Zirui Ge, Xinyang Tong, Wenxuan Song, Han Zhao, Wei Zhao, Pengxu Hou, Siteng Huang, Yifan Tang, Wenhui Wang, Ru Zhang, Jianyi Liu, Donglin Wang</p><p><b>Upvotes:</b> 216</p><p><b>Summary:</b> Vision-Language-Action (VLA) models typically bridge the gap between perceptual and action spaces by pre-training a large-scale Vision-Language Model (VLM) on robotic data. While this approach greatly enhances performance, it also incurs significant training costs. In this paper, we investigate how to effectively bridge vision-language (VL) representations to action (A). We introduce VLA-Adapter, a novel paradigm designed to reduce the reliance of VLA models on large-scale VLMs and extensive pre-training. To this end, we first systematically analyze the effectiveness of various VL conditions and present key findings on which conditions are essential for bridging perception and action spaces. Based on these insights, we propose a lightweight Policy module with Bridge Attention, which autonomously injects the optimal condition into the action space. In this way, our method achieves high performance using only a 0.5B-parameter backbone, without any robotic data pre-training. Extensive experiments on both simulated and real-world robotic benchmarks demonstrate that VLA-Adapter not only achieves state-of-the-art level performance, but also offers the fast inference speed reported to date. Furthermore, thanks to the proposed advanced bridging paradigm, VLA-Adapter enables the training of a powerful VLA model in just 8 hours on a single consumer-grade GPU, greatly lowering the barrier to deploying the VLA model. Project page: https://vla-adapter.github.io/.</p> - https://arxiv.org/abs/2509.09372 - Thu, 11 Sep 2025 11:42:21 +0000 + StreamingVLM: Real-Time Understanding for Infinite Video Streams + https://arxiv.org/abs/2510.09608 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.09608.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ruyi Xu, Guangxuan Xiao, Yukang Chen, Liuning He, Kelly Peng, Yao Lu, Song Han</p><p><b>Upvotes:</b> 49</p><p><b>Summary:</b> Vision-language models (VLMs) could power real-time assistants and autonomous agents, but they face a critical challenge: understanding near-infinite video streams without escalating latency and memory usage. Processing entire videos with full attention leads to quadratic computational costs and poor performance on long videos. Meanwhile, simple sliding window methods are also flawed, as they either break coherence or suffer from high latency due to redundant recomputation. In this paper, we introduce StreamingVLM, a model designed for real-time, stable understanding of infinite visual input. Our approach is a unified framework that aligns training with streaming inference. During inference, we maintain a compact KV cache by reusing states of attention sinks, a short window of recent vision tokens, and a long window of recent text tokens. This streaming ability is instilled via a simple supervised fine-tuning (SFT) strategy that applies full attention on short, overlapped video chunks, which effectively mimics the inference-time attention pattern without training on prohibitively long contexts. For evaluation, we build Inf-Streams-Eval, a new benchmark with videos averaging over two hours that requires dense, per-second alignment between frames and text. On Inf-Streams-Eval, StreamingVLM achieves a 66.18% win rate against GPT-4O mini and maintains stable, real-time performance at up to 8 FPS on a single NVIDIA H100. Notably, our SFT strategy also enhances general VQA abilities without any VQA-specific fine-tuning, improving performance on LongVideoBench by +4.30 and OVOBench Realtime by +5.96. Code is available at https://github.com/mit-han-lab/streaming-vlm.</p> + https://arxiv.org/abs/2510.09608 + Fri, 10 Oct 2025 17:59:58 +0000 - Kling-Avatar: Grounding Multimodal Instructions for Cascaded Long-Duration Avatar Animation Synthesis - https://arxiv.org/abs/2509.09595 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.09595.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yikang Ding, Jiwen Liu, Wenyuan Zhang, Zekun Wang, Wentao Hu, Liyuan Cui, Mingming Lao, Yingchao Shao, Hui Liu, Xiaohan Li, Ming Chen, Xiaoqiang Liu, Yu-Shen Liu, Pengfei Wan</p><p><b>Upvotes:</b> 47</p><p><b>Summary:</b> Recent advances in audio-driven avatar video generation have significantly enhanced audio-visual realism. However, existing methods treat instruction conditioning merely as low-level tracking driven by acoustic or visual cues, without modeling the communicative purpose conveyed by the instructions. This limitation compromises their narrative coherence and character expressiveness. To bridge this gap, we introduce Kling-Avatar, a novel cascaded framework that unifies multimodal instruction understanding with photorealistic portrait generation. Our approach adopts a two-stage pipeline. In the first stage, we design a multimodal large language model (MLLM) director that produces a blueprint video conditioned on diverse instruction signals, thereby governing high-level semantics such as character motion and emotions. In the second stage, guided by blueprint keyframes, we generate multiple sub-clips in parallel using a first-last frame strategy. This global-to-local framework preserves fine-grained details while faithfully encoding the high-level intent behind multimodal instructions. Our parallel architecture also enables fast and stable generation of long-duration videos, making it suitable for real-world applications such as digital human livestreaming and vlogging. To comprehensively evaluate our method, we construct a benchmark of 375 curated samples covering diverse instructions and challenging scenarios. Extensive experiments demonstrate that Kling-Avatar is capable of generating vivid, fluent, long-duration videos at up to 1080p and 48 fps, achieving superior performance in lip synchronization accuracy, emotion and dynamic expressiveness, instruction controllability, identity preservation, and cross-domain generalization. These results establish Kling-Avatar as a new benchmark for semantically grounded, high-fidelity audio-driven avatar synthesis.</p> - https://arxiv.org/abs/2509.09595 - Thu, 11 Sep 2025 16:34:57 +0000 + OmniVideoBench: Towards Audio-Visual Understanding Evaluation for Omni MLLMs + https://arxiv.org/abs/2510.10689 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.10689.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Caorui Li, Yu Chen, Yiyan Ji, Jin Xu, Zhenyu Cui, Shihao Li, Yuanxing Zhang, Jiafu Tang, Zhenghao Song, Dingling Zhang, Ying He, Haoxiang Liu, Yuxuan Wang, Qiufeng Wang, Zhenhe Wu, Jiehui Luo, Zhiyu Pan, Weihao Xie, Chenchen Zhang, Zhaohui Wang, Jiayi Tian, Yanghai Wang, Zhe Cao, Minxin Dai, Ke Wang, Runzhe Wen, Yinghao Ma, Yaning Pan, Sungkyun Chang, Termeh Taheri, Haiwen Xia, Christos Plachouras, Emmanouil Benetos, Yizhi Li, Ge Zhang, Jian Yang, Tianhao Peng, Zili Wang, Minghao Liu, Junran Peng, Zhaoxiang Zhang, Jiaheng Liu</p><p><b>Upvotes:</b> 46</p><p><b>Summary:</b> Recent advances in multimodal large language models (MLLMs) have demonstrated substantial potential in video understanding. However, existing benchmarks fail to comprehensively evaluate synergistic reasoning capabilities across audio and visual modalities, often neglecting either one of the modalities or integrating them in a logically inconsistent manner. To bridge this gap, we introduce OmniVideoBench, a large-scale and rigorously designed benchmark dedicated to assessing synergistic audio-visual understanding, with a strong emphasis on modality complementarity and logical consistency. Specifically, OmniVideoBench comprises 1000 high-quality question-answer(QA) pairs, each annotated with step-by-step reasoning traces, derived from 628 diverse videos ranging from several seconds to 30 minutes, and manually verified to guarantee complete correctness and uniqueness. Moreover, OmniVideoBench encompasses 13 carefully designed question types, covering temporal reasoning, spatial localization, counting, causal inference, summarization, and beyond, thereby capturing the essential challenges of video understanding. Evaluation of multiple MLLMs on OmniVideoBench reveals a pronounced gap between model performance and human reasoning, with open-source models lagging significantly behind their closed-source counterparts, underscoring the inherent difficulty of genuine audio-visual reasoning. We will release OmniVideoBench to foster the development of MLLMs with stronger and more generalizable reasoning capabilities.</p> + https://arxiv.org/abs/2510.10689 + Sun, 12 Oct 2025 16:34:00 +0000 - SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning - https://arxiv.org/abs/2509.09674 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.09674.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haozhan Li, Yuxin Zuo, Jiale Yu, Yuhao Zhang, Zhaohui Yang, Kaiyan Zhang, Xuekai Zhu, Yuchen Zhang, Tianxing Chen, Ganqu Cui, Dehui Wang, Dingxiang Luo, Yuchen Fan, Youbang Sun, Jia Zeng, Jiangmiao Pang, Shanghang Zhang, Yu Wang, Yao Mu, Bowen Zhou, Ning Ding</p><p><b>Upvotes:</b> 76</p><p><b>Summary:</b> Vision-Language-Action (VLA) models have recently emerged as a powerful paradigm for robotic manipulation. Despite substantial progress enabled by large-scale pretraining and supervised fine-tuning (SFT), these models face two fundamental challenges: (i) the scarcity and high cost of large-scale human-operated robotic trajectories required for SFT scaling, and (ii) limited generalization to tasks involving distribution shift. Recent breakthroughs in Large Reasoning Models (LRMs) demonstrate that reinforcement learning (RL) can dramatically enhance step-by-step reasoning capabilities, raising a natural question: Can RL similarly improve the long-horizon step-by-step action planning of VLA? In this work, we introduce SimpleVLA-RL, an efficient RL framework tailored for VLA models. Building upon veRL, we introduce VLA-specific trajectory sampling, scalable parallelization, multi-environment rendering, and optimized loss computation. When applied to OpenVLA-OFT, SimpleVLA-RL achieves SoTA performance on LIBERO and even outperforms pi_0 on RoboTwin 1.0\&2.0 with the exploration-enhancing strategies we introduce. SimpleVLA-RL not only reduces dependence on large-scale data and enables robust generalization, but also remarkably surpasses SFT in real-world tasks. Moreover, we identify a novel phenomenon ``pushcut'' during RL training, wherein the policy discovers previously unseen patterns beyond those seen in the previous training process. Github: https://github.com/PRIME-RL/SimpleVLA-RL</p> - https://arxiv.org/abs/2509.09674 - Thu, 11 Sep 2025 17:59:17 +0000 + Latent Refinement Decoding: Enhancing Diffusion-Based Language Models by Refining Belief States + https://arxiv.org/abs/2510.11052 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.11052.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qinglin Zhu, Yizhen Yao, Runcong Zhao, Yanzheng Xiang, Amrutha Saseendran, Chen Jin, Philip Alexander Teare, Bin Liang, Yulan He, Lin Gui</p><p><b>Upvotes:</b> 51</p><p><b>Summary:</b> Autoregressive (AR) models remain the standard for natural language generation but still suffer from high latency due to strictly sequential decoding. Recent diffusion-inspired approaches, such as LlaDA and Dream, mitigate this by generating in parallel, yet they suffer from two core limitations: information loss, as predictive distributions for non-finalized tokens are discarded at each step, and premature commitment, where local decisions are made without sufficient global coordination. We introduce Latent Refinement Decoding (LRD), a two-stage framework with Latent Refinement and a Predictive Feedback Loop. The first stage maintains masked positions as distributional mixtures of predicted tokens and the mask embedding, allowing the model to establish more globally consistent beliefs. The second stage progressively finalizes confident tokens while retaining uncertain ones for iterative feedback. KL-divergence dynamics provide a principled and reliable criterion for convergence and early stopping. Experiments across coding (HumanEval +6.3, MBPP +2.6) and reasoning (GSM8K +2.9, MATH500 +3.8) show that LRD improves accuracy while delivering speedups of up to 10.6x, making it a strong and versatile alternative for parallel sequence generation.</p> + https://arxiv.org/abs/2510.11052 + Mon, 13 Oct 2025 06:38:13 +0000 - SpatialVID: A Large-Scale Video Dataset with Spatial Annotations - https://arxiv.org/abs/2509.09676 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.09676.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiahao Wang, Yufeng Yuan, Rujie Zheng, Youtian Lin, Jian Gao, Lin-Zhuo Chen, Yajie Bao, Yi Zhang, Chang Zeng, Yanxi Zhou, Xiaoxiao Long, Hao Zhu, Zhaoxiang Zhang, Xun Cao, Yao Yao</p><p><b>Upvotes:</b> 31</p><p><b>Summary:</b> Significant progress has been made in spatial intelligence, spanning both spatial reconstruction and world exploration. However, the scalability and real-world fidelity of current models remain severely constrained by the scarcity of large-scale, high-quality training data. While several datasets provide camera pose information, they are typically limited in scale, diversity, and annotation richness, particularly for real-world dynamic scenes with ground-truth camera motion. To this end, we collect SpatialVID, a dataset consists of a large corpus of in-the-wild videos with diverse scenes, camera movements and dense 3D annotations such as per-frame camera poses, depth, and motion instructions. Specifically, we collect more than 21,000 hours of raw video, and process them into 2.7 million clips through a hierarchical filtering pipeline, totaling 7,089 hours of dynamic content. A subsequent annotation pipeline enriches these clips with detailed spatial and semantic information, including camera poses, depth maps, dynamic masks, structured captions, and serialized motion instructions. Analysis of SpatialVID's data statistics reveals a richness and diversity that directly foster improved model generalization and performance, establishing it as a key asset for the video and 3D vision research community.</p> - https://arxiv.org/abs/2509.09676 - Thu, 11 Sep 2025 17:59:31 +0000 + Emergent Misalignment via In-Context Learning: Narrow in-context examples can produce broadly misaligned LLMs + https://arxiv.org/abs/2510.11288 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.11288.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Nikita Afonin, Nikita Andriyanov, Nikhil Bageshpura, Kyle Liu, Kevin Zhu, Sunishchal Dev, Ashwinee Panda, Alexander Panchenko, Oleg Rogov, Elena Tutubalina, Mikhail Seleznyov</p><p><b>Upvotes:</b> 45</p><p><b>Summary:</b> Recent work has shown that narrow finetuning can produce broadly misaligned LLMs, a phenomenon termed emergent misalignment (EM). While concerning, these findings were limited to finetuning and activation steering, leaving out in-context learning (ICL). We therefore ask: does EM emerge in ICL? We find that it does: across three datasets, three frontier models produce broadly misaligned responses at rates between 2% and 17% given 64 narrow in-context examples, and up to 58% with 256 examples. We also examine mechanisms of EM by eliciting step-by-step reasoning (while leaving in-context examples unchanged). Manual analysis of the resulting chain-of-thought shows that 67.5% of misaligned traces explicitly rationalize harmful outputs by adopting a reckless or dangerous ''persona'', echoing prior results on finetuning-induced EM.</p> + https://arxiv.org/abs/2510.11288 + Mon, 13 Oct 2025 11:23:56 +0000 - FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmark - https://arxiv.org/abs/2509.09680 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.09680.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Rongyao Fang, Aldrich Yu, Chengqi Duan, Linjiang Huang, Shuai Bai, Yuxuan Cai, Kun Wang, Si Liu, Xihui Liu, Hongsheng Li</p><p><b>Upvotes:</b> 42</p><p><b>Summary:</b> The advancement of open-source text-to-image (T2I) models has been hindered by the absence of large-scale, reasoning-focused datasets and comprehensive evaluation benchmarks, resulting in a performance gap compared to leading closed-source systems. To address this challenge, We introduce FLUX-Reason-6M and PRISM-Bench (Precise and Robust Image Synthesis Measurement Benchmark). FLUX-Reason-6M is a massive dataset consisting of 6 million high-quality FLUX-generated images and 20 million bilingual (English and Chinese) descriptions specifically designed to teach complex reasoning. The image are organized according to six key characteristics: Imagination, Entity, Text rendering, Style, Affection, and Composition, and design explicit Generation Chain-of-Thought (GCoT) to provide detailed breakdowns of image generation steps. The whole data curation takes 15,000 A100 GPU days, providing the community with a resource previously unattainable outside of large industrial labs. PRISM-Bench offers a novel evaluation standard with seven distinct tracks, including a formidable Long Text challenge using GCoT. Through carefully designed prompts, it utilizes advanced vision-language models for nuanced human-aligned assessment of prompt-image alignment and image aesthetics. Our extensive evaluation of 19 leading models on PRISM-Bench reveals critical performance gaps and highlights specific areas requiring improvement. Our dataset, benchmark, and evaluation code are released to catalyze the next wave of reasoning-oriented T2I generation. Project page: https://flux-reason-6m.github.io/ .</p> - https://arxiv.org/abs/2509.09680 - Thu, 11 Sep 2025 17:59:59 +0000 + Diffusion Transformers with Representation Autoencoders + https://arxiv.org/abs/2510.11690 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.11690.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Boyang Zheng, Nanye Ma, Shengbang Tong, Saining Xie</p><p><b>Upvotes:</b> 160</p><p><b>Summary:</b> Latent generative modeling, where a pretrained autoencoder maps pixels into a latent space for the diffusion process, has become the standard strategy for Diffusion Transformers (DiT); however, the autoencoder component has barely evolved. Most DiTs continue to rely on the original VAE encoder, which introduces several limitations: outdated backbones that compromise architectural simplicity, low-dimensional latent spaces that restrict information capacity, and weak representations that result from purely reconstruction-based training and ultimately limit generative quality. In this work, we explore replacing the VAE with pretrained representation encoders (e.g., DINO, SigLIP, MAE) paired with trained decoders, forming what we term Representation Autoencoders (RAEs). These models provide both high-quality reconstructions and semantically rich latent spaces, while allowing for a scalable transformer-based architecture. Since these latent spaces are typically high-dimensional, a key challenge is enabling diffusion transformers to operate effectively within them. We analyze the sources of this difficulty, propose theoretically motivated solutions, and validate them empirically. Our approach achieves faster convergence without auxiliary representation alignment losses. Using a DiT variant equipped with a lightweight, wide DDT head, we achieve strong image generation results on ImageNet: 1.51 FID at 256x256 (no guidance) and 1.13 at both 256x256 and 512x512 (with guidance). RAE offers clear advantages and should be the new default for diffusion transformer training.</p> + https://arxiv.org/abs/2510.11690 + Mon, 13 Oct 2025 17:51:39 +0000 - UI-S1: Advancing GUI Automation via Semi-online Reinforcement Learning - https://arxiv.org/abs/2509.11543 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.11543.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhengxi Lu, Jiabo Ye, Fei Tang, Yongliang Shen, Haiyang Xu, Ziwei Zheng, Weiming Lu, Ming Yan, Fei Huang, Jun Xiao, Yueting Zhuang</p><p><b>Upvotes:</b> 46</p><p><b>Summary:</b> Graphical User Interface (GUI) agents have demonstrated remarkable progress in automating complex user interface interactions through reinforcement learning. However, current approaches face a fundamental dilemma: offline RL enables stable training on pre-collected trajectories, but struggles with multi-step task execution for lack of trajectory-level reward signals; online RL captures these signals through environment interaction, but suffers from sparse rewards and prohibitive deployment costs. To address it, we present Semi-online Reinforcement Learning, a novel paradigm that simulates online RL on offline trajectories. During each rollout process, we preserve the original model output within the multi-turn dialogue, where a Patch Module adaptively recovers the divergence between rollout and expert trajectories. To capture long-term training signals, Semi-online RL introduces discounted future returns into the reward computation and optimizes the policy with weighted step-level and episode-level advantages. We further introduce Semi-Online Performance (SOP), a metric that aligns better with true online performance, serving as a practical and effective proxy for real-world evaluation. Experiments show that ours Semi-online RL achieves SOTA performance among 7B models across four dynamic benchmarks, with significant gains over the base model (e.g., +12.0% on AndroidWorld, +23.8% on AITW), demonstrating significant progress in bridging the gap between offline training efficiency and online multi-turn reasoning. The code is available at https://github.com/X-PLUG/MobileAgent/tree/main/UI-S1.</p> - https://arxiv.org/abs/2509.11543 - Mon, 15 Sep 2025 03:24:08 +0000 + Scaling Language-Centric Omnimodal Representation Learning + https://arxiv.org/abs/2510.11693 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.11693.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chenghao Xiao, Hou Pong Chan, Hao Zhang, Weiwen Xu, Mahani Aljunied, Yu Rong</p><p><b>Upvotes:</b> 97</p><p><b>Summary:</b> Recent multimodal embedding approaches leveraging multimodal large language models (MLLMs) fine-tuned with contrastive learning (CL) have shown promising results, yet the underlying reasons behind their superiority remain underexplored. This work argues that a crucial advantage of MLLM-based approaches stems from implicit cross-modal alignment achieved during generative pretraining, where the language decoder learns to exploit multimodal signals within a shared representation space for generating unimodal outputs. Through analysis of anisotropy and kernel similarity structure, we empirically confirm that latent alignment emerges within MLLM representations, allowing CL to serve as a lightweight refinement stage. Leveraging this insight, we propose a Language-Centric Omnimodal Embedding framework, termed LCO-Emb. Extensive experiments across diverse backbones and benchmarks demonstrate its effectiveness, achieving state-of-the-art performance across modalities. Furthermore, we identify a Generation-Representation Scaling Law (GRSL), showing that the representational capabilities gained through contrastive refinement scales positively with the MLLM's generative capabilities. This suggests that improving generative abilities evolves as an effective paradigm for enhancing representation quality. We provide a theoretical explanation of GRSL, which formally links the MLLM's generative quality to the upper bound on its representation performance, and validate it on a challenging, low-resource visual-document retrieval task, showing that continual generative pretraining before CL can further enhance the potential of a model's embedding capabilities. Codes, models, and resources are available at https://github.com/LCO-Embedding/LCO-Embedding.</p> + https://arxiv.org/abs/2510.11693 + Mon, 13 Oct 2025 17:53:52 +0000 - OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling - https://arxiv.org/abs/2509.12201 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.12201.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yang Zhou, Yifan Wang, Jianjun Zhou, Wenzheng Chang, Haoyu Guo, Zizun Li, Kaijing Ma, Xinyue Li, Yating Wang, Haoyi Zhu, Mingyu Liu, Dingning Liu, Jiange Yang, Zhoujie Fu, Junyi Chen, Chunhua Shen, Jiangmiao Pang, Kaipeng Zhang, Tong He</p><p><b>Upvotes:</b> 103</p><p><b>Summary:</b> The field of 4D world modeling - aiming to jointly capture spatial geometry and temporal dynamics - has witnessed remarkable progress in recent years, driven by advances in large-scale generative models and multimodal learning. However, the development of truly general 4D world models remains fundamentally constrained by the availability of high-quality data. Existing datasets and benchmarks often lack the dynamic complexity, multi-domain diversity, and spatial-temporal annotations required to support key tasks such as 4D geometric reconstruction, future prediction, and camera-control video generation. To address this gap, we introduce OmniWorld, a large-scale, multi-domain, multi-modal dataset specifically designed for 4D world modeling. OmniWorld consists of a newly collected OmniWorld-Game dataset and several curated public datasets spanning diverse domains. Compared with existing synthetic datasets, OmniWorld-Game provides richer modality coverage, larger scale, and more realistic dynamic interactions. Based on this dataset, we establish a challenging benchmark that exposes the limitations of current state-of-the-art (SOTA) approaches in modeling complex 4D environments. Moreover, fine-tuning existing SOTA methods on OmniWorld leads to significant performance gains across 4D reconstruction and video generation tasks, strongly validating OmniWorld as a powerful resource for training and evaluation. We envision OmniWorld as a catalyst for accelerating the development of general-purpose 4D world models, ultimately advancing machines' holistic understanding of the physical world.</p> - https://arxiv.org/abs/2509.12201 - Mon, 15 Sep 2025 17:59:19 +0000 + QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs + https://arxiv.org/abs/2510.11696 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.11696.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wei Huang, Yi Ge, Shuai Yang, Yicheng Xiao, Huizi Mao, Yujun Lin, Hanrong Ye, Sifei Liu, Ka Chun Cheung, Hongxu Yin, Yao Lu, Xiaojuan Qi, Song Han, Yukang Chen</p><p><b>Upvotes:</b> 168</p><p><b>Summary:</b> We propose QeRL, a Quantization-enhanced Reinforcement Learning framework for large language models (LLMs). While RL is essential for LLMs' reasoning capabilities, it is resource-intensive, requiring substantial GPU memory and long rollout durations. QeRL addresses these issues by combining NVFP4 quantization with Low-Rank Adaptation (LoRA), accelerating rollout phase of RL while reducing memory overhead. Beyond efficiency, our findings show that quantization noise increases policy entropy, enhancing exploration, and enabling the discovery of better strategies during RL. To further optimize exploration, QeRL introduces an Adaptive Quantization Noise (AQN) mechanism, which dynamically adjusts noise during training. Experiments demonstrate that QeRL delivers over 1.5 times speedup in the rollout phase. Moreover, this is the first framework to enable RL training of a 32B LLM on a single H100 80GB GPU, while delivering overall speedups for RL training. It also achieves faster reward growth and higher final accuracy than 16-bit LoRA and QLoRA, while matching the performance of full-parameter fine-tuning on mathematical benchmarks such as GSM8K (90.8%) and MATH 500 (77.4%) in the 7B model. These results establish QeRL as an efficient and effective framework for RL training in LLMs.</p> + https://arxiv.org/abs/2510.11696 + Mon, 13 Oct 2025 17:55:09 +0000 - Hunyuan3D Studio: End-to-End AI Pipeline for Game-Ready 3D Asset Generation - https://arxiv.org/abs/2509.12815 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.12815.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Biwen Lei, Yang Li, Xinhai Liu, Shuhui Yang, Lixin Xu, Jingwei Huang, Ruining Tang, Haohan Weng, Jian Liu, Jing Xu, Zhen Zhou, Yiling Zhu, Jiankai Xing, Jiachen Xu, Changfeng Ma, Xinhao Yan, Yunhan Yang, Chunshi Wang, Duoteng Xu, Xueqi Ma, Yuguang Chen, Jing Li, Mingxin Yang, Sheng Zhang, Yifei Feng, Xin Huang, Di Luo, Zebin He, Puhua Jiang, Changrong Hu, Zihan Qin, Shiwei Miao, Haolin Liu, Yunfei Zhao, Zeqiang Lai, Qingxiang Lin, Zibo Zhao, Kunhong Li, Xianghui Yang, Huiwen Shi, Xin Yang, Yuxuan Wang, Zebin Yao, Yihang Lian, Sicong Liu, Xintong Han, Wangchen Qin, Caisheng Ouyang, Jianyin Liu, Tianwen Yuan, Shuai Jiang, Hong Duan, Yanqi Niu, Wencong Lin, Yifu Sun, Shirui Huang, Lin Niu, Gu Gong, Guojian Xiao, Bojian Zheng, Xiang Yuan, Qi Chen, Jie Xiao, Dongyang Zheng, Xiaofeng Yang, Kai Liu, Jianchen Zhu, Lifu Wang, Qinglin Lu, Jie Liu, Liang Dong, Fan Jiang, Ruibin Chen, Lei Wang, Chao Zhang, Jiaxin Lin, Hao Zhang, Zheng Ye, Peng He, Runzhou Wu, Yinhe Wu, Jiayao Du, Jupeng Chen, Xinyue Mao, Dongyuan Guo, Yixuan Tang, Yulin Tsai, Yonghao Tan, Jiaao Yu, Junlin Yu, Keren Zhang, Yifan Li, Peng Chen, Tian Liu, Di Wang, Yuhong Liu, Linus, Jie Jiang, Zhuo Chen, Chunchao Guo</p><p><b>Upvotes:</b> 38</p><p><b>Summary:</b> The creation of high-quality 3D assets, a cornerstone of modern game development, has long been characterized by labor-intensive and specialized workflows. This paper presents Hunyuan3D Studio, an end-to-end AI-powered content creation platform designed to revolutionize the game production pipeline by automating and streamlining the generation of game-ready 3D assets. At its core, Hunyuan3D Studio integrates a suite of advanced neural modules (such as Part-level 3D Generation, Polygon Generation, Semantic UV, etc.) into a cohesive and user-friendly system. This unified framework allows for the rapid transformation of a single concept image or textual description into a fully-realized, production-quality 3D model complete with optimized geometry and high-fidelity PBR textures. We demonstrate that assets generated by Hunyuan3D Studio are not only visually compelling but also adhere to the stringent technical requirements of contemporary game engines, significantly reducing iteration time and lowering the barrier to entry for 3D content creation. By providing a seamless bridge from creative intent to technical asset, Hunyuan3D Studio represents a significant leap forward for AI-assisted workflows in game development and interactive media.</p> - https://arxiv.org/abs/2509.12815 - Tue, 16 Sep 2025 08:33:03 +0000 + Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model + https://arxiv.org/abs/2510.12276 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.12276.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fuhao Li, Wenxuan Song, Han Zhao, Jingbo Wang, Pengxiang Ding, Donglin Wang, Long Zeng, Haoang Li</p><p><b>Upvotes:</b> 142</p><p><b>Summary:</b> Vision-language-action (VLA) models have recently shown strong potential in enabling robots to follow language instructions and execute precise actions. However, most VLAs are built upon vision-language models pretrained solely on 2D data, which lack accurate spatial awareness and hinder their ability to operate in the 3D physical world. Existing solutions attempt to incorporate explicit 3D sensor inputs such as depth maps or point clouds, but these approaches face challenges due to sensor noise, hardware heterogeneity, and incomplete depth coverage in existing datasets. Alternative methods that estimate 3D cues from 2D images also suffer from the limited performance of depth estimators.We propose Spatial Forcing (SF), a simple yet effective alignment strategy that implicitly forces VLA models to develop spatial comprehension capabilities without relying on explicit 3D inputs or depth estimators. SF aligns intermediate visual embeddings of VLAs with geometric representations produced by pretrained 3D foundation models. By enforcing alignment at intermediate layers, SF guides VLAs to encode richer spatial representations that enhance action precision.Extensive experiments in simulation and real-world environments demonstrate that SF achieves state-of-the-art results, surpassing both 2D- and 3D-based VLAs. SF further accelerates training by up to 3.8x and improves data efficiency across diverse robotic tasks. Project page is at https://spatial-forcing.github.io/</p> + https://arxiv.org/abs/2510.12276 + Tue, 14 Oct 2025 08:27:10 +0000 - Single-stream Policy Optimization - https://arxiv.org/abs/2509.13232 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.13232.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhongwen Xu, Zihan Ding</p><p><b>Upvotes:</b> 34</p><p><b>Summary:</b> We revisit policy-gradient optimization for Large Language Models (LLMs) from a single-stream perspective. Prevailing group-based methods like GRPO reduce variance with on-the-fly baselines but suffer from critical flaws: frequent degenerate groups erase learning signals, and synchronization barriers hinder scalability. We introduce Single-stream Policy Optimization (SPO), which eliminates these issues by design. SPO replaces per-group baselines with a persistent, KL-adaptive value tracker and normalizes advantages globally across the batch, providing a stable, low-variance learning signal for every sample. Being group-free, SPO enables higher throughput and scales effectively in long-horizon or tool-integrated settings where generation times vary. Furthermore, the persistent value tracker naturally enables an adaptive curriculum via prioritized sampling. Experiments using Qwen3-8B show that SPO converges more smoothly and attains higher accuracy than GRPO, while eliminating computation wasted on degenerate groups. Ablation studies confirm that SPO's gains stem from its principled approach to baseline estimation and advantage normalization, offering a more robust and efficient path for LLM reasoning. Across five hard math benchmarks with Qwen3 8B, SPO improves the average maj@32 by +3.4 percentage points (pp) over GRPO, driven by substantial absolute point gains on challenging datasets, including +7.3 pp on BRUMO 25, +4.4 pp on AIME 25, +3.3 pp on HMMT 25, and achieves consistent relative gain in pass@k across the evaluated k values. SPO's success challenges the prevailing trend of adding incidental complexity to RL algorithms, highlighting a path where fundamental principles, not architectural workarounds, drive the next wave of progress in LLM reasoning.</p> - https://arxiv.org/abs/2509.13232 - Tue, 16 Sep 2025 16:39:11 +0000 + A Survey of Vibe Coding with Large Language Models + https://arxiv.org/abs/2510.12399 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.12399.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuyao Ge, Lingrui Mei, Zenghao Duan, Tianhao Li, Yujia Zheng, Yiwei Wang, Lexin Wang, Jiayu Yao, Tianyu Liu, Yujun Cai, Baolong Bi, Fangda Guo, Jiafeng Guo, Shenghua Liu, Xueqi Cheng</p><p><b>Upvotes:</b> 46</p><p><b>Summary:</b> The advancement of large language models (LLMs) has catalyzed a paradigm shift from code generation assistance to autonomous coding agents, enabling a novel development methodology termed "Vibe Coding" where developers validate AI-generated implementations through outcome observation rather than line-by-line code comprehension. Despite its transformative potential, the effectiveness of this emergent paradigm remains under-explored, with empirical evidence revealing unexpected productivity losses and fundamental challenges in human-AI collaboration. To address this gap, this survey provides the first comprehensive and systematic review of Vibe Coding with large language models, establishing both theoretical foundations and practical frameworks for this transformative development approach. Drawing from systematic analysis of over 1000 research papers, we survey the entire vibe coding ecosystem, examining critical infrastructure components including LLMs for coding, LLM-based coding agent, development environment of coding agent, and feedback mechanisms. We first introduce Vibe Coding as a formal discipline by formalizing it through a Constrained Markov Decision Process that captures the dynamic triadic relationship among human developers, software projects, and coding agents. Building upon this theoretical foundation, we then synthesize existing practices into five distinct development models: Unconstrained Automation, Iterative Conversational Collaboration, Planning-Driven, Test-Driven, and Context-Enhanced Models, thus providing the first comprehensive taxonomy in this domain. Critically, our analysis reveals that successful Vibe Coding depends not merely on agent capabilities but on systematic context engineering, well-established development environments, and human-agent collaborative development models.</p> + https://arxiv.org/abs/2510.12399 + Tue, 14 Oct 2025 11:26:56 +0000 - WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning - https://arxiv.org/abs/2509.13305 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.13305.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kuan Li, Zhongwang Zhang, Huifeng Yin, Rui Ye, Yida Zhao, Liwen Zhang, Litu Ou, Dingchu Zhang, Xixi Wu, Jialong Wu, Xinyu Wang, Zile Qiao, Zhen Zhang, Yong Jiang, Pengjun Xie, Fei Huang, Jingren Zhou</p><p><b>Upvotes:</b> 83</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 open-source agents in complex information-seeking tasks, matching proprietary agents' performance and closing the capability gap.</p> - https://arxiv.org/abs/2509.13305 - Tue, 16 Sep 2025 17:57:03 +0000 + Robot Learning: A Tutorial + https://arxiv.org/abs/2510.12403 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.12403.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Francesco Capuano, Caroline Pascal, Adil Zouitine, Thomas Wolf, Michel Aractingi</p><p><b>Upvotes:</b> 95</p><p><b>Summary:</b> Robot learning is at an inflection point, driven by rapid advancements in machine learning and the growing availability of large-scale robotics data. This shift from classical, model-based methods to data-driven, learning-based paradigms is unlocking unprecedented capabilities in autonomous systems. This tutorial navigates the landscape of modern robot learning, charting a course from the foundational principles of Reinforcement Learning and Behavioral Cloning to generalist, language-conditioned models capable of operating across diverse tasks and even robot embodiments. This work is intended as a guide for researchers and practitioners, and our goal is to equip the reader with the conceptual understanding and practical tools necessary to contribute to developments in robot learning, with ready-to-use examples implemented in lerobot.</p> + https://arxiv.org/abs/2510.12403 + Tue, 14 Oct 2025 11:36:46 +0000 - WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agents - https://arxiv.org/abs/2509.13309 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.13309.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zile Qiao, Guoxin Chen, Xuanzhong Chen, Donglei Yu, Wenbiao Yin, Xinyu Wang, Zhen Zhang, Baixuan Li, Huifeng Yin, Kuan Li, Rui Min, Minpeng Liao, Yong Jiang, Pengjun Xie, Fei Huang, Jingren Zhou</p><p><b>Upvotes:</b> 66</p><p><b>Summary:</b> Recent advances in deep-research systems have demonstrated the potential for AI agents to autonomously discover and synthesize knowledge from external sources. In this paper, we introduce WebResearcher, a novel framework for building such agents through two key components: (1) WebResearcher, an iterative deep-research paradigm that reformulates deep research as a Markov Decision Process, where agents periodically consolidate findings into evolving reports while maintaining focused workspaces, overcoming the context suffocation and noise contamination that plague existing mono-contextual approaches; and (2) WebFrontier, a scalable data synthesis engine that generates high-quality training data through tool-augmented complexity escalation, enabling systematic creation of research tasks that bridge the gap between passive knowledge recall and active knowledge construction. Notably, we find that the training data from our paradigm significantly enhances tool-use capabilities even for traditional mono-contextual methods. Furthermore, our paradigm naturally scales through parallel thinking, enabling concurrent multi-agent exploration for more comprehensive conclusions. Extensive experiments across 6 challenging benchmarks demonstrate that WebResearcher achieves state-of-the-art performance, even surpassing frontier proprietary systems.</p> - https://arxiv.org/abs/2509.13309 - Tue, 16 Sep 2025 17:57:17 +0000 + Advancing End-to-End Pixel Space Generative Modeling via Self-supervised Pre-training + https://arxiv.org/abs/2510.12586 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.12586.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiachen Lei, Keli Liu, Julius Berner, Haiming Yu, Hongkai Zheng, Jiahong Wu, Xiangxiang Chu</p><p><b>Upvotes:</b> 107</p><p><b>Summary:</b> Pixel-space generative models are often more difficult to train and generally underperform compared to their latent-space counterparts, leaving a persistent performance and efficiency gap. In this paper, we introduce a novel two-stage training framework that closes this gap for pixel-space diffusion and consistency models. In the first stage, we pre-train encoders to capture meaningful semantics from clean images while aligning them with points along the same deterministic sampling trajectory, which evolves points from the prior to the data distribution. In the second stage, we integrate the encoder with a randomly initialized decoder and fine-tune the complete model end-to-end for both diffusion and consistency models. Our training framework demonstrates strong empirical performance on ImageNet dataset. Specifically, our diffusion model reaches an FID of 2.04 on ImageNet-256 and 2.35 on ImageNet-512 with 75 number of function evaluations (NFE), surpassing prior pixel-space methods by a large margin in both generation quality and efficiency while rivaling leading VAE-based models at comparable training cost. Furthermore, on ImageNet-256, our consistency model achieves an impressive FID of 8.82 in a single sampling step, significantly surpassing its latent-space counterpart. To the best of our knowledge, this marks the first successful training of a consistency model directly on high-resolution images without relying on pre-trained VAEs or diffusion models.</p> + https://arxiv.org/abs/2510.12586 + Tue, 14 Oct 2025 14:41:16 +0000 - Scaling Agents via Continual Pre-training - https://arxiv.org/abs/2509.13310 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.13310.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Liangcai Su, Zhen Zhang, Guangyu Li, Zhuo Chen, Chenxi Wang, Maojia Song, Xinyu Wang, Kuan Li, Jialong Wu, Xuanzhong Chen, Zile Qiao, Zhongwang Zhang, Huifeng Yin, Shihao Cai, Runnan Fang, Zhengwei Tao, Wenbiao Yin, Chenxiong Qian, Yong Jiang, Pengjun Xie, Fei Huang, Jingren Zhou</p><p><b>Upvotes:</b> 107</p><p><b>Summary:</b> Large language models (LLMs) have evolved into agentic systems capable of autonomous tool use and multi-step reasoning for complex problem-solving. However, post-training approaches building upon general-purpose foundation models consistently underperform in agentic tasks, particularly in open-source implementations. We identify the root cause: the absence of robust agentic foundation models forces models during post-training to simultaneously learn diverse agentic behaviors while aligning them to expert demonstrations, thereby creating fundamental optimization tensions. To this end, we are the first to propose incorporating Agentic Continual Pre-training (Agentic CPT) into the deep research agents training pipeline to build powerful agentic foundational models. Based on this approach, we develop a deep research agent model named AgentFounder. We evaluate our AgentFounder-30B on 10 benchmarks and achieve state-of-the-art performance while retains strong tool-use ability, notably 39.9% on BrowseComp-en, 43.3% on BrowseComp-zh, and 31.5% Pass@1 on HLE.</p> - https://arxiv.org/abs/2509.13310 - Tue, 16 Sep 2025 17:57:19 +0000 + UniMoE-Audio: Unified Speech and Music Generation with Dynamic-Capacity MoE + https://arxiv.org/abs/2510.13344 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.13344.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhenyu Liu, Yunxin Li, Xuanyu Zhang, Qixun Teng, Shenyuan Jiang, Xinyu Chen, Haoyuan Shi, Jinchao Li, Qi Wang, Haolan Chen, Fanbo Meng, Mingjun Zhao, Yu Xu, Yancheng He, Baotian Hu, Min Zhang</p><p><b>Upvotes:</b> 61</p><p><b>Summary:</b> Recent advances in unified multimodal models indicate a clear trend towards comprehensive content generation. However, the auditory domain remains a significant challenge, with music and speech often developed in isolation, hindering progress towards universal audio synthesis. This separation stems from inherent task conflicts and severe data imbalances, which impede the development of a truly unified audio generation model. To address this challenge, we propose UniMoE-Audio, a unified speech and music generation model within a novel Dynamic-Capacity Mixture-of-Experts (MoE) framework. Architecturally, UniMoE-Audio introduces a Top-P routing strategy for dynamic expert number allocation, and a hybrid expert design comprising routed experts for domain-specific knowledge, shared experts for domain-agnostic features, and null experts for adaptive computation skipping. To tackle data imbalance, we introduce a three-stage training curriculum: 1) Independent Specialist Training leverages original datasets to instill domain-specific knowledge into each "proto-expert" without interference; 2) MoE Integration and Warmup incorporates these specialists into the UniMoE-Audio architecture, warming up the gate module and shared expert using a subset of balanced dataset; and 3) Synergistic Joint Training trains the entire model end-to-end on the fully balanced dataset, fostering enhanced cross-domain synergy. Extensive experiments show that UniMoE-Audio not only achieves state-of-the-art performance on major speech and music generation benchmarks, but also demonstrates superior synergistic learning, mitigating the performance degradation typically seen in naive joint training. Our findings highlight the substantial potential of specialized MoE architecture and curated training strategies in advancing the field of universal audio generation. Homepage: https://mukioxun.github.io/Uni-MoE-site/home.html</p> + https://arxiv.org/abs/2510.13344 + Wed, 15 Oct 2025 09:30:25 +0000 - Towards General Agentic Intelligence via Environment Scaling - https://arxiv.org/abs/2509.13311 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.13311.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Runnan Fang, Shihao Cai, Baixuan Li, Jialong Wu, Guangyu Li, Wenbiao Yin, Xinyu Wang, Xiaobin Wang, Liangcai Su, Zhen Zhang, Shibin Wu, Zhengwei Tao, Yong Jiang, Pengjun Xie, Fei Huang, Jingren Zhou</p><p><b>Upvotes:</b> 68</p><p><b>Summary:</b> Advanced agentic intelligence is a prerequisite for deploying Large Language Models in practical, real-world applications. Diverse real-world APIs demand precise, robust function-calling intelligence, which needs agents to develop these capabilities through interaction in varied environments. The breadth of function-calling competence is closely tied to the diversity of environments in which agents are trained. In this work, we scale up environments as a step towards advancing general agentic intelligence. This gives rise to two central challenges: (i) how to scale environments in a principled manner, and (ii) how to effectively train agentic capabilities from experiences derived through interactions with these environments. To address these, we design a scalable framework that automatically constructs heterogeneous environments that are fully simulated, systematically broadening the space of function-calling scenarios. We further adapt a two-phase agent fine-tuning strategy: first endowing agents with fundamental agentic capabilities, then specializing them for domain-specific contexts. Extensive experiments on agentic benchmarks, tau-bench, tau2-Bench, and ACEBench, demonstrate that our trained model, AgentScaler, significantly enhances the function-calling capability of models.</p> - https://arxiv.org/abs/2509.13311 - Tue, 16 Sep 2025 17:57:20 +0000 + Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization + https://arxiv.org/abs/2510.13554 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.13554.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yang Li, Zhichen Dong, Yuhan Sun, Weixun Wang, Shaopan Xiong, Yijia Luo, Jiashun Liu, Han Lu, Jiamang Wang, Wenbo Su, Bo Zheng, Junchi Yan</p><p><b>Upvotes:</b> 55</p><p><b>Summary:</b> The reasoning pattern of Large language models (LLMs) remains opaque, and Reinforcement learning (RL) typically applies uniform credit across an entire generation, blurring the distinction between pivotal and routine steps. This work positions attention as a privileged substrate that renders the internal logic of LLMs legible, not merely as a byproduct of computation, but as a mechanistic blueprint of reasoning itself. We first distinguish attention heads between locally and globally focused information processing and reveal that locally focused heads produce a sawtooth pattern near the diagonal indicating phrasal chunks, while globally focused heads expose tokens that exert broad downstream influence over future tokens. We formalize these with two metrics: 1) Windowed Average Attention Distance, which measures the extent of backward attention within a clipped window; 2) Future Attention Influence, which quantifies a token's global importance as the average attention it receives from subsequent tokens. Taken together, these signals reveal a recurring preplan-and-anchor mechanism, where the model first performs a long-range contextual reference to generate an introductory token, which is immediately followed by or coincides with a semantic anchor token that organizes subsequent reasoning. Leveraging these insights, we introduce three novel RL strategies that dynamically perform targeted credit assignment to critical nodes (preplan tokens, anchor tokens, and their temporal coupling) and show consistent performance gains across various reasoning tasks. By aligning optimization with the model's intrinsic reasoning rhythm, we aim to transform opaque optimization into an actionable structure-aware process, hoping to offer a potential step toward more transparent and effective optimization of LLM reasoning.</p> + https://arxiv.org/abs/2510.13554 + Wed, 15 Oct 2025 13:49:51 +0000 - WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research - https://arxiv.org/abs/2509.13312 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.13312.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zijian Li, Xin Guan, Bo Zhang, Shen Huang, Houquan Zhou, Shaopeng Lai, Ming Yan, Yong Jiang, Pengjun Xie, Fei Huang, Jun Zhang, Jingren Zhou</p><p><b>Upvotes:</b> 100</p><p><b>Summary:</b> This paper tackles open-ended deep research (OEDR), a complex challenge where AI agents must synthesize vast web-scale information into insightful reports. Current approaches are plagued by dual-fold limitations: static research pipelines that decouple planning from evidence acquisition and one-shot generation paradigms that easily suffer from long-context failure issues like "loss in the middle" and hallucinations. To address these challenges, we introduce WebWeaver, a novel dual-agent framework that emulates the human research process. The planner operates in a dynamic cycle, iteratively interleaving evidence acquisition with outline optimization to produce a comprehensive, source-grounded outline linking to a memory bank of evidence. The writer then executes a hierarchical retrieval and writing process, composing the report section by section. By performing targeted retrieval of only the necessary evidence from the memory bank for each part, it effectively mitigates long-context issues. Our framework establishes a new state-of-the-art across major OEDR benchmarks, including DeepResearch Bench, DeepConsult, and DeepResearchGym. These results validate our human-centric, iterative methodology, demonstrating that adaptive planning and focused synthesis are crucial for producing high-quality, reliable, and well-structured reports.</p> - https://arxiv.org/abs/2509.13312 - Tue, 16 Sep 2025 17:57:21 +0000 + FlashWorld: High-quality 3D Scene Generation within Seconds + https://arxiv.org/abs/2510.13678 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.13678.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xinyang Li, Tengfei Wang, Zixiao Gu, Shengchuan Zhang, Chunchao Guo, Liujuan Cao</p><p><b>Upvotes:</b> 69</p><p><b>Summary:</b> We propose FlashWorld, a generative model that produces 3D scenes from a single image or text prompt in seconds, 10~100times faster than previous works while possessing superior rendering quality. Our approach shifts from the conventional multi-view-oriented (MV-oriented) paradigm, which generates multi-view images for subsequent 3D reconstruction, to a 3D-oriented approach where the model directly produces 3D Gaussian representations during multi-view generation. While ensuring 3D consistency, 3D-oriented method typically suffers poor visual quality. FlashWorld includes a dual-mode pre-training phase followed by a cross-mode post-training phase, effectively integrating the strengths of both paradigms. Specifically, leveraging the prior from a video diffusion model, we first pre-train a dual-mode multi-view diffusion model, which jointly supports MV-oriented and 3D-oriented generation modes. To bridge the quality gap in 3D-oriented generation, we further propose a cross-mode post-training distillation by matching distribution from consistent 3D-oriented mode to high-quality MV-oriented mode. This not only enhances visual quality while maintaining 3D consistency, but also reduces the required denoising steps for inference. Also, we propose a strategy to leverage massive single-view images and text prompts during this process to enhance the model's generalization to out-of-distribution inputs. Extensive experiments demonstrate the superiority and efficiency of our method.</p> + https://arxiv.org/abs/2510.13678 + Wed, 15 Oct 2025 15:35:48 +0000 - ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization - https://arxiv.org/abs/2509.13313 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.13313.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xixi Wu, Kuan Li, Yida Zhao, Liwen Zhang, Litu Ou, Huifeng Yin, Zhongwang Zhang, Yong Jiang, Pengjun Xie, Fei Huang, Minhao Cheng, Shuai Wang, Hong Cheng, Jingren Zhou</p><p><b>Upvotes:</b> 72</p><p><b>Summary:</b> Large Language Model (LLM)-based web agents demonstrate strong performance on knowledge-intensive tasks but are hindered by context window limitations in paradigms like ReAct. Complex queries involving multiple entities, intertwined relationships, and high uncertainty demand extensive search cycles that rapidly exhaust context budgets before reaching complete solutions. To overcome this challenge, we introduce ReSum, a novel paradigm that enables indefinite exploration through periodic context summarization. ReSum converts growing interaction histories into compact reasoning states, maintaining awareness of prior discoveries while bypassing context constraints. For paradigm adaptation, we propose ReSum-GRPO, integrating GRPO with segmented trajectory training and advantage broadcasting to familiarize agents with summary-conditioned reasoning. Extensive experiments on web agents of varying scales across three benchmarks demonstrate that ReSum delivers an average absolute improvement of 4.5\% over ReAct, with further gains of up to 8.2\% following ReSum-GRPO training. Notably, with only 1K training samples, our WebResummer-30B (a ReSum-GRPO-trained version of WebSailor-30B) achieves 33.3\% Pass@1 on BrowseComp-zh and 18.3\% on BrowseComp-en, surpassing existing open-source web agents.</p> - https://arxiv.org/abs/2509.13313 - Tue, 16 Sep 2025 17:57:22 +0000 + Bee: A High-Quality Corpus and Full-Stack Suite to Unlock Advanced Fully Open MLLMs + https://arxiv.org/abs/2510.13795 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.13795.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yi Zhang, Bolin Ni, Xin-Sheng Chen, Heng-Rui Zhang, Yongming Rao, Houwen Peng, Qinglin Lu, Han Hu, Meng-Hao Guo, Shi-Min Hu</p><p><b>Upvotes:</b> 50</p><p><b>Summary:</b> Fully open multimodal large language models (MLLMs) currently lag behind proprietary counterparts, primarily due to a significant gap in data quality for supervised fine-tuning (SFT). Existing open-source datasets are often plagued by widespread noise and a critical deficit in complex reasoning data, such as Chain-of-Thought (CoT), which hinders the development of advanced model capabilities. Addressing these challenges, our work makes three primary contributions. First, we introduce Honey-Data-15M, a new SFT dataset comprising approximately 15 million QA pairs, processed through multiple cleaning techniques and enhanced with a novel dual-level (short and long) CoT enrichment strategy. Second, we introduce HoneyPipe, the data curation pipeline, and its underlying framework DataStudio, providing the community with a transparent and adaptable methodology for data curation that moves beyond static dataset releases. Finally, to validate our dataset and pipeline, we train Bee-8B, an 8B model on Honey-Data-15M. Experiments show that Bee-8B establishes a new state-of-the-art (SOTA) for fully open MLLMs, achieving performance that is competitive with, and in some cases surpasses, recent semi-open models such as InternVL3.5-8B. Our work delivers to the community a suite of foundational resources, including: the Honey-Data-15M corpus; the full-stack suite comprising HoneyPipe and DataStudio; training recipes; an evaluation harness; and the model weights. This effort demonstrates that a principled focus on data quality is a key pathway to developing fully open MLLMs that are highly competitive with their semi-open counterparts.</p> + https://arxiv.org/abs/2510.13795 + Wed, 15 Oct 2025 17:52:59 +0000 - MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe - https://arxiv.org/abs/2509.18154 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.18154.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tianyu Yu, Zefan Wang, Chongyi Wang, Fuwei Huang, Wenshuo Ma, Zhihui He, Tianchi Cai, Weize Chen, Yuxiang Huang, Yuanqian Zhao, Bokai Xu, Junbo Cui, Yingjing Xu, Liqing Ruan, Luoyuan Zhang, Hanyu Liu, Jingkun Tang, Hongyuan Liu, Qining Guo, Wenhao Hu, Bingxiang He, Jie Zhou, Jie Cai, Ji Qi, Zonghao Guo, Chi Chen, Guoyang Zeng, Yuxuan Li, Ganqu Cui, Ning Ding, Xu Han, Yuan Yao, Zhiyuan Liu, Maosong Sun</p><p><b>Upvotes:</b> 46</p><p><b>Summary:</b> Multimodal Large Language Models (MLLMs) are undergoing rapid progress and represent the frontier of AI development. However, their training and inference efficiency have emerged as a core bottleneck in making MLLMs more accessible and scalable. To address the challenges, we present MiniCPM-V 4.5, an 8B parameter model designed for high efficiency and strong performance. We introduce three core improvements in model architecture, data strategy and training method: a unified 3D-Resampler model architecture for highly compact encoding over images and videos, a unified learning paradigm for document knowledge and text recognition without heavy data engineering, and a hybrid reinforcement learning strategy for proficiency in both short and long reasoning modes. Comprehensive experimental results in OpenCompass evaluation show that MiniCPM-V 4.5 surpasses widely used proprietary models such as GPT-4o-latest, and significantly larger open-source models such as Qwen2.5-VL 72B. Notably, the strong performance is achieved with remarkable efficiency. For example, on the widely adopted VideoMME benchmark, MiniCPM-V 4.5 achieves state-of-the-art performance among models under 30B size, using just 46.7\% GPU memory cost and 8.7\% inference time of Qwen2.5-VL 7B.</p> - https://arxiv.org/abs/2509.18154 - Tue, 16 Sep 2025 19:41:48 +0000 + BitNet Distillation + https://arxiv.org/abs/2510.13998 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.13998.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xun Wu, Shaohan Huang, Wenhui Wang, Ting Song, Li Dong, Yan Xia, Furu Wei</p><p><b>Upvotes:</b> 52</p><p><b>Summary:</b> In this paper, we present BitNet Distillation (BitDistill), a lightweight pipeline that fine-tunes off-the-shelf full-precision LLMs (e.g., Qwen) into 1.58-bit precision (i.e., ternary weights {-1, 0, 1}) for specific downstream tasks, achieving strong task-specific performance with minimal computational cost. Specifically, BitDistill incorporates three key techniques: the SubLN module, as introduced in BitNet; multi-head attention distillation, based on MiniLM; and continual pre-training, which serves as a crucial warm-up step to mitigate the scalability issue of the performance gap between finetuned full-precision and 1.58-bit LLMs on specific tasks. Experimental results show that BitDistill achieves performance comparable to the full-precision counterpart models across model size, while enabling up to 10x memory savings and 2.65x faster inference on CPUs. Code is available at https://github.com/microsoft/BitNet.</p> + https://arxiv.org/abs/2510.13998 + Wed, 15 Oct 2025 18:28:12 +0000 - Hala Technical Report: Building Arabic-Centric Instruction & Translation Models at Scale - https://arxiv.org/abs/2509.14008 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.14008.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hasan Abed Al Kader Hammoud, Mohammad Zbeeb, Bernard Ghanem</p><p><b>Upvotes:</b> 86</p><p><b>Summary:</b> We present Hala, a family of Arabic-centric instruction and translation models built with our translate-and-tune pipeline. We first compress a strong ARleftrightarrowEN teacher to FP8 (yielding sim2times higher throughput with no quality loss) and use it to create high-fidelity bilingual supervision. A lightweight language model LFM2-1.2B is then fine-tuned on this data and used to translate high-quality English instruction sets into Arabic, producing a million-scale corpus tailored to instruction following. We train Hala models at 350M, 700M, 1.2B, and 9B parameters, and apply slerp merging to balance Arabic specialization with base-model strengths. On Arabic-centric benchmarks, Hala achieves state-of-the-art results within both the "nano" (leq2B) and "small" (7-9B) categories, outperforming their bases. We release models, data, evaluation, and recipes to accelerate research in Arabic NLP.</p> - https://arxiv.org/abs/2509.14008 - Wed, 17 Sep 2025 14:19:28 +0000 + AI for Service: Proactive Assistance with AI Glasses + https://arxiv.org/abs/2510.14359 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.14359.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zichen Wen, Yiyu Wang, Chenfei Liao, Boxue Yang, Junxian Li, Weifeng Liu, Haocong He, Bolong Feng, Xuyang Liu, Yuanhuiyi Lyu, Xu Zheng, Xuming Hu, Linfeng Zhang</p><p><b>Upvotes:</b> 72</p><p><b>Summary:</b> In an era where AI is evolving from a passive tool into an active and adaptive companion, we introduce AI for Service (AI4Service), a new paradigm that enables proactive and real-time assistance in daily life. Existing AI services remain largely reactive, responding only to explicit user commands. We argue that a truly intelligent and helpful assistant should be capable of anticipating user needs and taking actions proactively when appropriate. To realize this vision, we propose Alpha-Service, a unified framework that addresses two fundamental challenges: Know When to intervene by detecting service opportunities from egocentric video streams, and Know How to provide both generalized and personalized services. Inspired by the von Neumann computer architecture and based on AI glasses, Alpha-Service consists of five key components: an Input Unit for perception, a Central Processing Unit for task scheduling, an Arithmetic Logic Unit for tool utilization, a Memory Unit for long-term personalization, and an Output Unit for natural human interaction. As an initial exploration, we implement Alpha-Service through a multi-agent system deployed on AI glasses. Case studies, including a real-time Blackjack advisor, a museum tour guide, and a shopping fit assistant, demonstrate its ability to seamlessly perceive the environment, infer user intent, and provide timely and useful assistance without explicit prompts.</p> + https://arxiv.org/abs/2510.14359 + Thu, 16 Oct 2025 06:55:28 +0000 - SAIL-VL2 Technical Report - https://arxiv.org/abs/2509.14033 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.14033.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weijie Yin, Yongjie Ye, Fangxun Shu, Yue Liao, Zijian Kang, Hongyuan Dong, Haiyang Yu, Dingkang Yang, Jiacong Wang, Han Wang, Wenzhuo Liu, Xiao Liang, Shuicheng Yan, Chao Feng</p><p><b>Upvotes:</b> 43</p><p><b>Summary:</b> We introduce SAIL-VL2, an open-suite vision-language foundation model (LVM) for comprehensive multimodal understanding and reasoning. As the successor to SAIL-VL, SAIL-VL2 achieves state-of-the-art performance at the 2B and 8B parameter scales across diverse image and video benchmarks, demonstrating strong capabilities from fine-grained perception to complex reasoning. Three core innovations drive its effectiveness. First, a large-scale data curation pipeline with scoring and filtering strategies enhances both quality and distribution across captioning, OCR, QA, and video data, improving training efficiency. Second, a progressive training framework begins with a powerful pre-trained vision encoder (SAIL-ViT), advances through multimodal pre-training, and culminates in a thinking-fusion SFT-RL hybrid paradigm that systematically strengthens model capabilities. Third, architectural advances extend beyond dense LLMs to efficient sparse Mixture-of-Experts (MoE) designs. With these contributions, SAIL-VL2 demonstrates competitive performance across 106 datasets and achieves state-of-the-art results on challenging reasoning benchmarks such as MMMU and MathVista. Furthermore, on the OpenCompass leaderboard, SAIL-VL2-2B ranks first among officially released open-source models under the 4B parameter scale, while serving as an efficient and extensible foundation for the open-source multimodal community.</p> - https://arxiv.org/abs/2509.14033 - Wed, 17 Sep 2025 14:34:02 +0000 + PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model + https://arxiv.org/abs/2510.14528 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.14528.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Cheng Cui, Ting Sun, Suyin Liang, Tingquan Gao, Zelun Zhang, Jiaxuan Liu, Xueqing Wang, Changda Zhou, Hongen Liu, Manhui Lin, Yue Zhang, Yubo Zhang, Handong Zheng, Jing Zhang, Jun Zhang, Yi Liu, Dianhai Yu, Yanjun Ma</p><p><b>Upvotes:</b> 78</p><p><b>Summary:</b> In this report, we propose PaddleOCR-VL, a SOTA and resource-efficient model tailored for document parsing. Its core component is PaddleOCR-VL-0.9B, a compact yet powerful vision-language model (VLM) that integrates a NaViT-style dynamic resolution visual encoder with the ERNIE-4.5-0.3B language model to enable accurate element recognition. This innovative model efficiently supports 109 languages and excels in recognizing complex elements (e.g., text, tables, formulas, and charts), while maintaining minimal resource consumption. Through comprehensive evaluations on widely used public benchmarks and in-house benchmarks, PaddleOCR-VL achieves SOTA performance in both page-level document parsing and element-level recognition. It significantly outperforms existing solutions, exhibits strong competitiveness against top-tier VLMs, and delivers fast inference speeds. These strengths make it highly suitable for practical deployment in real-world scenarios.</p> + https://arxiv.org/abs/2510.14528 + Thu, 16 Oct 2025 10:18:48 +0000 - Baseer: A Vision-Language Model for Arabic Document-to-Markdown OCR - https://arxiv.org/abs/2509.18174 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.18174.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Khalil Hennara, Muhammad Hreden, Mohamed Motasim Hamed, Ahmad Bastati, Zeina Aldallal, Sara Chrouf, Safwan AlModhayan</p><p><b>Upvotes:</b> 121</p><p><b>Summary:</b> Arabic document OCR remains a challenging task due to the language's cursive script, diverse fonts, diacritics, and right-to-left orientation. While modern Multimodal Large Language Models (MLLMs) have advanced document understanding for high-resource languages, their performance on Arabic remains limited. In this work, we introduce Baseer, a vision-language model fine- tuned specifically for Arabic document OCR. Leveraging a large-scale dataset combining synthetic and real-world documents, Baseer is trained using a decoder-only fine-tuning strategy to adapt a pre-trained MLLM while preserving general visual features. We also present Misraj-DocOCR, a high-quality, expert-verified benchmark designed for rigorous evaluation of Arabic OCR systems. Our experiments show that Baseer significantly outperforms existing open-source and commercial solutions, achieving a WER of 0.25 and establishing a new state-of-the-art in the domain of Arabic document OCR. Our results highlight the benefits of domain-specific adaptation of general-purpose MLLMs and establish a strong baseline for high-accuracy OCR on morphologically rich languages like Arabic.</p> - https://arxiv.org/abs/2509.18174 - Wed, 17 Sep 2025 15:07:29 +0000 + Agentic Entropy-Balanced Policy Optimization + https://arxiv.org/abs/2510.14545 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.14545.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Guanting Dong, Licheng Bao, Zhongyuan Wang, Kangzhi Zhao, Xiaoxi Li, Jiajie Jin, Jinghan Yang, Hangyu Mao, Fuzheng Zhang, Kun Gai, Guorui Zhou, Yutao Zhu, Ji-Rong Wen, Zhicheng Dou</p><p><b>Upvotes:</b> 101</p><p><b>Summary:</b> Recently, Agentic Reinforcement Learning (Agentic RL) has made significant progress in incentivizing the multi-turn, long-horizon tool-use capabilities of web agents. While mainstream agentic RL algorithms autonomously explore high-uncertainty tool-call steps under the guidance of entropy, excessive reliance on entropy signals can impose further constraints, leading to the training collapse. In this paper, we delve into the challenges caused by entropy and propose the Agentic Entropy-Balanced Policy Optimization (AEPO), an agentic RL algorithm designed to balance entropy in both the rollout and policy update phases. AEPO comprises two core components: (1) a dynamic entropy-balanced rollout mechanism that adaptively allocate global and branch sampling budget through entropy pre-monitoring, while imposing a branch penalty on consecutive high-entropy tool-call steps to prevent over-branching issues; and (2) Entropy-Balanced Policy Optimization that inserts a stop-gradient operation into the high-entropy clipping term to preserve and properly rescale gradients on high-entropy tokens, while incorporating entropy-aware advantage estimation to prioritize learning on high-uncertainty tokens. Results across 14 challenging datasets show that AEPO consistently outperforms 7 mainstream RL algorithms. With just 1K RL samples, Qwen3-14B with AEPO achieves impressive results: 47.6% on GAIA, 11.2% on Humanity's Last Exam, and 43.0% on WebWalker for Pass@1; 65.0% on GAIA, 26.0% on Humanity's Last Exam, and 70.0% on WebWalker for Pass@5. Further analysis reveals that AEPO improves rollout sampling diversity while maintaining stable policy entropy, facilitating scalable web agent training.</p> + https://arxiv.org/abs/2510.14545 + Thu, 16 Oct 2025 10:40:52 +0000 - AToken: A Unified Tokenizer for Vision - https://arxiv.org/abs/2509.14476 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.14476.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiasen Lu, Liangchen Song, Mingze Xu, Byeongjoo Ahn, Yanjun Wang, Chen Chen, Afshin Dehghan, Yinfei Yang</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> We present AToken, the first unified visual tokenizer that achieves both high-fidelity reconstruction and semantic understanding across images, videos, and 3D assets. Unlike existing tokenizers that specialize in either reconstruction or understanding for single modalities, AToken encodes these diverse visual inputs into a shared 4D latent space, unifying both tasks and modalities in a single framework. Specifically, we introduce a pure transformer architecture with 4D rotary position embeddings to process visual inputs of arbitrary resolutions and temporal durations. To ensure stable training, we introduce an adversarial-free training objective that combines perceptual and Gram matrix losses, achieving state-of-the-art reconstruction quality. By employing a progressive training curriculum, AToken gradually expands from single images, videos, and 3D, and supports both continuous and discrete latent tokens. AToken achieves 0.21 rFID with 82.2% ImageNet accuracy for images, 3.01 rFVD with 32.6% MSRVTT retrieval for videos, and 28.19 PSNR with 90.9% classification accuracy for 3D. In downstream applications, AToken enables both visual generation tasks (e.g., image generation with continuous and discrete tokens, text-to-video generation, image-to-3D synthesis) and understanding tasks (e.g., multimodal LLMs), achieving competitive performance across all benchmarks. These results shed light on the next-generation multimodal AI systems built upon unified visual tokenization.</p> - https://arxiv.org/abs/2509.14476 - Wed, 17 Sep 2025 23:11:18 +0000 + ImagerySearch: Adaptive Test-Time Search for Video Generation Beyond Semantic Dependency Constraints + https://arxiv.org/abs/2510.14847 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.14847.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Meiqi Wu, Jiashu Zhu, Xiaokun Feng, Chubin Chen, Chen Zhu, Bingze Song, Fangyuan Mao, Jiahong Wu, Xiangxiang Chu, Kaiqi Huang</p><p><b>Upvotes:</b> 55</p><p><b>Summary:</b> Video generation models have achieved remarkable progress, particularly excelling in realistic scenarios; however, their performance degrades notably in imaginative scenarios. These prompts often involve rarely co-occurring concepts with long-distance semantic relationships, falling outside training distributions. Existing methods typically apply test-time scaling for improving video quality, but their fixed search spaces and static reward designs limit adaptability to imaginative scenarios. To fill this gap, we propose ImagerySearch, a prompt-guided adaptive test-time search strategy that dynamically adjusts both the inference search space and reward function according to semantic relationships in the prompt. This enables more coherent and visually plausible videos in challenging imaginative settings. To evaluate progress in this direction, we introduce LDT-Bench, the first dedicated benchmark for long-distance semantic prompts, consisting of 2,839 diverse concept pairs and an automated protocol for assessing creative generation capabilities. Extensive experiments show that ImagerySearch consistently outperforms strong video generation baselines and existing test-time scaling approaches on LDT-Bench, and achieves competitive improvements on VBench, demonstrating its effectiveness across diverse prompt types. We will release LDT-Bench and code to facilitate future research on imaginative video generation.</p> + https://arxiv.org/abs/2510.14847 + Thu, 16 Oct 2025 16:19:13 +0000 - SWE-QA: Can Language Models Answer Repository-level Code Questions? - https://arxiv.org/abs/2509.14635 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.14635.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weihan Peng, Yuling Shi, Yuhang Wang, Xinyun Zhang, Beijun Shen, Xiaodong Gu</p><p><b>Upvotes:</b> 34</p><p><b>Summary:</b> Understanding and reasoning about entire software repositories is an essential capability for intelligent software engineering tools. While existing benchmarks such as CoSQA and CodeQA have advanced the field, they predominantly focus on small, self-contained code snippets. These setups fail to capture the complexity of real-world repositories, where effective understanding and reasoning often require navigating multiple files, understanding software architecture, and grounding answers in long-range code dependencies. In this paper, we present SWE-QA, a repository-level code question answering (QA) benchmark designed to facilitate research on automated QA systems in realistic code environments. SWE-QA involves 576 high-quality question-answer pairs spanning diverse categories, including intention understanding, cross-file reasoning, and multi-hop dependency analysis. To construct SWE-QA, we first crawled 77,100 GitHub issues from 11 popular repositories. Based on an analysis of naturally occurring developer questions extracted from these issues, we developed a two-level taxonomy of repository-level questions and constructed a set of seed questions for each category. For each category, we manually curated and validated questions and collected their corresponding answers. As a prototype application, we further develop SWE-QA-Agent, an agentic framework in which LLM agents reason and act to find answers automatically. We evaluate six advanced LLMs on SWE-QA under various context augmentation strategies. Experimental results highlight the promise of LLMs, particularly our SWE-QA-Agent framework, in addressing repository-level QA, while also revealing open challenges and pointing to future research directions.</p> - https://arxiv.org/abs/2509.14635 - Thu, 18 Sep 2025 05:25:32 +0000 + NANO3D: A Training-Free Approach for Efficient 3D Editing Without Masks + https://arxiv.org/abs/2510.15019 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.15019.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junliang Ye, Shenghao Xie, Ruowen Zhao, Zhengyi Wang, Hongyu Yan, Wenqiang Zu, Lei Ma, Jun Zhu</p><p><b>Upvotes:</b> 61</p><p><b>Summary:</b> 3D object editing is essential for interactive content creation in gaming, animation, and robotics, yet current approaches remain inefficient, inconsistent, and often fail to preserve unedited regions. Most methods rely on editing multi-view renderings followed by reconstruction, which introduces artifacts and limits practicality. To address these challenges, we propose Nano3D, a training-free framework for precise and coherent 3D object editing without masks. Nano3D integrates FlowEdit into TRELLIS to perform localized edits guided by front-view renderings, and further introduces region-aware merging strategies, Voxel/Slat-Merge, which adaptively preserve structural fidelity by ensuring consistency between edited and unedited areas. Experiments demonstrate that Nano3D achieves superior 3D consistency and visual quality compared with existing methods. Based on this framework, we construct the first large-scale 3D editing datasets Nano3D-Edit-100k, which contains over 100,000 high-quality 3D editing pairs. This work addresses long-standing challenges in both algorithm design and data availability, significantly improving the generality and reliability of 3D editing, and laying the groundwork for the development of feed-forward 3D editing models. Project Page:https://jamesyjl.github.io/Nano3D</p> + https://arxiv.org/abs/2510.15019 + Thu, 16 Oct 2025 17:51:50 +0000 - Reasoning over Boundaries: Enhancing Specification Alignment via Test-time Delibration - https://arxiv.org/abs/2509.14760 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.14760.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haoran Zhang, Yafu Li, Xuyang Hu, Dongrui Liu, Zhilin Wang, Bo Li, Yu Cheng</p><p><b>Upvotes:</b> 50</p><p><b>Summary:</b> Large language models (LLMs) are increasingly applied in diverse real-world scenarios, each governed by bespoke behavioral and safety specifications (spec) custom-tailored by users or organizations. These spec, categorized into safety-spec and behavioral-spec, vary across scenarios and evolve with changing preferences and requirements. We formalize this challenge as specification alignment, focusing on LLMs' ability to follow dynamic, scenario-specific spec from both behavioral and safety perspectives. To address this challenge, we propose Align3, a lightweight method that employs Test-Time Deliberation (TTD) with hierarchical reflection and revision to reason over the specification boundaries. We further present SpecBench, a unified benchmark for measuring specification alignment, covering 5 scenarios, 103 spec, and 1,500 prompts. Experiments on 15 reasoning and 18 instruct models with several TTD methods, including Self-Refine, TPO, and MoreThink, yield three key findings: (i) test-time deliberation enhances specification alignment; (ii) Align3 advances the safety-helpfulness trade-off frontier with minimal overhead; (iii) SpecBench effectively reveals alignment gaps. These results highlight the potential of test-time deliberation as an effective strategy for reasoning over the real-world specification boundaries.</p> - https://arxiv.org/abs/2509.14760 - Thu, 18 Sep 2025 09:08:53 +0000 + WithAnyone: Towards Controllable and ID Consistent Image Generation + https://arxiv.org/abs/2510.14975 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.14975.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hengyuan Xu, Wei Cheng, Peng Xing, Yixiao Fang, Shuhan Wu, Rui Wang, Xianfang Zeng, Daxin Jiang, Gang Yu, Xingjun Ma, Yu-Gang Jiang</p><p><b>Upvotes:</b> 79</p><p><b>Summary:</b> Identity-consistent generation has become an important focus in text-to-image research, with recent models achieving notable success in producing images aligned with a reference identity. Yet, the scarcity of large-scale paired datasets containing multiple images of the same individual forces most approaches to adopt reconstruction-based training. This reliance often leads to a failure mode we term copy-paste, where the model directly replicates the reference face rather than preserving identity across natural variations in pose, expression, or lighting. Such over-similarity undermines controllability and limits the expressive power of generation. To address these limitations, we (1) construct a large-scale paired dataset MultiID-2M, tailored for multi-person scenarios, providing diverse references for each identity; (2) introduce a benchmark that quantifies both copy-paste artifacts and the trade-off between identity fidelity and variation; and (3) propose a novel training paradigm with a contrastive identity loss that leverages paired data to balance fidelity with diversity. These contributions culminate in WithAnyone, a diffusion-based model that effectively mitigates copy-paste while preserving high identity similarity. Extensive qualitative and quantitative experiments demonstrate that WithAnyone significantly reduces copy-paste artifacts, improves controllability over pose and expression, and maintains strong perceptual quality. User studies further validate that our method achieves high identity fidelity while enabling expressive controllable generation.</p> + https://arxiv.org/abs/2510.14975 + Thu, 16 Oct 2025 17:59:54 +0000 - Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation - https://arxiv.org/abs/2509.15194 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.15194.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yujun Zhou, Zhenwen Liang, Haolin Liu, Wenhao Yu, Kishan Panaganti, Linfeng Song, Dian Yu, Xiangliang Zhang, Haitao Mi, Dong Yu</p><p><b>Upvotes:</b> 32</p><p><b>Summary:</b> Large language models (LLMs) are increasingly trained with reinforcement learning from verifiable rewards (RLVR), yet real-world deployment demands models that can self-improve without labels or external judges. Existing label-free methods, confidence minimization, self-consistency, or majority-vote objectives, stabilize learning but steadily shrink exploration, causing an entropy collapse: generations become shorter, less diverse, and brittle. Unlike prior approaches such as Test-Time Reinforcement Learning (TTRL), which primarily adapt models to the immediate unlabeled dataset at hand, our goal is broader: to enable general improvements without sacrificing the model's inherent exploration capacity and generalization ability, i.e., evolving. We formalize this issue and propose EVolution-Oriented and Label-free Reinforcement Learning (EVOL-RL), a simple rule that couples stability with variation under a label-free setting. EVOL-RL keeps the majority-voted answer as a stable anchor (selection) while adding a novelty-aware reward that favors responses whose reasoning differs from what has already been produced (variation), measured in semantic space. Implemented with GRPO, EVOL-RL also uses asymmetric clipping to preserve strong signals and an entropy regularizer to sustain search. This majority-for-selection + novelty-for-variation design prevents collapse, maintains longer and more informative chains of thought, and improves both pass@1 and pass@n. EVOL-RL consistently outperforms the majority-only TTRL baseline; e.g., training on label-free AIME24 lifts Qwen3-4B-Base AIME25 pass@1 from TTRL's 4.6% to 16.4%, and pass@16 from 18.5% to 37.9%. EVOL-RL not only prevents diversity collapse but also unlocks stronger generalization across domains (e.g., GPQA). Furthermore, we demonstrate that EVOL-RL also boosts performance in the RLVR setting, highlighting its broad applicability.</p> - https://arxiv.org/abs/2509.15194 - Thu, 18 Sep 2025 17:50:04 +0000 + From Pixels to Words -- Towards Native Vision-Language Primitives at Scale + https://arxiv.org/abs/2510.14979 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.14979.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haiwen Diao, Mingxuan Li, Silei Wu, Linjun Dai, Xiaohua Wang, Hanming Deng, Lewei Lu, Dahua Lin, Ziwei Liu</p><p><b>Upvotes:</b> 65</p><p><b>Summary:</b> The edifice of native Vision-Language Models (VLMs) has emerged as a rising contender to typical modular VLMs, shaped by evolving model architectures and training paradigms. Yet, two lingering clouds cast shadows over its widespread exploration and promotion: (-) What fundamental constraints set native VLMs apart from modular ones, and to what extent can these barriers be overcome? (-) How to make research in native VLMs more accessible and democratized, thereby accelerating progress in the field. In this paper, we clarify these challenges and outline guiding principles for constructing native VLMs. Specifically, one native VLM primitive should: (i) effectively align pixel and word representations within a shared semantic space; (ii) seamlessly integrate the strengths of formerly separate vision and language modules; (iii) inherently embody various cross-modal properties that support unified vision-language encoding, aligning, and reasoning. Hence, we launch NEO, a novel family of native VLMs built from first principles, capable of rivaling top-tier modular counterparts across diverse real-world scenarios. With only 390M image-text examples, NEO efficiently develops visual perception from scratch while mitigating vision-language conflicts inside a dense and monolithic model crafted from our elaborate primitives. We position NEO as a cornerstone for scalable and powerful native VLMs, paired with a rich set of reusable components that foster a cost-effective and extensible ecosystem. Our code and models are publicly available at: https://github.com/EvolvingLMMs-Lab/NEO.</p> + https://arxiv.org/abs/2510.14979 + Thu, 16 Oct 2025 17:59:58 +0000 - FlowRL: Matching Reward Distributions for LLM Reasoning - https://arxiv.org/abs/2509.15207 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.15207.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xuekai Zhu, Daixuan Cheng, Dinghuai Zhang, Hengli Li, Kaiyan Zhang, Che Jiang, Youbang Sun, Ermo Hua, Yuxin Zuo, Xingtai Lv, Qizheng Zhang, Lin Chen, Fanghao Shao, Bo Xue, Yunchong Song, Zhenjie Yang, Ganqu Cui, Ning Ding, Jianfeng Gao, Xiaodong Liu, Bowen Zhou, Hongyuan Mei, Zhouhan Lin</p><p><b>Upvotes:</b> 103</p><p><b>Summary:</b> We propose FlowRL: matching the full reward distribution via flow balancing instead of maximizing rewards in large language model (LLM) reinforcement learning (RL). Recent advanced reasoning models adopt reward-maximizing methods (\eg, PPO and GRPO), which tend to over-optimize dominant reward signals while neglecting less frequent but valid reasoning paths, thus reducing diversity. In contrast, we transform scalar rewards into a normalized target distribution using a learnable partition function, and then minimize the reverse KL divergence between the policy and the target distribution. We implement this idea as a flow-balanced optimization method that promotes diverse exploration and generalizable reasoning trajectories. We conduct experiments on math and code reasoning tasks: FlowRL achieves a significant average improvement of 10.0% over GRPO and 5.1% over PPO on math benchmarks, and performs consistently better on code reasoning tasks. These results highlight reward distribution-matching as a key step toward efficient exploration and diverse reasoning in LLM reinforcement learning.</p> - https://arxiv.org/abs/2509.15207 - Thu, 18 Sep 2025 17:56:36 +0000 + Latent Diffusion Model without Variational Autoencoder + https://arxiv.org/abs/2510.15301 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.15301.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Minglei Shi, Haolin Wang, Wenzhao Zheng, Ziyang Yuan, Xiaoshi Wu, Xintao Wang, Pengfei Wan, Jie Zhou, Jiwen Lu</p><p><b>Upvotes:</b> 48</p><p><b>Summary:</b> Recent progress in diffusion-based visual generation has largely relied on latent diffusion models with variational autoencoders (VAEs). While effective for high-fidelity synthesis, this VAE+diffusion paradigm suffers from limited training efficiency, slow inference, and poor transferability to broader vision tasks. These issues stem from a key limitation of VAE latent spaces: the lack of clear semantic separation and strong discriminative structure. Our analysis confirms that these properties are crucial not only for perception and understanding tasks, but also for the stable and efficient training of latent diffusion models. Motivated by this insight, we introduce SVG, a novel latent diffusion model without variational autoencoders, which leverages self-supervised representations for visual generation. SVG constructs a feature space with clear semantic discriminability by leveraging frozen DINO features, while a lightweight residual branch captures fine-grained details for high-fidelity reconstruction. Diffusion models are trained directly on this semantically structured latent space to facilitate more efficient learning. As a result, SVG enables accelerated diffusion training, supports few-step sampling, and improves generative quality. Experimental results further show that SVG preserves the semantic and discriminative capabilities of the underlying self-supervised representations, providing a principled pathway toward task-general, high-quality visual representations.</p> + https://arxiv.org/abs/2510.15301 + Fri, 17 Oct 2025 04:17:44 +0000 - ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data - https://arxiv.org/abs/2509.15221 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.15221.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhaoyang Liu, JingJing Xie, Zichen Ding, Zehao Li, Bowen Yang, Zhenyu Wu, Xuehui Wang, Qiushi Sun, Shi Liu, Weiyun Wang, Shenglong Ye, Qingyun Li, Zeyue Tian, Gen Luo, Xiangyu Yue, Biqing Qi, Kai Chen, Bowen Zhou, Yu Qiao, Qifeng Chen, Wenhai Wang</p><p><b>Upvotes:</b> 102</p><p><b>Summary:</b> Vision-Language Models (VLMs) have enabled computer use agents (CUAs) that operate GUIs autonomously, showing great potential, yet progress is limited by the lack of large-scale, open-source computer use data and foundation models. In this work, we introduce ScaleCUA, a step toward scaling open-source CUAs. It offers a large-scale dataset spanning 6 operating systems and 3 task domains, built via a closed-loop pipeline uniting automated agents with human experts. Trained on this scaled-up data, ScaleCUA can operate seamlessly across platforms. Specifically, it delivers strong gains over baselines (+26.6 on WebArena-Lite-v2, +10.7 on ScreenSpot-Pro) and sets new state-of-the-art results (94.4% on MMBench-GUI L1-Hard, 60.6% on OSWorld-G, 47.4% on WebArena-Lite-v2). These findings underscore the power of data-driven scaling for general-purpose computer use agents. We will release data, models, and code to advance future research: https://github.com/OpenGVLab/ScaleCUA.</p> - https://arxiv.org/abs/2509.15221 - Thu, 18 Sep 2025 17:59:22 +0000 + A Theoretical Study on Bridging Internal Probability and Self-Consistency for LLM Reasoning + https://arxiv.org/abs/2510.15444 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.15444.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhi Zhou, Yuhao Tan, Zenan Li, Yuan Yao, Lan-Zhe Guo, Yu-Feng Li, Xiaoxing Ma</p><p><b>Upvotes:</b> 144</p><p><b>Summary:</b> Test-time scaling seeks to improve the reasoning performance of large language models (LLMs) by adding computational resources. A prevalent approach within the field is sampling-based test-time scaling methods, which enhance reasoning by generating multiple reasoning paths for a given input during inference. However, despite its practical success, the theoretical foundations remain underexplored. In this paper, we provide the first theoretical framework for analyzing sampling-based test-time scaling methods, grounded in the perspective of confidence estimation. Based on the framework, we analyze two dominant paradigms: self-consistency and perplexity, and reveal key limitations: self-consistency suffers from high estimation error while perplexity exhibits substantial modeling error and possible degradation of the estimation error convergence. To address these limitations, we introduce RPC, a hybrid method that leverages our theoretical insights through two key components: Perplexity Consistency and Reasoning Pruning. Perplexity Consistency combines the strengths of self-consistency and perplexity, boosting the convergence rate of estimation error from linear to exponential while preserving model error. Reasoning Pruning prevents degradation by eliminating low-probability reasoning paths. Both theoretical analysis and empirical results across seven benchmark datasets demonstrate that RPC has a strong potential for reducing reasoning error. Notably, RPC achieves reasoning performance comparable to self-consistency while not only enhancing confidence reliability but also reducing sampling costs by 50%. The code and resources are available at https://wnjxyk.github.io/RPC.</p> + https://arxiv.org/abs/2510.15444 + Fri, 17 Oct 2025 08:59:30 +0000 - Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification - https://arxiv.org/abs/2509.15591 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.15591.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zinan Lin, Enshu Liu, Xuefei Ning, Junyi Zhu, Wenyu Wang, Sergey Yekhanin</p><p><b>Upvotes:</b> 44</p><p><b>Summary:</b> Generative modeling, representation learning, and classification are three core problems in machine learning (ML), yet their state-of-the-art (SoTA) solutions remain largely disjoint. In this paper, we ask: Can a unified principle address all three? Such unification could simplify ML pipelines and foster greater synergy across tasks. We introduce Latent Zoning Network (LZN) as a step toward this goal. At its core, LZN creates a shared Gaussian latent space that encodes information across all tasks. Each data type (e.g., images, text, labels) is equipped with an encoder that maps samples to disjoint latent zones, and a decoder that maps latents back to data. ML tasks are expressed as compositions of these encoders and decoders: for example, label-conditional image generation uses a label encoder and image decoder; image embedding uses an image encoder; classification uses an image encoder and label decoder. We demonstrate the promise of LZN in three increasingly complex scenarios: (1) LZN can enhance existing models (image generation): When combined with the SoTA Rectified Flow model, LZN improves FID on CIFAR10 from 2.76 to 2.59-without modifying the training objective. (2) LZN can solve tasks independently (representation learning): LZN can implement unsupervised representation learning without auxiliary loss functions, outperforming the seminal MoCo and SimCLR methods by 9.3% and 0.2%, respectively, on downstream linear classification on ImageNet. (3) LZN can solve multiple tasks simultaneously (joint generation and classification): With image and label encoders/decoders, LZN performs both tasks jointly by design, improving FID and achieving SoTA classification accuracy on CIFAR10. The code and trained models are available at https://github.com/microsoft/latent-zoning-networks. The project website is at https://zinanlin.me/blogs/latent_zoning_networks.html.</p> - https://arxiv.org/abs/2509.15591 - Fri, 19 Sep 2025 04:47:16 +0000 + Language Models are Injective and Hence Invertible + https://arxiv.org/abs/2510.15511 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.15511.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Giorgos Nikolaou, Tommaso Mencattini, Donato Crisostomi, Andrea Santilli, Yannis Panagakis, Emanuele Rodola'</p><p><b>Upvotes:</b> 61</p><p><b>Summary:</b> Transformer components such as non-linear activations and normalization are inherently non-injective, suggesting that different inputs could map to the same output and prevent exact recovery of the input from a model's representations. In this paper, we challenge this view. First, we prove mathematically that transformer language models mapping discrete input sequences to their corresponding sequence of continuous representations are injective and therefore lossless, a property established at initialization and preserved during training. Second, we confirm this result empirically through billions of collision tests on six state-of-the-art language models, and observe no collisions. Third, we operationalize injectivity: we introduce SipIt, the first algorithm that provably and efficiently reconstructs the exact input text from hidden activations, establishing linear-time guarantees and demonstrating exact invertibility in practice. Overall, our work establishes injectivity as a fundamental and exploitable property of language models, with direct implications for transparency, interpretability, and safe deployment.</p> + https://arxiv.org/abs/2510.15511 + Fri, 17 Oct 2025 10:25:30 +0000 - MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer - https://arxiv.org/abs/2509.16197 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.16197.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yanghao Li, Rui Qian, Bowen Pan, Haotian Zhang, Haoshuo Huang, Bowen Zhang, Jialing Tong, Haoxuan You, Xianzhi Du, Zhe Gan, Hyunjik Kim, Chao Jia, Zhenbang Wang, Yinfei Yang, Mingfei Gao, Zi-Yi Dou, Wenze Hu, Chang Gao, Dongxu Li, Philipp Dufter, Zirui Wang, Guoli Yin, Zhengdong Zhang, Chen Chen, Yang Zhao, Ruoming Pang, Zhifeng Chen</p><p><b>Upvotes:</b> 49</p><p><b>Summary:</b> Unified multimodal Large Language Models (LLMs) that can both understand and generate visual content hold immense potential. However, existing open-source models often suffer from a performance trade-off between these capabilities. We present Manzano, a simple and scalable unified framework that substantially reduces this tension by coupling a hybrid image tokenizer with a well-curated training recipe. A single shared vision encoder feeds two lightweight adapters that produce continuous embeddings for image-to-text understanding and discrete tokens for text-to-image generation within a common semantic space. A unified autoregressive LLM predicts high-level semantics in the form of text and image tokens, with an auxiliary diffusion decoder subsequently translating the image tokens into pixels. The architecture, together with a unified training recipe over understanding and generation data, enables scalable joint learning of both capabilities. Manzano achieves state-of-the-art results among unified models, and is competitive with specialist models, particularly on text-rich evaluation. Our studies show minimal task conflicts and consistent gains from scaling model size, validating our design choice of a hybrid tokenizer.</p> - https://arxiv.org/abs/2509.16197 - Fri, 19 Sep 2025 17:58:00 +0000 + Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset + https://arxiv.org/abs/2510.15742 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.15742.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qingyan Bai, Qiuyu Wang, Hao Ouyang, Yue Yu, Hanlin Wang, Wen Wang, Ka Leong Cheng, Shuailei Ma, Yanhong Zeng, Zichen Liu, Yinghao Xu, Yujun Shen, Qifeng Chen</p><p><b>Upvotes:</b> 49</p><p><b>Summary:</b> Instruction-based video editing promises to democratize content creation, yet its progress is severely hampered by the scarcity of large-scale, high-quality training data. We introduce Ditto, a holistic framework designed to tackle this fundamental challenge. At its heart, Ditto features a novel data generation pipeline that fuses the creative diversity of a leading image editor with an in-context video generator, overcoming the limited scope of existing models. To make this process viable, our framework resolves the prohibitive cost-quality trade-off by employing an efficient, distilled model architecture augmented by a temporal enhancer, which simultaneously reduces computational overhead and improves temporal coherence. Finally, to achieve full scalability, this entire pipeline is driven by an intelligent agent that crafts diverse instructions and rigorously filters the output, ensuring quality control at scale. Using this framework, we invested over 12,000 GPU-days to build Ditto-1M, a new dataset of one million high-fidelity video editing examples. We trained our model, Editto, on Ditto-1M with a curriculum learning strategy. The results demonstrate superior instruction-following ability and establish a new state-of-the-art in instruction-based video editing.</p> + https://arxiv.org/abs/2510.15742 + Fri, 17 Oct 2025 15:31:40 +0000 - RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation - https://arxiv.org/abs/2509.16198 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.16198.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jane Luo, Xin Zhang, Steven Liu, Jie Wu, Yiming Huang, Yangyu Huang, Chengyu Yin, Ying Xin, Jianfeng Liu, Yuefeng Zhan, Hao Sun, Qi Chen, Scarlett Li, Mao Yang</p><p><b>Upvotes:</b> 119</p><p><b>Summary:</b> Large language models excel at function- and file-level code generation, yet generating complete repositories from scratch remains a fundamental challenge. This process demands coherent and reliable planning across proposal- and implementation-level stages, while natural language, due to its ambiguity and verbosity, is ill-suited for faithfully representing complex software structures. To address this, we introduce the Repository Planning Graph (RPG), a persistent representation that unifies proposal- and implementation-level planning by encoding capabilities, file structures, data flows, and functions in one graph. RPG replaces ambiguous natural language with an explicit blueprint, enabling long-horizon planning and scalable repository generation. Building on RPG, we develop ZeroRepo, a graph-driven framework for repository generation from scratch. It operates in three stages: proposal-level planning and implementation-level refinement to construct the graph, followed by graph-guided code generation with test validation. To evaluate this setting, we construct RepoCraft, a benchmark of six real-world projects with 1,052 tasks. On RepoCraft, ZeroRepo produces repositories averaging nearly 36K LOC, roughly 3.9times the strongest baseline (Claude Code) and about 64times other baselines. It attains 81.5% functional coverage and a 69.7% pass rate, exceeding Claude Code by 27.3 and 35.8 percentage points, respectively. Further analysis shows that RPG models complex dependencies, enables progressively more sophisticated planning through near-linear scaling, and enhances LLM understanding of repositories, thereby accelerating agent localization.</p> - https://arxiv.org/abs/2509.16198 - Fri, 19 Sep 2025 17:58:14 +0000 + OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM + https://arxiv.org/abs/2510.15870 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.15870.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hanrong Ye, Chao-Han Huck Yang, Arushi Goel, Wei Huang, Ligeng Zhu, Yuanhang Su, Sean Lin, An-Chieh Cheng, Zhen Wan, Jinchuan Tian, Yuming Lou, Dong Yang, Zhijian Liu, Yukang Chen, Ambrish Dantrey, Ehsan Jahangiri, Sreyan Ghosh, Daguang Xu, Ehsan Hosseini-Asl, Danial Mohseni Taheri, Vidya Murali, Sifei Liu, Jason Lu, Oluwatobi Olabiyi, Frank Wang, Rafael Valle, Bryan Catanzaro, Andrew Tao, Song Han, Jan Kautz, Hongxu Yin, Pavlo Molchanov</p><p><b>Upvotes:</b> 85</p><p><b>Summary:</b> Advancing machine intelligence requires developing the ability to perceive across multiple modalities, much as humans sense the world. We introduce OmniVinci, an initiative to build a strong, open-source, omni-modal LLM. We carefully study the design choices across model architecture and data curation. For model architecture, we present three key innovations: (i) OmniAlignNet for strengthening alignment between vision and audio embeddings in a shared omni-modal latent space; (ii) Temporal Embedding Grouping for capturing relative temporal alignment between vision and audio signals; and (iii) Constrained Rotary Time Embedding for encoding absolute temporal information in omni-modal embeddings. We introduce a curation and synthesis pipeline that generates 24M single-modal and omni-modal conversations. We find that modalities reinforce one another in both perception and reasoning. Our model, OmniVinci, outperforms Qwen2.5-Omni with +19.05 on DailyOmni (cross-modal understanding), +1.7 on MMAR (audio), and +3.9 on Video-MME (vision), while using just 0.2T training tokens - a 6 times reduction compared to Qwen2.5-Omni's 1.2T. We finally demonstrate omni-modal advantages in downstream applications spanning robotics, medical AI, and smart factory.</p> + https://arxiv.org/abs/2510.15870 + Fri, 17 Oct 2025 17:59:59 +0000 - ARE: Scaling Up Agent Environments and Evaluations - https://arxiv.org/abs/2509.17158 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.17158.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Pierre Andrews, Amine Benhalloum, Gerard Moreno-Torres Bertran, Matteo Bettini, Amar Budhiraja, Ricardo Silveira Cabral, Virginie Do, Romain Froger, Emilien Garreau, Jean-Baptiste Gaya, Hugo Laurençon, Maxime Lecanu, Kunal Malkan, Dheeraj Mekala, Pierre Ménard, Grégoire Mialon, Ulyana Piterbarg, Mikhail Plekhanov, Mathieu Rita, Andrey Rusakov, Thomas Scialom, Vladislav Vorotilov, Mengjue Wang, Ian Yu</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> We introduce Meta Agents Research Environments (ARE), a research platform for scalable creation of environments, integration of synthetic or real applications, and execution of agentic orchestrations. ARE provides simple abstractions to build complex and diverse environments, each with their own rules, tools, content, and verifiers, helping to bridge the gap between model development and real-world deployment. We also propose Gaia2, a benchmark built in ARE and designed to measure general agent capabilities. Beyond search and execution, Gaia2 requires agents to handle ambiguities and noise, adapt to dynamic environments, collaborate with other agents, and operate under temporal constraints. Unlike prior benchmarks, Gaia2 runs asynchronously, surfacing new failure modes that are invisible in static settings. Our experiments show that no system dominates across the intelligence spectrum: stronger reasoning often comes at the cost of efficiency, and budget scaling curves plateau, highlighting the need for new architectures and adaptive compute strategies. Perhaps more importantly, ARE abstractions enable continuous extension of Gaia2 to other environments, empowering the community to rapidly create new benchmarks tailored to their domains. In AI's second half, progress increasingly depends on defining meaningful tasks and robust evaluations to drive frontier capabilities forward.</p> - https://arxiv.org/abs/2509.17158 - Sun, 21 Sep 2025 16:59:45 +0000 + RL makes MLLMs see better than SFT + https://arxiv.org/abs/2510.16333 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.16333.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junha Song, Sangdoo Yun, Dongyoon Han, Jaegul Choo, Byeongho Heo</p><p><b>Upvotes:</b> 47</p><p><b>Summary:</b> A dominant assumption in Multimodal Language Model (MLLM) research is that its performance is largely inherited from the LLM backbone, given its immense parameter scale and remarkable capabilities. This has created a void in the understanding of the vision encoder, which determines how MLLMs perceive images. The recent shift in MLLM training paradigms, from Supervised Finetuning (SFT) to Reinforcement Learning (RL), magnifies this oversight-namely, the significant lack of analysis on how such training reshapes the vision encoder as well as the MLLM. To address this, we first investigate the impact of training strategies on MLLMs, where RL shows a clear advantage over SFT in strongly vision-related VQA benchmarks. Motivated by this, we conduct a critical yet under-explored analysis of the vision encoder of MLLMs through diverse and in-depth experiments, ranging from ImageNet classification and segmentation to gradient visualization. Our results demonstrate that MLLM's post-training strategy (i.e., SFT or RL) not only leads to distinct outcomes on MLLM downstream tasks, but also fundamentally reshapes MLLM's underlying visual representations. Specifically, the key finding of our study is that RL produces stronger and precisely localized visual representations compared to SFT, boosting the ability of the vision encoder for MLLM. We then reframe our findings into a simple recipe for building strong vision encoders for MLLMs, Preference-Instructed Vision OpTimization (PIVOT). When integrated into MLLMs, a PIVOT-trained vision encoder outperforms even larger and more heavily-trained counterparts, despite requiring less than 1% of the computational cost of standard vision pretraining. This result opens an effective and efficient path for advancing the vision backbones of MLLMs. Project page available at https://june-page.github.io/pivot/</p> + https://arxiv.org/abs/2510.16333 + Sat, 18 Oct 2025 03:37:17 +0000 - LIMI: Less is More for Agency - https://arxiv.org/abs/2509.17567 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.17567.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yang Xiao, Mohan Jiang, Jie Sun, Keyu Li, Jifan Lin, Yumin Zhuang, Ji Zeng, Shijie Xia, Qishuo Hua, Xuefeng Li, Xiaojie Cai, Tongyu Wang, Yue Zhang, Liming Liu, Xia Wu, Jinlong Hou, Yuan Cheng, Wenjie Li, Xiang Wang, Dequan Wang, Pengfei Liu</p><p><b>Upvotes:</b> 94</p><p><b>Summary:</b> We define Agency as the emergent capacity of AI systems to function as autonomous agents actively discovering problems, formulating hypotheses, and executing solutions through self-directed engagement with environments and tools. This fundamental capability marks the dawn of the Age of AI Agency, driven by a critical industry shift: the urgent need for AI systems that don't just think, but work. While current AI excels at reasoning and generating responses, industries demand autonomous agents that can execute tasks, operate tools, and drive real-world outcomes. As agentic intelligence becomes the defining characteristic separating cognitive systems from productive workers, efficiently cultivating machine autonomy becomes paramount. Current approaches assume that more data yields better agency, following traditional scaling laws from language modeling. We fundamentally challenge this paradigm. LIMI (Less Is More for Intelligent Agency) demonstrates that agency follows radically different development principles. Through strategic focus on collaborative software development and scientific research workflows, we show that sophisticated agentic intelligence can emerge from minimal but strategically curated demonstrations of autonomous behavior. Using only 78 carefully designed training samples, LIMI achieves 73.5% on comprehensive agency benchmarks, dramatically outperforming state-of-the-art models: Kimi-K2-Instruct (24.1%), DeepSeek-V3.1 (11.9%), Qwen3-235B-A22B-Instruct (27.5%), and GLM-4.5 (45.1%). Most strikingly, LIMI demonstrates 53.7% improvement over models trained on 10,000 samples-achieving superior agentic intelligence with 128 times fewer samples. Our findings establish the Agency Efficiency Principle: machine autonomy emerges not from data abundance but from strategic curation of high-quality agentic demonstrations.</p> - https://arxiv.org/abs/2509.17567 - Mon, 22 Sep 2025 10:59:32 +0000 + DeepAnalyze: Agentic Large Language Models for Autonomous Data Science + https://arxiv.org/abs/2510.16872 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.16872.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shaolei Zhang, Ju Fan, Meihao Fan, Guoliang Li, Xiaoyong Du</p><p><b>Upvotes:</b> 90</p><p><b>Summary:</b> Autonomous data science, from raw data sources to analyst-grade deep research reports, has been a long-standing challenge, and is now becoming feasible with the emergence of powerful large language models (LLMs). Recent workflow-based data agents have shown promising results on specific data tasks but remain fundamentally limited in achieving fully autonomous data science due to their reliance on predefined workflows. In this paper, we introduce DeepAnalyze-8B, the first agentic LLM designed for autonomous data science, capable of automatically completing the end-toend pipeline from data sources to analyst-grade deep research reports. To tackle high-complexity data science tasks, we propose a curriculum-based agentic training paradigm that emulates the learning trajectory of human data scientists, enabling LLMs to progressively acquire and integrate multiple capabilities in real-world environments. We also introduce a data-grounded trajectory synthesis framework that constructs high-quality training data. Through agentic training, DeepAnalyze learns to perform a broad spectrum of data tasks, ranging from data question answering and specialized analytical tasks to open-ended data research. Experiments demonstrate that, with only 8B parameters, DeepAnalyze outperforms previous workflow-based agents built on most advanced proprietary LLMs. The model, code, and training data of DeepAnalyze are open-sourced, paving the way toward autonomous data science.</p> + https://arxiv.org/abs/2510.16872 + Sun, 19 Oct 2025 15:13:42 +0000 - OmniInsert: Mask-Free Video Insertion of Any Reference via Diffusion Transformer Models - https://arxiv.org/abs/2509.17627 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.17627.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jinshu Chen, Xinghui Li, Xu Bai, Tianxiang Ma, Pengze Zhang, Zhuowei Chen, Gen Li, Lijie Liu, Songtao Zhao, Bingchuan Li, Qian He</p><p><b>Upvotes:</b> 63</p><p><b>Summary:</b> Recent advances in video insertion based on diffusion models are impressive. However, existing methods rely on complex control signals but struggle with subject consistency, limiting their practical applicability. In this paper, we focus on the task of Mask-free Video Insertion and aim to resolve three key challenges: data scarcity, subject-scene equilibrium, and insertion harmonization. To address the data scarcity, we propose a new data pipeline InsertPipe, constructing diverse cross-pair data automatically. Building upon our data pipeline, we develop OmniInsert, a novel unified framework for mask-free video insertion from both single and multiple subject references. Specifically, to maintain subject-scene equilibrium, we introduce a simple yet effective Condition-Specific Feature Injection mechanism to distinctly inject multi-source conditions and propose a novel Progressive Training strategy that enables the model to balance feature injection from subjects and source video. Meanwhile, we design the Subject-Focused Loss to improve the detailed appearance of the subjects. To further enhance insertion harmonization, we propose an Insertive Preference Optimization methodology to optimize the model by simulating human preferences, and incorporate a Context-Aware Rephraser module during reference to seamlessly integrate the subject into the original scenes. To address the lack of a benchmark for the field, we introduce InsertBench, a comprehensive benchmark comprising diverse scenes with meticulously selected subjects. Evaluation on InsertBench indicates OmniInsert outperforms state-of-the-art closed-source commercial solutions. The code will be released.</p> - https://arxiv.org/abs/2509.17627 - Mon, 22 Sep 2025 11:35:55 +0000 + Chem-R: Learning to Reason as a Chemist + https://arxiv.org/abs/2510.16880 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.16880.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weida Wang, Benteng Chen, Di Zhang, Wanhao Liu, Shuchen Pu, Ben Gao, Jin Zeng, Lei Bai, Wanli Ouyang, Xiaoyong Wei, Tianshu Yu, Tianfan Fu, Shuzhou Sun, Jiatong Li, Zifu Wang, Yuqiang Li, Shufei Zhang</p><p><b>Upvotes:</b> 52</p><p><b>Summary:</b> Although large language models (LLMs) have significant potential to advance chemical discovery, current LLMs lack core chemical knowledge, produce unreliable reasoning trajectories, and exhibit suboptimal performance across diverse chemical tasks. To address these challenges, we propose Chem-R, a generalizable Chemical Reasoning model designed to emulate the deliberative processes of chemists. Chem-R is trained through a three-phase framework that progressively builds advanced reasoning capabilities, including: 1) Chemical Foundation Training, which establishes core chemical knowledge. 2) Chemical Reasoning Protocol Distillation, incorporating structured, expert-like reasoning traces to guide systematic and reliable problem solving. 3) Multi-task Group Relative Policy Optimization that optimizes the model for balanced performance across diverse molecular- and reaction-level tasks. This structured pipeline enables Chem-R to achieve state-of-the-art performance on comprehensive benchmarks, surpassing leading large language models, including Gemini-2.5-Pro and DeepSeek-R1, by up to 46% on molecular tasks and 66% on reaction tasks. Meanwhile, Chem-R also consistently outperforms the existing chemical foundation models across both molecular and reaction level tasks. These results highlight Chem-R's robust generalization, interpretability, and potential as a foundation for next-generation AI-driven chemical discovery.</p> + https://arxiv.org/abs/2510.16880 + Sun, 19 Oct 2025 15:27:13 +0000 - Qwen3-Omni Technical Report - https://arxiv.org/abs/2509.17765 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.17765.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jin Xu, Zhifang Guo, Hangrui Hu, Yunfei Chu, Xiong Wang, Jinzheng He, Yuxuan Wang, Xian Shi, Ting He, Xinfa Zhu, Yuanjun Lv, Yongqi Wang, Dake Guo, He Wang, Linhan Ma, Pei Zhang, Xinyu Zhang, Hongkun Hao, Zishan Guo, Baosong Yang, Bin Zhang, Ziyang Ma, Xipin Wei, Shuai Bai, Keqin Chen, Xuejing Liu, Peng Wang, Mingkun Yang, Dayiheng Liu, Xingzhang Ren, Bo Zheng, Rui Men, Fan Zhou, Bowen Yu, Jianxin Yang, Le Yu, Jingren Zhou, Junyang Lin</p><p><b>Upvotes:</b> 121</p><p><b>Summary:</b> We present Qwen3-Omni, a single multimodal model that, for the first time, maintains state-of-the-art performance across text, image, audio, and video without any degradation relative to single-modal counterparts. Qwen3-Omni matches the performance of same-sized single-modal models within the Qwen series and excels particularly on audio tasks. Across 36 audio and audio-visual benchmarks, Qwen3-Omni achieves open-source SOTA on 32 benchmarks and overall SOTA on 22, outperforming strong closed-source models such as Gemini-2.5-Pro, Seed-ASR, and GPT-4o-Transcribe. Qwen3-Omni adopts a Thinker-Talker MoE architecture that unifies perception and generation across text, images, audio, and video, yielding fluent text and natural real-time speech. It supports text interaction in 119 languages, speech understanding in 19 languages, and speech generation in 10 languages. To reduce first-packet latency in streaming synthesis, Talker autoregressively predicts discrete speech codecs using a multi-codebook scheme. Leveraging the representational capacity of these codebooks, we replace computationally intensive block-wise diffusion with a lightweight causal ConvNet, enabling streaming from the first codec frame. In cold-start settings, Qwen3-Omni achieves a theoretical end-to-end first-packet latency of 234 ms. To further strengthen multimodal reasoning, we introduce a Thinking model that explicitly reasons over inputs from any modality. Since the research community currently lacks a general-purpose audio captioning model, we fine-tuned Qwen3-Omni-30B-A3B to obtain Qwen3-Omni-30B-A3B-Captioner, which produces detailed, low-hallucination captions for arbitrary audio inputs. Qwen3-Omni-30B-A3B, Qwen3-Omni-30B-A3B-Thinking, and Qwen3-Omni-30B-A3B-Captioner are publicly released under the Apache 2.0 license.</p> - https://arxiv.org/abs/2509.17765 - Mon, 22 Sep 2025 13:26:24 +0000 + FineVision: Open Data Is All You Need + https://arxiv.org/abs/2510.17269 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.17269.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Luis Wiedmann, Orr Zohar, Amir Mahla, Xiaohan Wang, Rui Li, Thibaud Frere, Leandro von Werra, Aritra Roy Gosthipaty, Andrés Marafioti</p><p><b>Upvotes:</b> 61</p><p><b>Summary:</b> The advancement of vision-language models (VLMs) is hampered by a fragmented landscape of inconsistent and contaminated public datasets. We introduce FineVision, a meticulously collected, curated, and unified corpus of 24 million samples - the largest open resource of its kind. We unify more than 200 sources into 185 subsets via a semi-automated, human-in-the-loop pipeline: automation performs bulk ingestion and schema mapping, while reviewers audit mappings and spot-check outputs to verify faithful consumption of annotations, appropriate formatting and diversity, and safety; issues trigger targeted fixes and re-runs. The workflow further applies rigorous de-duplication within and across sources and decontamination against 66 public benchmarks. FineVision also encompasses agentic/GUI tasks with a unified action space; reviewers validate schemas and inspect a sample of trajectories to confirm executable fidelity. Models trained on FineVision consistently outperform those trained on existing open mixtures across a broad evaluation suite, underscoring the benefits of scale, data hygiene, and balanced automation with human oversight. We release the corpus and curation tools to accelerate data-centric VLM research.</p> + https://arxiv.org/abs/2510.17269 + Mon, 20 Oct 2025 07:54:46 +0000 - OnePiece: Bringing Context Engineering and Reasoning to Industrial Cascade Ranking System - https://arxiv.org/abs/2509.18091 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.18091.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sunhao Dai, Jiakai Tang, Jiahua Wu, Kun Wang, Yuxuan Zhu, Bingjun Chen, Bangyang Hong, Yu Zhao, Cong Fu, Kangle Wu, Yabo Ni, Anxiang Zeng, Wenjie Wang, Xu Chen, Jun Xu, See-Kiong Ng</p><p><b>Upvotes:</b> 32</p><p><b>Summary:</b> Despite the growing interest in replicating the scaled success of large language models (LLMs) in industrial search and recommender systems, most existing industrial efforts remain limited to transplanting Transformer architectures, which bring only incremental improvements over strong Deep Learning Recommendation Models (DLRMs). From a first principle perspective, the breakthroughs of LLMs stem not only from their architectures but also from two complementary mechanisms: context engineering, which enriches raw input queries with contextual cues to better elicit model capabilities, and multi-step reasoning, which iteratively refines model outputs through intermediate reasoning paths. However, these two mechanisms and their potential to unlock substantial improvements remain largely underexplored in industrial ranking systems. In this paper, we propose OnePiece, a unified framework that seamlessly integrates LLM-style context engineering and reasoning into both retrieval and ranking models of industrial cascaded pipelines. OnePiece is built on a pure Transformer backbone and further introduces three key innovations: (1) structured context engineering, which augments interaction history with preference and scenario signals and unifies them into a structured tokenized input sequence for both retrieval and ranking; (2) block-wise latent reasoning, which equips the model with multi-step refinement of representations and scales reasoning bandwidth via block size; (3) progressive multi-task training, which leverages user feedback chains to effectively supervise reasoning steps during training. OnePiece has been deployed in the main personalized search scenario of Shopee and achieves consistent online gains across different key business metrics, including over +2% GMV/UU and a +2.90% increase in advertising revenue.</p> - https://arxiv.org/abs/2509.18091 - Mon, 22 Sep 2025 17:59:07 +0000 + PICABench: How Far Are We from Physically Realistic Image Editing? + https://arxiv.org/abs/2510.17681 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.17681.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuandong Pu, Le Zhuo, Songhao Han, Jinbo Xing, Kaiwen Zhu, Shuo Cao, Bin Fu, Si Liu, Hongsheng Li, Yu Qiao, Wenlong Zhang, Xi Chen, Yihao Liu</p><p><b>Upvotes:</b> 61</p><p><b>Summary:</b> Image editing has achieved remarkable progress recently. Modern editing models could already follow complex instructions to manipulate the original content. However, beyond completing the editing instructions, the accompanying physical effects are the key to the generation realism. For example, removing an object should also remove its shadow, reflections, and interactions with nearby objects. Unfortunately, existing models and benchmarks mainly focus on instruction completion but overlook these physical effects. So, at this moment, how far are we from physically realistic image editing? To answer this, we introduce PICABench, which systematically evaluates physical realism across eight sub-dimension (spanning optics, mechanics, and state transitions) for most of the common editing operations (add, remove, attribute change, etc). We further propose the PICAEval, a reliable evaluation protocol that uses VLM-as-a-judge with per-case, region-level human annotations and questions. Beyond benchmarking, we also explore effective solutions by learning physics from videos and construct a training dataset PICA-100K. After evaluating most of the mainstream models, we observe that physical realism remains a challenging problem with large rooms to explore. We hope that our benchmark and proposed solutions can serve as a foundation for future work moving from naive content editing toward physically consistent realism.</p> + https://arxiv.org/abs/2510.17681 + Mon, 20 Oct 2025 15:53:57 +0000 - Do You Need Proprioceptive States in Visuomotor Policies? - https://arxiv.org/abs/2509.18644 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.18644.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Juntu Zhao, Wenbo Lu, Di Zhang, Yufeng Liu, Yushen Liang, Tianluo Zhang, Yifeng Cao, Junyuan Xie, Yingdong Hu, Shengjie Wang, Junliang Guo, Dequan Wang, Yang Gao</p><p><b>Upvotes:</b> 49</p><p><b>Summary:</b> Imitation-learning-based visuomotor policies have been widely used in robot manipulation, where both visual observations and proprioceptive states are typically adopted together for precise control. However, in this study, we find that this common practice makes the policy overly reliant on the proprioceptive state input, which causes overfitting to the training trajectories and results in poor spatial generalization. On the contrary, we propose the State-free Policy, removing the proprioceptive state input and predicting actions only conditioned on visual observations. The State-free Policy is built in the relative end-effector action space, and should ensure the full task-relevant visual observations, here provided by dual wide-angle wrist cameras. Empirical results demonstrate that the State-free policy achieves significantly stronger spatial generalization than the state-based policy: in real-world tasks such as pick-and-place, challenging shirt-folding, and complex whole-body manipulation, spanning multiple robot embodiments, the average success rate improves from 0\% to 85\% in height generalization and from 6\% to 64\% in horizontal generalization. Furthermore, they also show advantages in data efficiency and cross-embodiment adaptation, enhancing their practicality for real-world deployment.</p> - https://arxiv.org/abs/2509.18644 - Tue, 23 Sep 2025 04:56:59 +0000 + Glyph: Scaling Context Windows via Visual-Text Compression + https://arxiv.org/abs/2510.17800 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.17800.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiale Cheng, Yusen Liu, Xinyu Zhang, Yulin Fei, Wenyi Hong, Ruiliang Lyu, Weihan Wang, Zhe Su, Xiaotao Gu, Xiao Liu, Yushi Bai, Jie Tang, Hongning Wang, Minlie Huang</p><p><b>Upvotes:</b> 63</p><p><b>Summary:</b> Large language models (LLMs) increasingly rely on long-context modeling for tasks such as document understanding, code analysis, and multi-step reasoning. However, scaling context windows to the million-token level brings prohibitive computational and memory costs, limiting the practicality of long-context LLMs. In this work, we take a different perspective-visual context scaling-to tackle this challenge. Instead of extending token-based sequences, we propose Glyph, a framework that renders long texts into images and processes them with vision-language models (VLMs). This approach substantially compresses textual input while preserving semantic information, and we further design an LLM-driven genetic search to identify optimal visual rendering configurations for balancing accuracy and compression. Through extensive experiments, we demonstrate that our method achieves 3-4x token compression while maintaining accuracy comparable to leading LLMs such as Qwen3-8B on various long-context benchmarks. This compression also leads to around 4x faster prefilling and decoding, and approximately 2x faster SFT training. Furthermore, under extreme compression, a 128K-context VLM could scale to handle 1M-token-level text tasks. In addition, the rendered text data benefits real-world multimodal tasks, such as document understanding. Our code and model are released at https://github.com/thu-coai/Glyph.</p> + https://arxiv.org/abs/2510.17800 + Mon, 20 Oct 2025 17:58:56 +0000 - Reinforcement Learning on Pre-Training Data - https://arxiv.org/abs/2509.19249 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.19249.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Siheng Li, Kejiao Li, Zenan Xu, Guanhua Huang, Evander Yang, Kun Li, Haoyuan Wu, Jiajia Wu, Zihao Zheng, Chenchen Zhang, Kun Shi, Kyrierl Deng, Qi Yi, Ruibin Xiong, Tingqiang Xu, Yuhao Jiang, Jianfeng Yan, Yuyuan Zeng, Guanghui Xu, Jinbao Xue, Zhijiang Xu, Zheng Fang, Shuai Li, Qibin Liu, Xiaoxue Li, Zhuoyu Li, Yangyu Tao, Fei Gao, Cheng Jiang, Bo Chao Wang, Kai Liu, Jianchen Zhu, Wai Lam, Wayyt Wang, Bo Zhou, Di Wang</p><p><b>Upvotes:</b> 61</p><p><b>Summary:</b> The growing disparity between the exponential scaling of computational resources and the finite growth of high-quality text data now constrains conventional scaling approaches for large language models (LLMs). To address this challenge, we introduce Reinforcement Learning on Pre-Training data (RLPT), a new training-time scaling paradigm for optimizing LLMs. In contrast to prior approaches that scale training primarily through supervised learning, RLPT enables the policy to autonomously explore meaningful trajectories to learn from pre-training data and improve its capability through reinforcement learning (RL). While existing RL strategies such as reinforcement learning from human feedback (RLHF) and reinforcement learning with verifiable rewards (RLVR) rely on human annotation for reward construction, RLPT eliminates this dependency by deriving reward signals directly from pre-training data. Specifically, it adopts a next-segment reasoning objective, rewarding the policy for accurately predicting subsequent text segments conditioned on the preceding context. This formulation allows RL to be scaled on pre-training data, encouraging the exploration of richer trajectories across broader contexts and thereby fostering more generalizable reasoning skills. Extensive experiments on both general-domain and mathematical reasoning benchmarks across multiple models validate the effectiveness of RLPT. For example, when applied to Qwen3-4B-Base, RLPT yields absolute improvements of 3.0, 5.1, 8.1, 6.0, 6.6, and 5.3 on MMLU, MMLU-Pro, GPQA-Diamond, KOR-Bench, AIME24, and AIME25, respectively. The results further demonstrate favorable scaling behavior, suggesting strong potential for continued gains with more compute. In addition, RLPT provides a solid foundation, extending the reasoning boundaries of LLMs and enhancing RLVR performance.</p> - https://arxiv.org/abs/2509.19249 - Tue, 23 Sep 2025 17:10:40 +0000 + Efficient Long-context Language Model Training by Core Attention Disaggregation + https://arxiv.org/abs/2510.18121 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.18121.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yonghao Zhuang, Junda Chen, Bo Pang, Yi Gu, Yibo Zhu, Yimin Jiang, Ion Stoica, Eric Xing, Hao Zhang</p><p><b>Upvotes:</b> 116</p><p><b>Summary:</b> We present core attention disaggregation (CAD), a technique that improves long-context large language model training by decoupling the core attention computation, softmax(QK^T)V, from the rest of the model and executing it on a separate pool of devices. In existing systems, core attention is colocated with other layers; at long context lengths, its quadratic compute growth compared to the near-linear growth of other components causes load imbalance and stragglers across data and pipeline parallel groups. CAD is enabled by two observations. First, core attention is stateless: it has no trainable parameters and only minimal transient data, so balancing reduces to scheduling compute-bound tasks. Second, it is composable: modern attention kernels retain high efficiency when processing fused batches of token-level shards with arbitrary lengths. CAD partitions core attention into token-level tasks and dispatches them to dedicated attention servers, which dynamically rebatch tasks to equalize compute without sacrificing kernel efficiency. We implement CAD in a system called DistCA, which uses a ping-pong execution scheme to fully overlap communication with computation and in-place execution on attention servers to reduce memory use. On 512 H200 GPUs and context lengths up to 512k tokens, DistCA improves end-to-end training throughput by up to 1.35x, eliminates data and pipeline parallel stragglers, and achieves near-perfect compute and memory balance.</p> + https://arxiv.org/abs/2510.18121 + Mon, 20 Oct 2025 21:40:51 +0000 - VCRL: Variance-based Curriculum Reinforcement Learning for Large Language Models - https://arxiv.org/abs/2509.19803 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.19803.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Guochao Jiang, Wenfeng Feng, Guofeng Quan, Chuzhan Hao, Yuewei Zhang, Guohua Liu, Hao Wang</p><p><b>Upvotes:</b> 113</p><p><b>Summary:</b> Policy-based reinforcement learning currently plays an important role in improving LLMs on mathematical reasoning tasks. However, existing rollout-based reinforcement learning methods (GRPO, DAPO, GSPO, etc.) fail to explicitly consider LLMs' learning ability for samples of different difficulty levels, which is contrary to the human cognitive process of mathematical reasoning tasks from easy to difficult. Intuitively, we find that the variance of the rollout group's reward in RLVR partly reflects the difficulty of the current sample for LLMs. Samples that are too easy or too difficult have a lower variance, while samples with moderate difficulty have a higher variance. Based on this, we propose VCRL, a curriculum reinforcement learning framework that dynamically controls the difficulty of training samples based on the variance of group rewards. Experiments on five mathematical benchmarks and two models reveal the advantages of VCRL over the current LLM RL baselines.</p> - https://arxiv.org/abs/2509.19803 - Wed, 24 Sep 2025 06:38:58 +0000 + World-in-World: World Models in a Closed-Loop World + https://arxiv.org/abs/2510.18135 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.18135.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiahan Zhang, Muqing Jiang, Nanru Dai, Taiming Lu, Arda Uzunoglu, Shunchi Zhang, Yana Wei, Jiahao Wang, Vishal M. Patel, Paul Pu Liang, Daniel Khashabi, Cheng Peng, Rama Chellappa, Tianmin Shu, Alan Yuille, Yilun Du, Jieneng Chen</p><p><b>Upvotes:</b> 85</p><p><b>Summary:</b> Generative world models (WMs) can now simulate worlds with striking visual realism, which naturally raises the question of whether they can endow embodied agents with predictive perception for decision making. Progress on this question has been limited by fragmented evaluation: most existing benchmarks adopt open-loop protocols that emphasize visual quality in isolation, leaving the core issue of embodied utility unresolved, i.e., do WMs actually help agents succeed at embodied tasks? To address this gap, we introduce World-in-World, the first open platform that benchmarks WMs in a closed-loop world that mirrors real agent-environment interactions. World-in-World provides a unified online planning strategy and a standardized action API, enabling heterogeneous WMs for decision making. We curate four closed-loop environments that rigorously evaluate diverse WMs, prioritize task success as the primary metric, and move beyond the common focus on visual quality; we also present the first data scaling law for world models in embodied settings. Our study uncovers three surprises: (1) visual quality alone does not guarantee task success, controllability matters more; (2) scaling post-training with action-observation data is more effective than upgrading the pretrained video generators; and (3) allocating more inference-time compute allows WMs to substantially improve closed-loop performance.</p> + https://arxiv.org/abs/2510.18135 + Mon, 20 Oct 2025 22:09:15 +0000 - SIM-CoT: Supervised Implicit Chain-of-Thought - https://arxiv.org/abs/2509.20317 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.20317.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xilin Wei, Xiaoran Liu, Yuhang Zang, Xiaoyi Dong, Yuhang Cao, Jiaqi Wang, Xipeng Qiu, Dahua Lin</p><p><b>Upvotes:</b> 35</p><p><b>Summary:</b> Implicit Chain-of-Thought (CoT) methods present a promising, token-efficient alternative to explicit CoT reasoning in Large Language Models (LLMs), but a persistent performance gap has limited the application of implicit CoT. We identify a core latent instability issue by scaling the computational budget of implicit CoT approaches: as we increase the number of implicit reasoning tokens to enhance performance, the training process often becomes unstable and collapses. Our analysis reveals that this instability arises from the latent representations becoming homogeneous and losing their semantic diversity, a failure caused by insufficient step-level supervision in existing implicit CoT approaches. To address this issue, we propose SIM-CoT, a plug-and-play training module that introduces step-level supervision to stabilize and enrich the latent reasoning space. Specifically, SIM-CoT employs an auxiliary decoder during training to align each implicit token with its corresponding explicit reasoning step, ensuring that latent states capture distinct and meaningful information. The proposed auxiliary decoder is removed during inference, preserving the computational efficiency of implicit CoT methods with no added overhead. In addition, the auxiliary decoder affords interpretability of implicit reasoning by projecting each latent token onto an explicit reasoning vocabulary, enabling per-step visualization of semantic roles and diagnosis. SIM-CoT significantly enhances both the in-domain accuracy and out-of-domain stability of various implicit CoT methods, boosting baselines like Coconut by +8.2% on GPT-2 and CODI by +3.0% on LLaMA-3.1 8B. Demonstrating strong scalability, SIM-CoT also surpasses the explicit CoT baseline on GPT-2 by 2.1% with 2.3\times greater token efficiency, while substantially closing the performance gap on larger models like LLaMA-3.1 8B.</p> - https://arxiv.org/abs/2509.20317 - Wed, 24 Sep 2025 17:01:32 +0000 + DeepSeek-OCR: Contexts Optical Compression + https://arxiv.org/abs/2510.18234 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.18234.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haoran Wei, Yaofeng Sun, Yukun Li</p><p><b>Upvotes:</b> 64</p><p><b>Summary:</b> We present DeepSeek-OCR as an initial investigation into the feasibility of compressing long contexts via optical 2D mapping. DeepSeek-OCR consists of two components: DeepEncoder and DeepSeek3B-MoE-A570M as the decoder. Specifically, DeepEncoder serves as the core engine, designed to maintain low activations under high-resolution input while achieving high compression ratios to ensure an optimal and manageable number of vision tokens. Experiments show that when the number of text tokens is within 10 times that of vision tokens (i.e., a compression ratio < 10x), the model can achieve decoding (OCR) precision of 97%. Even at a compression ratio of 20x, the OCR accuracy still remains at about 60%. This shows considerable promise for research areas such as historical long-context compression and memory forgetting mechanisms in LLMs. Beyond this, DeepSeek-OCR also demonstrates high practical value. On OmniDocBench, it surpasses GOT-OCR2.0 (256 tokens/page) using only 100 vision tokens, and outperforms MinerU2.0 (6000+ tokens per page on average) while utilizing fewer than 800 vision tokens. In production, DeepSeek-OCR can generate training data for LLMs/VLMs at a scale of 200k+ pages per day (a single A100-40G). Codes and model weights are publicly accessible at http://github.com/deepseek-ai/DeepSeek-OCR.</p> + https://arxiv.org/abs/2510.18234 + Tue, 21 Oct 2025 02:41:44 +0000 - Video models are zero-shot learners and reasoners - https://arxiv.org/abs/2509.20328 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.20328.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Thaddäus Wiedemer, Yuxuan Li, Paul Vicol, Shixiang Shane Gu, Nick Matarese, Kevin Swersky, Been Kim, Priyank Jaini, Robert Geirhos</p><p><b>Upvotes:</b> 86</p><p><b>Summary:</b> The remarkable zero-shot capabilities of Large Language Models (LLMs) have propelled natural language processing from task-specific models to unified, generalist foundation models. This transformation emerged from simple primitives: large, generative models trained on web-scale data. Curiously, the same primitives apply to today's generative video models. Could video models be on a trajectory towards general-purpose vision understanding, much like LLMs developed general-purpose language understanding? We demonstrate that Veo 3 can solve a broad variety of tasks it wasn't explicitly trained for: segmenting objects, detecting edges, editing images, understanding physical properties, recognizing object affordances, simulating tool use, and more. These abilities to perceive, model, and manipulate the visual world enable early forms of visual reasoning like maze and symmetry solving. Veo's emergent zero-shot capabilities indicate that video models are on a path to becoming unified, generalist vision foundation models.</p> - https://arxiv.org/abs/2509.20328 - Wed, 24 Sep 2025 17:17:27 +0000 + BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping + https://arxiv.org/abs/2510.18927 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.18927.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhiheng Xi, Xin Guo, Yang Nan, Enyu Zhou, Junrui Shen, Wenxiang Chen, Jiaqi Liu, Jixuan Huang, Zhihao Zhang, Honglin Guo, Xun Deng, Zhikai Lei, Miao Zheng, Guoteng Wang, Shuo Zhang, Peng Sun, Rui Zheng, Hang Yan, Tao Gui, Qi Zhang, Xuanjing Huang</p><p><b>Upvotes:</b> 81</p><p><b>Summary:</b> Reinforcement learning (RL) has recently become the core paradigm for aligning and strengthening large language models (LLMs). Yet, applying RL in off-policy settings--where stale data from past policies are used for training--improves sample efficiency, but remains challenging: policy entropy declines sharply, optimization often becomes unstable and may even collapse. Through theoretical and empirical analysis, we identify two key insights: (i) an imbalance in optimization, where negative-advantage samples dominate the policy gradient, suppressing useful behaviors and risking gradient explosions; and (ii) the derived Entropy-Clip Rule, which reveals that the fixed clipping mechanism in PPO-like objectives systematically blocks entropy-increasing updates, thereby driving the policy toward over-exploitation at the expense of exploration. Building on these insights, we propose BAlanced Policy Optimization with Adaptive Clipping (BAPO), a simple yet effective method that dynamically adjusts clipping bounds to adaptively re-balance positive and negative contributions, preserve entropy, and stabilize RL optimization. Across diverse off-policy scenarios--including sample replay and partial rollout--BAPO achieves fast, stable, and data-efficient training. On AIME 2024 and AIME 2025 benchmarks, our 7B BAPO model surpasses open-source counterparts such as SkyWork-OR1-7B, while our 32B BAPO model not only achieves state-of-the-art results among models of the same scale but also outperforms leading proprietary systems like o3-mini and Gemini-2.5-Flash-Thinking.</p> + https://arxiv.org/abs/2510.18927 + Tue, 21 Oct 2025 12:55:04 +0000 - EmbeddingGemma: Powerful and Lightweight Text Representations - https://arxiv.org/abs/2509.20354 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.20354.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Henrique Schechter Vera, Sahil Dua, Biao Zhang, Daniel Salz, Ryan Mullins, Sindhu Raghuram Panyam, Sara Smoot, Iftekhar Naim, Joe Zou, Feiyang Chen, Daniel Cer, Alice Lisak, Min Choi, Lucas Gonzalez, Omar Sanseviero, Glenn Cameron, Ian Ballantyne, Kat Black, Kaifeng Chen, Weiyi Wang, Zhe Li, Gus Martins, Jinhyuk Lee, Mark Sherwood, Juyeong Ji, Renjie Wu, Jingxiao Zheng, Jyotinder Singh, Abheesht Sharma, Divya Sreepat, Aashi Jain, Adham Elarabawy, AJ Co, Andreas Doumanoglou, Babak Samari, Ben Hora, Brian Potetz, Dahun Kim, Enrique Alfonseca, Fedor Moiseev, Feng Han, Frank Palma Gomez, Gustavo Hernández Ábrego, Hesen Zhang, Hui Hui, Jay Han, Karan Gill, Ke Chen, Koert Chen, Madhuri Shanbhogue, Michael Boratko, Paul Suganthan, Sai Meher Karthik Duddu, Sandeep Mariserla, Setareh Ariafar, Shanfeng Zhang, Shijie Zhang, Simon Baumgartner, Sonam Goenka, Steve Qiu, Tanmaya Dabral, Trevor Walker, Vikram Rao, Waleed Khawaja, Wenlei Zhou, Xiaoqi Ren, Ye Xia, Yichang Chen, Yi-Ting Chen, Zhe Dong, Zhongli Ding, Francesco Visin, Gaël Liu, Jiageng Zhang, Kathleen Kenealy, Michelle Casbon, Ravin Kumar, Thomas Mesnard, Zach Gleicher, Cormac Brick, Olivier Lacombe, Adam Roberts, Yunhsuan Sung, Raphael Hoffmann, Tris Warkentin, Armand Joulin, Tom Duerig, Mojtaba Seyedhosseini</p><p><b>Upvotes:</b> 32</p><p><b>Summary:</b> We introduce EmbeddingGemma, a new lightweight, open text embedding model based on the Gemma 3 language model family. Our innovative training recipe strategically captures knowledge from larger models via encoder-decoder initialization and geometric embedding distillation. We improve model robustness and expressiveness with a spread-out regularizer, and ensure generalizability by merging checkpoints from varied, optimized mixtures. Evaluated on the Massive Text Embedding Benchmark (MTEB) across multilingual, English, and code domains, EmbeddingGemma (300M) achieves state-of-the-art results. Notably, it outperforms prior top models, both proprietary and open, with fewer than 500M parameters, and provides performance comparable to models double its size, offering an exceptional performance-to-cost ratio. Remarkably, this lead persists when quantizing model weights or truncating embedding outputs. This makes EmbeddingGemma particularly well-suited for low-latency and high-throughput use cases such as on-device applications. We provide ablation studies exploring our key design choices. We release EmbeddingGemma to the community to promote further research.</p> - https://arxiv.org/abs/2509.20354 - Wed, 24 Sep 2025 17:56:51 +0000 + UniGenBench++: A Unified Semantic Evaluation Benchmark for Text-to-Image Generation + https://arxiv.org/abs/2510.18701 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.18701.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yibin Wang, Zhimin Li, Yuhang Zang, Jiazi Bu, Yujie Zhou, Yi Xin, Junjun He, Chunyu Wang, Qinglin Lu, Cheng Jin, Jiaqi Wang</p><p><b>Upvotes:</b> 66</p><p><b>Summary:</b> Recent progress in text-to-image (T2I) generation underscores the importance of reliable benchmarks in evaluating how accurately generated images reflect the semantics of their textual prompt. However, (1) existing benchmarks lack the diversity of prompt scenarios and multilingual support, both essential for real-world applicability; (2) they offer only coarse evaluations across primary dimensions, covering a narrow range of sub-dimensions, and fall short in fine-grained sub-dimension assessment. To address these limitations, we introduce UniGenBench++, a unified semantic assessment benchmark for T2I generation. Specifically, it comprises 600 prompts organized hierarchically to ensure both coverage and efficiency: (1) spans across diverse real-world scenarios, i.e., 5 main prompt themes and 20 subthemes; (2) comprehensively probes T2I models' semantic consistency over 10 primary and 27 sub evaluation criteria, with each prompt assessing multiple testpoints. To rigorously assess model robustness to variations in language and prompt length, we provide both English and Chinese versions of each prompt in short and long forms. Leveraging the general world knowledge and fine-grained image understanding capabilities of a closed-source Multi-modal Large Language Model (MLLM), i.e., Gemini-2.5-Pro, an effective pipeline is developed for reliable benchmark construction and streamlined model assessment. Moreover, to further facilitate community use, we train a robust evaluation model that enables offline assessment of T2I model outputs. Through comprehensive benchmarking of both open- and closed-sourced T2I models, we systematically reveal their strengths and weaknesses across various aspects.</p> + https://arxiv.org/abs/2510.18701 + Tue, 21 Oct 2025 14:56:46 +0000 - Seedream 4.0: Toward Next-generation Multimodal Image Generation - https://arxiv.org/abs/2509.20427 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.20427.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Team Seedream, Yunpeng Chen, Yu Gao, Lixue Gong, Meng Guo, Qiushan Guo, Zhiyao Guo, Xiaoxia Hou, Weilin Huang, Yixuan Huang, Xiaowen Jian, Huafeng Kuang, Zhichao Lai, Fanshi Li, Liang Li, Xiaochen Lian, Chao Liao, Liyang Liu, Wei Liu, Yanzuo Lu, Zhengxiong Luo, Tongtong Ou, Guang Shi, Yichun Shi, Shiqi Sun, Yu Tian, Zhi Tian, Peng Wang, Rui Wang, Xun Wang, Ye Wang, Guofeng Wu, Jie Wu, Wenxu Wu, Yonghui Wu, Xin Xia, Xuefeng Xiao, Shuang Xu, Xin Yan, Ceyuan Yang, Jianchao Yang, Zhonghua Zhai, Chenlin Zhang, Heng Zhang, Qi Zhang, Xinyu Zhang, Yuwei Zhang, Shijia Zhao, Wenliang Zhao, Wenjia Zhu</p><p><b>Upvotes:</b> 68</p><p><b>Summary:</b> We introduce Seedream 4.0, an efficient and high-performance multimodal image generation system that unifies text-to-image (T2I) synthesis, image editing, and multi-image composition within a single framework. We develop a highly efficient diffusion transformer with a powerful VAE which also can reduce the number of image tokens considerably. This allows for efficient training of our model, and enables it to fast generate native high-resolution images (e.g., 1K-4K). Seedream 4.0 is pretrained on billions of text-image pairs spanning diverse taxonomies and knowledge-centric concepts. Comprehensive data collection across hundreds of vertical scenarios, coupled with optimized strategies, ensures stable and large-scale training, with strong generalization. By incorporating a carefully fine-tuned VLM model, we perform multi-modal post-training for training both T2I and image editing tasks jointly. For inference acceleration, we integrate adversarial distillation, distribution matching, and quantization, as well as speculative decoding. It achieves an inference time of up to 1.8 seconds for generating a 2K image (without a LLM/VLM as PE model). Comprehensive evaluations reveal that Seedream 4.0 can achieve state-of-the-art results on both T2I and multimodal image editing. In particular, it demonstrates exceptional multimodal capabilities in complex tasks, including precise image editing and in-context reasoning, and also allows for multi-image reference, and can generate multiple output images. This extends traditional T2I systems into an more interactive and multidimensional creative tool, pushing the boundary of generative AI for both creativity and professional applications. Seedream 4.0 is now accessible on https://www.volcengine.com/experience/ark?launch=seedream.</p> - https://arxiv.org/abs/2509.20427 - Wed, 24 Sep 2025 17:59:04 +0000 + Every Step Evolves: Scaling Reinforcement Learning for Trillion-Scale Thinking Model + https://arxiv.org/abs/2510.18855 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.18855.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ling Team, Anqi Shen, Baihui Li, Bin Hu, Bin Jing, Cai Chen, Chao Huang, Chao Zhang, Chaokun Yang, Cheng Lin, Chengyao Wen, Congqi Li, Deng Zhao, Dingbo Yuan, Donghai You, Fagui Mao, Fanzhuang Meng, Feng Xu, Guojie Li, Guowei Wang, Hao Dai, Haonan Zheng, Hong Liu, Jia Guo, Jiaming Liu, Jian Liu, Jianhao Fu, Jiannan Shi, Jianwen Wang, Jianxin Lai, Jin Yang, Jun Mei, Jun Zhou, Junbo Zhao, Junping Zhao, Kuan Xu, Le Su, Lei Chen, Li Tang, Liang Jiang, Liangcheng Fu, Lianhao Xu, Linfeng Shi, Lisha Liao, Longfei Zheng, Meng Li, Mingchun Chen, Qi Zuo, Qiang Cheng, Qianggang Cao, Qitao Shi, Quanrui Guo, Senlin Zhu, Shaofei Wang, Shaomian Zheng, Shuaicheng Li, Shuwei Gu, Siba Chen, Tao Wu, Tao Zhang, Tianyu Zhang, Tianyu Zhou, Tiwei Bie, Tongkai Yang, Wang Hong, Wang Ren, Weihua Chen, Wenbo Yu, Wengang Zheng, Xiangchun Wang, Xiaodong Yan, Xiaopei Wan, Xin Zhao, Xinyu Kong, Xinyu Tang, Xudong Han, Xudong Wang, Xuemin Yang, Xueyu Hu, Yalin Zhang, Yan Sun, Yicheng Shan, Yilong Wang, Yingying Xu, Yongkang Liu, Yongzhen Guo, Yuanyuan Wang, Yuchen Yan, Yuefan Wang, Yuhong Guo, Zehuan Li, Zhankai Xu, Zhe Li, Zhenduo Zhang, Zhengke Gui, Zhenxuan Pan, Zhenyu Huang, Zhenzhong Lan, Zhiqiang Ding, Zhiqiang Zhang, Zhixun Li, Zhizhen Liu, Zihao Wang, Zujie Wen</p><p><b>Upvotes:</b> 62</p><p><b>Summary:</b> We present Ring-1T, the first open-source, state-of-the-art thinking model with a trillion-scale parameter. It features 1 trillion total parameters and activates approximately 50 billion per token. Training such models at a trillion-parameter scale introduces unprecedented challenges, including train-inference misalignment, inefficiencies in rollout processing, and bottlenecks in the RL system. To address these, we pioneer three interconnected innovations: (1) IcePop stabilizes RL training via token-level discrepancy masking and clipping, resolving instability from training-inference mismatches; (2) C3PO++ improves resource utilization for long rollouts under a token budget by dynamically partitioning them, thereby obtaining high time efficiency; and (3) ASystem, a high-performance RL framework designed to overcome the systemic bottlenecks that impede trillion-parameter model training. Ring-1T delivers breakthrough results across critical benchmarks: 93.4 on AIME-2025, 86.72 on HMMT-2025, 2088 on CodeForces, and 55.94 on ARC-AGI-v1. Notably, it attains a silver medal-level result on the IMO-2025, underscoring its exceptional reasoning capabilities. By releasing the complete 1T parameter MoE model to the community, we provide the research community with direct access to cutting-edge reasoning capabilities. This contribution marks a significant milestone in democratizing large-scale reasoning intelligence and establishes a new baseline for open-source model performance.</p> + https://arxiv.org/abs/2510.18855 + Tue, 21 Oct 2025 17:46:14 +0000 - Tree Search for LLM Agent Reinforcement Learning - https://arxiv.org/abs/2509.21240 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.21240.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuxiang Ji, Ziyu Ma, Yong Wang, Guanhua Chen, Xiangxiang Chu, Liaoni Wu</p><p><b>Upvotes:</b> 81</p><p><b>Summary:</b> Recent advances in reinforcement learning (RL) have significantly enhanced the agentic capabilities of large language models (LLMs). In long-term and multi-turn agent tasks, existing approaches driven solely by outcome rewards often suffer from the problem of sparse supervision. To address the challenge, we propose Tree-based Group Relative Policy Optimization (Tree-GRPO), a grouped agent RL method based on tree search, where each tree node represents the complete agent interaction step. By sharing common prefixes, the tree search sampling increases the number of rollouts achievable within a fixed budget of tokens or tool calls. Moreover, we find that the tree-structured trajectory naturally allows the construction of step-wise process supervised signals even using only the outcome reward. Based on this, Tree-GRPO estimates the grouped relative advantages both on intra-tree and inter-tree levels. Through theoretical analysis, we demonstrate that the objective of intra-tree level group relative policy optimization is equivalent to that of step-level direct preference learning. Experiments across 11 datasets and 3 types of QA tasks demonstrate the superiority of the proposed tree-based RL over the chain-based RL method.</p> - https://arxiv.org/abs/2509.21240 - Thu, 25 Sep 2025 14:37:09 +0000 + LightMem: Lightweight and Efficient Memory-Augmented Generation + https://arxiv.org/abs/2510.18866 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.18866.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jizhan Fang, Xinle Deng, Haoming Xu, Ziyan Jiang, Yuqi Tang, Ziwen Xu, Shumin Deng, Yunzhi Yao, Mengru Wang, Shuofei Qiao, Huajun Chen, Ningyu Zhang</p><p><b>Upvotes:</b> 106</p><p><b>Summary:</b> Despite their remarkable capabilities, Large Language Models (LLMs) struggle to effectively leverage historical interaction information in dynamic and complex environments. Memory systems enable LLMs to move beyond stateless interactions by introducing persistent information storage, retrieval, and utilization mechanisms. However, existing memory systems often introduce substantial time and computational overhead. To this end, we introduce a new memory system called LightMem, which strikes a balance between the performance and efficiency of memory systems. Inspired by the Atkinson-Shiffrin model of human memory, LightMem organizes memory into three complementary stages. First, cognition-inspired sensory memory rapidly filters irrelevant information through lightweight compression and groups information according to their topics. Next, topic-aware short-term memory consolidates these topic-based groups, organizing and summarizing content for more structured access. Finally, long-term memory with sleep-time update employs an offline procedure that decouples consolidation from online inference. Experiments on LongMemEval with GPT and Qwen backbones show that LightMem outperforms strong baselines in accuracy (up to 10.9% gains) while reducing token usage by up to 117x, API calls by up to 159x, and runtime by over 12x. The code is available at https://github.com/zjunlp/LightMem.</p> + https://arxiv.org/abs/2510.18866 + Tue, 21 Oct 2025 17:58:17 +0000 - Hunyuan3D-Omni: A Unified Framework for Controllable Generation of 3D Assets - https://arxiv.org/abs/2509.21245 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.21245.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Team Hunyuan3D, Bowen Zhang, Chunchao Guo, Haolin Liu, Hongyu Yan, Huiwen Shi, Jingwei Huang, Junlin Yu, Kunhong Li, Linus, Penghao Wang, Qingxiang Lin, Sicong Liu, Xianghui Yang, Yixuan Tang, Yunfei Zhao, Zeqiang Lai, Zhihao Liang, Zibo Zhao</p><p><b>Upvotes:</b> 36</p><p><b>Summary:</b> Recent advances in 3D-native generative models have accelerated asset creation for games, film, and design. However, most methods still rely primarily on image or text conditioning and lack fine-grained, cross-modal controls, which limits controllability and practical adoption. To address this gap, we present Hunyuan3D-Omni, a unified framework for fine-grained, controllable 3D asset generation built on Hunyuan3D 2.1. In addition to images, Hunyuan3D-Omni accepts point clouds, voxels, bounding boxes, and skeletal pose priors as conditioning signals, enabling precise control over geometry, topology, and pose. Instead of separate heads for each modality, our model unifies all signals in a single cross-modal architecture. We train with a progressive, difficulty-aware sampling strategy that selects one control modality per example and biases sampling toward harder signals (e.g., skeletal pose) while downweighting easier ones (e.g., point clouds), encouraging robust multi-modal fusion and graceful handling of missing inputs. Experiments show that these additional controls improve generation accuracy, enable geometry-aware transformations, and increase robustness for production workflows.</p> - https://arxiv.org/abs/2509.21245 - Thu, 25 Sep 2025 14:39:17 +0000 + Every Attention Matters: An Efficient Hybrid Architecture for Long-Context Reasoning + https://arxiv.org/abs/2510.19338 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.19338.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ling Team, Bin Han, Caizhi Tang, Chen Liang, Donghao Zhang, Fan Yuan, Feng Zhu, Jie Gao, Jingyu Hu, Longfei Li, Meng Li, Mingyang Zhang, Peijie Jiang, Peng Jiao, Qian Zhao, Qingyuan Yang, Wenbo Shen, Xinxing Yang, Yalin Zhang, Yankun Ren, Yao Zhao, Yibo Cao, Yixuan Sun, Yue Zhang, Yuchen Fang, Zibin Lin, Zixuan Cheng, Jun Zhou</p><p><b>Upvotes:</b> 101</p><p><b>Summary:</b> In this technical report, we present the Ring-linear model series, specifically including Ring-mini-linear-2.0 and Ring-flash-linear-2.0. Ring-mini-linear-2.0 comprises 16B parameters and 957M activations, while Ring-flash-linear-2.0 contains 104B parameters and 6.1B activations. Both models adopt a hybrid architecture that effectively integrates linear attention and softmax attention, significantly reducing I/O and computational overhead in long-context inference scenarios. Compared to a 32 billion parameter dense model, this series reduces inference cost to 1/10, and compared to the original Ring series, the cost is also reduced by over 50%. Furthermore, through systematic exploration of the ratio between different attention mechanisms in the hybrid architecture, we have identified the currently optimal model structure. Additionally, by leveraging our self-developed high-performance FP8 operator library-linghe, overall training efficiency has been improved by 50%. Benefiting from the high alignment between the training and inference engine operators, the models can undergo long-term, stable, and highly efficient optimization during the reinforcement learning phase, consistently maintaining SOTA performance across multiple challenging complex reasoning benchmarks.</p> + https://arxiv.org/abs/2510.19338 + Wed, 22 Oct 2025 07:59:38 +0000 - MMR1: Enhancing Multimodal Reasoning with Variance-Aware Sampling and Open Resources - https://arxiv.org/abs/2509.21268 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.21268.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sicong Leng, Jing Wang, Jiaxi Li, Hao Zhang, Zhiqiang Hu, Boqiang Zhang, Yuming Jiang, Hang Zhang, Xin Li, Lidong Bing, Deli Zhao, Wei Lu, Yu Rong, Aixin Sun, Shijian Lu</p><p><b>Upvotes:</b> 93</p><p><b>Summary:</b> Large multimodal reasoning models have achieved rapid progress, but their advancement is constrained by two major limitations: the absence of open, large-scale, high-quality long chain-of-thought (CoT) data, and the instability of reinforcement learning (RL) algorithms in post-training. Group Relative Policy Optimization (GRPO), the standard framework for RL fine-tuning, is prone to gradient vanishing when reward variance is low, which weakens optimization signals and impairs convergence. This work makes three contributions: (1) We propose Variance-Aware Sampling (VAS), a data selection strategy guided by Variance Promotion Score (VPS) that combines outcome variance and trajectory diversity to promote reward variance and stabilize policy optimization. (2) We release large-scale, carefully curated resources containing ~1.6M long CoT cold-start data and ~15k RL QA pairs, designed to ensure quality, difficulty, and diversity, along with a fully reproducible end-to-end training codebase. (3) We open-source a family of multimodal reasoning models in multiple scales, establishing standardized baselines for the community. Experiments across mathematical reasoning benchmarks demonstrate the effectiveness of both the curated data and the proposed VAS. Comprehensive ablation studies and analyses provide further insight into the contributions of each component. In addition, we theoretically establish that reward variance lower-bounds the expected policy gradient magnitude, with VAS serving as a practical mechanism to realize this guarantee. Our code, data, and checkpoints are available at https://github.com/LengSicong/MMR1.</p> - https://arxiv.org/abs/2509.21268 - Thu, 25 Sep 2025 14:58:29 +0000 + LoongRL:Reinforcement Learning for Advanced Reasoning over Long Contexts + https://arxiv.org/abs/2510.19363 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.19363.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Siyuan Wang, Gaokai Zhang, Li Lyna Zhang, Ning Shang, Fan Yang, Dongyao Chen, Mao Yang</p><p><b>Upvotes:</b> 59</p><p><b>Summary:</b> Reasoning over long contexts is essential for large language models. While reinforcement learning (RL) enhances short-context reasoning by inducing "Aha" moments in chain-of-thought, the advanced thinking patterns required for long-context reasoning remain largely unexplored, and high-difficulty RL data are scarce. In this paper, we introduce LoongRL, a data-driven RL method for advanced long-context reasoning. Central to LoongRL is KeyChain, a synthesis approach that transforms short multi-hop QA into high-difficulty long-context tasks by inserting UUID chains that hide the true question among large collections of distracting documents. Solving these tasks requires the model to trace the correct chain step-by-step, identify the true question, retrieve relevant facts and reason over them to answer correctly. RL training on KeyChain data induces an emergent plan-retrieve-reason-recheck reasoning pattern that generalizes far beyond training length. Models trained at 16K effectively solve 128K tasks without prohibitive full-length RL rollout costs. On Qwen2.5-7B and 14B, LoongRL substantially improves long-context multi-hop QA accuracy by +23.5% and +21.1% absolute gains. The resulting LoongRL-14B reaches a score of 74.2, rivaling much larger frontier models such as o3-mini (74.5) and DeepSeek-R1 (74.9). It also improves long-context retrieval, passes all 128K needle-in-a-haystack stress tests, and preserves short-context reasoning capabilities.</p> + https://arxiv.org/abs/2510.19363 + Wed, 22 Oct 2025 08:35:28 +0000 - SciReasoner: Laying the Scientific Reasoning Ground Across Disciplines - https://arxiv.org/abs/2509.21320 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.21320.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yizhou Wang, Chen Tang, Han Deng, Jiabei Xiao, Jiaqi Liu, Jianyu Wu, Jun Yao, Pengze Li, Encheng Su, Lintao Wang, Guohang Zhuang, Yuchen Ren, Ben Fei, Ming Hu, Xin Chen, Dongzhan Zhou, Junjun He, Xiangyu Yue, Zhenfei Yin, Jiamin Wu, Qihao Zheng, Yuhao Zhou, Huihui Xu, Chenglong Ma, Yan Lu, Wenlong Zhang, Chunfeng Song, Philip Torr, Shixiang Tang, Xinzhu Ma, Wanli Ouyang, Lei Bai</p><p><b>Upvotes:</b> 91</p><p><b>Summary:</b> We present a scientific reasoning foundation model that aligns natural language with heterogeneous scientific representations. The model is pretrained on a 206B-token corpus spanning scientific text, pure sequences, and sequence-text pairs, then aligned via SFT on 40M instructions, annealed cold-start bootstrapping to elicit long-form chain-of-thought, and reinforcement learning with task-specific reward shaping, which instills deliberate scientific reasoning. It supports four capability families, covering up to 103 tasks across workflows: (i) faithful translation between text and scientific formats, (ii) text/knowledge extraction, (iii) property prediction, (iv) property classification, (v) unconditional and conditional sequence generation and design. Compared with specialist systems, our approach broadens instruction coverage, improves cross-domain generalization, and enhances fidelity. We detail data curation and training and show that cross-discipline learning strengthens transfer and downstream reliability. The model, instruct tuning datasets and the evaluation code are open-sourced at https://huggingface.co/SciReason and https://github.com/open-sciencelab/SciReason.</p> - https://arxiv.org/abs/2509.21320 - Thu, 25 Sep 2025 17:52:06 +0000 + Human-Agent Collaborative Paper-to-Page Crafting for Under $0.1 + https://arxiv.org/abs/2510.19600 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.19600.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qianli Ma, Siyu Wang, Yilin Chen, Yinhao Tang, Yixiang Yang, Chang Guo, Bingjie Gao, Zhening Xing, Yanan Sun, Zhipeng Zhang</p><p><b>Upvotes:</b> 66</p><p><b>Summary:</b> In the quest for scientific progress, communicating research is as vital as the discovery itself. Yet, researchers are often sidetracked by the manual, repetitive chore of building project webpages to make their dense papers accessible. While automation has tackled static slides and posters, the dynamic, interactive nature of webpages has remained an unaddressed challenge. To bridge this gap, we reframe the problem, arguing that the solution lies not in a single command, but in a collaborative, hierarchical process. We introduce AutoPage, a novel multi-agent system that embodies this philosophy. AutoPage deconstructs paper-to-page creation into a coarse-to-fine pipeline from narrative planning to multimodal content generation and interactive rendering. To combat AI hallucination, dedicated "Checker" agents verify each step against the source paper, while optional human checkpoints ensure the final product aligns perfectly with the author's vision, transforming the system from a mere tool into a powerful collaborative assistant. To rigorously validate our approach, we also construct PageBench, the first benchmark for this new task. Experiments show AutoPage not only generates high-quality, visually appealing pages but does so with remarkable efficiency in under 15 minutes for less than \0.1. Code and dataset will be released at https://mqleet.github.io/AutoPage_ProjectPage/{Webpage}$.</p> + https://arxiv.org/abs/2510.19600 + Wed, 22 Oct 2025 13:53:57 +0000 - ReviewScore: Misinformed Peer Review Detection with Large Language Models - https://arxiv.org/abs/2509.21679 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.21679.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hyun Ryu, Doohyuk Jang, Hyemin S. Lee, Joonhyun Jeong, Gyeongman Kim, Donghyeon Cho, Gyouk Chu, Minyeong Hwang, Hyeongwon Jang, Changhun Kim, Haechan Kim, Jina Kim, Joowon Kim, Yoonjeon Kim, Kwanhyung Lee, Chanjae Park, Heecheol Yun, Gregor Betz, Eunho Yang</p><p><b>Upvotes:</b> 58</p><p><b>Summary:</b> Peer review serves as a backbone of academic research, but in most AI conferences, the review quality is degrading as the number of submissions explodes. To reliably detect low-quality reviews, we define misinformed review points as either "weaknesses" in a review that contain incorrect premises, or "questions" in a review that can be already answered by the paper. We verify that 15.2% of weaknesses and 26.4% of questions are misinformed and introduce ReviewScore indicating if a review point is misinformed. To evaluate the factuality of each premise of weaknesses, we propose an automated engine that reconstructs every explicit and implicit premise from a weakness. We build a human expert-annotated ReviewScore dataset to check the ability of LLMs to automate ReviewScore evaluation. Then, we measure human-model agreements on ReviewScore using eight current state-of-the-art LLMs and verify moderate agreements. We also prove that evaluating premise-level factuality shows significantly higher agreements than evaluating weakness-level factuality. A thorough disagreement analysis further supports a potential of fully automated ReviewScore evaluation.</p> - https://arxiv.org/abs/2509.21679 - Thu, 25 Sep 2025 22:55:05 +0000 + AdaSPEC: Selective Knowledge Distillation for Efficient Speculative Decoders + https://arxiv.org/abs/2510.19779 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.19779.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuezhou Hu, Jiaxin Guo, Xinyu Feng, Tuo Zhao</p><p><b>Upvotes:</b> 58</p><p><b>Summary:</b> Speculative Decoding (SD) accelerates large language model inference by employing a small draft model to generate predictions, which are then verified by a larger target model. The effectiveness of SD hinges on the alignment between these models, which is typically enhanced by Knowledge Distillation (KD). However, conventional KD methods aim to minimize the KL divergence between the draft and target models across all tokens, a goal that is misaligned with the true objective of SD, which is to maximize token acceptance rate. Therefore, draft models often struggle to fully assimilate the target model's knowledge due to capacity constraints, leading to suboptimal performance. To address this challenge, we propose AdaSPEC, a novel method that incorporates selective token filtering into the KD process. AdaSPEC utilizes a reference model to identify and filter out difficult-to-fit tokens, enabling the distillation of a draft model that better aligns with the target model on simpler tokens. This approach improves the overall token acceptance rate without compromising generation quality. We evaluate AdaSPEC across diverse tasks, including arithmetic reasoning, instruction-following, coding, and summarization, using model configurations of 31M/1.4B and 350M/2.7B parameters. Our results demonstrate that AdaSPEC consistently outperforms the state-of-the-art DistillSpec method, achieving higher acceptance rates across all tasks (up to 15\%). The code is publicly available at https://github.com/yuezhouhu/adaspec.</p> + https://arxiv.org/abs/2510.19779 + Wed, 22 Oct 2025 17:13:00 +0000 - MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing - https://arxiv.org/abs/2509.22186 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.22186.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junbo Niu, Zheng Liu, Zhuangcheng Gu, Bin Wang, Linke Ouyang, Zhiyuan Zhao, Tao Chu, Tianyao He, Fan Wu, Qintong Zhang, Zhenjiang Jin, Guang Liang, Rui Zhang, Wenzheng Zhang, Yuan Qu, Zhifei Ren, Yuefeng Sun, Yuanhong Zheng, Dongsheng Ma, Zirui Tang, Boyu Niu, Ziyang Miao, Hejun Dong, Siyi Qian, Junyuan Zhang, Jingzhou Chen, Fangdong Wang, Xiaomeng Zhao, Liqun Wei, Wei Li, Shasha Wang, Ruiliang Xu, Yuanyuan Cao, Lu Chen, Qianqian Wu, Huaiyu Gu, Lindong Lu, Keming Wang, Dechen Lin, Guanlin Shen, Xuanhe Zhou, Linfeng Zhang, Yuhang Zang, Xiaoyi Dong, Jiaqi Wang, Bo Zhang, Lei Bai, Pei Chu, Weijia Li, Jiang Wu, Lijun Wu, Zhenxiang Li, Guangyu Wang, Zhongying Tu, Chao Xu, Kai Chen, Yu Qiao, Bowen Zhou, Dahua Lin, Wentao Zhang, Conghui He</p><p><b>Upvotes:</b> 92</p><p><b>Summary:</b> We introduce MinerU2.5, a 1.2B-parameter document parsing vision-language model that achieves state-of-the-art recognition accuracy while maintaining exceptional computational efficiency. Our approach employs a coarse-to-fine, two-stage parsing strategy that decouples global layout analysis from local content recognition. In the first stage, the model performs efficient layout analysis on downsampled images to identify structural elements, circumventing the computational overhead of processing high-resolution inputs. In the second stage, guided by the global layout, it performs targeted content recognition on native-resolution crops extracted from the original image, preserving fine-grained details in dense text, complex formulas, and tables. To support this strategy, we developed a comprehensive data engine that generates diverse, large-scale training corpora for both pretraining and fine-tuning. Ultimately, MinerU2.5 demonstrates strong document parsing ability, achieving state-of-the-art performance on multiple benchmarks, surpassing both general-purpose and domain-specific models across various recognition tasks, while maintaining significantly lower computational overhead.</p> - https://arxiv.org/abs/2509.22186 - Fri, 26 Sep 2025 10:45:48 +0000 + Open-o3 Video: Grounded Video Reasoning with Explicit Spatio-Temporal Evidence + https://arxiv.org/abs/2510.20579 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.20579.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiahao Meng, Xiangtai Li, Haochen Wang, Yue Tan, Tao Zhang, Lingdong Kong, Yunhai Tong, Anran Wang, Zhiyang Teng, Yujing Wang, Zhuochen Wang</p><p><b>Upvotes:</b> 52</p><p><b>Summary:</b> Most video reasoning models only generate textual reasoning traces without indicating when and where key evidence appears. Recent models such as OpenAI-o3 have sparked wide interest in evidence-centered reasoning for images, yet extending this ability to videos is more challenging, as it requires joint temporal tracking and spatial localization across dynamic scenes. We introduce Open-o3 Video, a non-agent framework that integrates explicit spatio-temporal evidence into video reasoning, and carefully collect training data and design training strategies to address the aforementioned challenges. The model highlights key timestamps, objects, and bounding boxes alongside its answers, allowing reasoning to be grounded in concrete visual observations. To enable this functionality, we first curate and build two high-quality datasets, STGR-CoT-30k for SFT and STGR-RL-36k for RL, with carefully constructed temporal and spatial annotations, since most existing datasets offer either temporal spans for videos or spatial boxes on images, lacking unified spatio-temporal supervision and reasoning traces. Then, we adopt a cold-start reinforcement learning strategy with multiple specially designed rewards that jointly encourage answer accuracy, temporal alignment, and spatial precision. On V-STAR benchmark, Open-o3 Video achieves state-of-the-art performance, raising mAM by 14.4% and mLGM by 24.2% on the Qwen2.5-VL baseline. Consistent improvements are also observed on a broad range of video understanding benchmarks, including VideoMME, WorldSense, VideoMMMU, and TVGBench. Beyond accuracy, the reasoning traces produced by Open-o3 Video also provide valuable signals for test-time scaling, enabling confidence-aware verification and improving answer reliability.</p> + https://arxiv.org/abs/2510.20579 + Thu, 23 Oct 2025 14:05:56 +0000 - StableToken: A Noise-Robust Semantic Speech Tokenizer for Resilient SpeechLLMs - https://arxiv.org/abs/2509.22220 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.22220.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuhan Song, Linhao Zhang, Chuhan Wu, Aiwei Liu, Wei Jia, Houfeng Wang, Xiao Zhou</p><p><b>Upvotes:</b> 57</p><p><b>Summary:</b> Prevalent semantic speech tokenizers, designed to capture linguistic content, are surprisingly fragile. We find they are not robust to meaning-irrelevant acoustic perturbations; even at high Signal-to-Noise Ratios (SNRs) where speech is perfectly intelligible, their output token sequences can change drastically, increasing the learning burden for downstream LLMs. This instability stems from two flaws: a brittle single-path quantization architecture and a distant training signal indifferent to intermediate token stability. To address this, we introduce StableToken, a tokenizer that achieves stability through a consensus-driven mechanism. Its multi-branch architecture processes audio in parallel, and these representations are merged via a powerful bit-wise voting mechanism to form a single, stable token sequence. StableToken sets a new state-of-the-art in token stability, drastically reducing Unit Edit Distance (UED) under diverse noise conditions. This foundational stability translates directly to downstream benefits, significantly improving the robustness of SpeechLLMs on a variety of tasks.</p> - https://arxiv.org/abs/2509.22220 - Fri, 26 Sep 2025 11:32:51 +0000 + DeepAgent: A General Reasoning Agent with Scalable Toolsets + https://arxiv.org/abs/2510.21618 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.21618.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiaoxi Li, Wenxiang Jiao, Jiarui Jin, Guanting Dong, Jiajie Jin, Yinuo Wang, Hao Wang, Yutao Zhu, Ji-Rong Wen, Yuan Lu, Zhicheng Dou</p><p><b>Upvotes:</b> 89</p><p><b>Summary:</b> Large reasoning models have demonstrated strong problem-solving abilities, yet real-world tasks often require external tools and long-horizon interactions. Existing agent frameworks typically follow predefined workflows, which limit autonomous and global task completion. In this paper, we introduce DeepAgent, an end-to-end deep reasoning agent that performs autonomous thinking, tool discovery, and action execution within a single, coherent reasoning process. To address the challenges of long-horizon interactions, particularly the context length explosion from multiple tool calls and the accumulation of interaction history, we introduce an autonomous memory folding mechanism that compresses past interactions into structured episodic, working, and tool memories, reducing error accumulation while preserving critical information. To teach general-purpose tool use efficiently and stably, we develop an end-to-end reinforcement learning strategy, namely ToolPO, that leverages LLM-simulated APIs and applies tool-call advantage attribution to assign fine-grained credit to the tool invocation tokens. Extensive experiments on eight benchmarks, including general tool-use tasks (ToolBench, API-Bank, TMDB, Spotify, ToolHop) and downstream applications (ALFWorld, WebShop, GAIA, HLE), demonstrate that DeepAgent consistently outperforms baselines across both labeled-tool and open-set tool retrieval scenarios. This work takes a step toward more general and capable agents for real-world applications. The code and demo are available at https://github.com/RUC-NLPIR/DeepAgent.</p> + https://arxiv.org/abs/2510.21618 + Fri, 24 Oct 2025 16:24:01 +0000 - EPO: Entropy-regularized Policy Optimization for LLM Agents Reinforcement Learning - https://arxiv.org/abs/2509.22576 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.22576.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xu Wujiang, Wentian Zhao, Zhenting Wang, Li Yu-Jhe, Jin Can, Jin Mingyu, Mei Kai, Wan Kun, Metaxas Dimitris</p><p><b>Upvotes:</b> 115</p><p><b>Summary:</b> Training LLM agents in multi-turn environments with sparse rewards, where completing a single task requires 30+ turns of interaction within an episode, presents a fundamental challenge for reinforcement learning. We identify a critical failure mode unique to this setting: the exploration-exploitation cascade failure. This cascade begins with early-stage policy premature convergence, where sparse feedback causes agents to commit to flawed, low-entropy strategies. Subsequently, agents enter late-stage policy collapse, where conventional entropy regularization becomes counterproductive, promoting chaotic exploration that destabilizes training. We propose Entropy-regularized Policy Optimization (EPO), a general framework that breaks this failure cycle through three synergistic mechanisms: (1) adopting entropy regularization in multi-turn settings to enhance exploration, (2) an entropy smoothing regularizer that bounds policy entropy within historical averages to prevent abrupt fluctuations, and (3) adaptive phase-based weighting that balances exploration and exploitation across training. Our analysis justifies that EPO guarantees monotonically decreasing entropy variance while maintaining convergence. EPO achieves up to 152% performance improvement on ScienceWorld and up to 19.8% on ALFWorld. Our work demonstrates that multi-turn sparse-reward settings require fundamentally different entropy control than traditional RL, with broad implications for LLM agent training.</p> - https://arxiv.org/abs/2509.22576 - Fri, 26 Sep 2025 16:51:44 +0000 + Video-Thinker: Sparking "Thinking with Videos" via Reinforcement Learning + https://arxiv.org/abs/2510.23473 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.23473.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shijian Wang, Jiarui Jin, Xingjian Wang, Linxin Song, Runhao Fu, Hecheng Wang, Zongyuan Ge, Yuan Lu, Xuelian Cheng</p><p><b>Upvotes:</b> 78</p><p><b>Summary:</b> Recent advances in image reasoning methods, particularly "Thinking with Images", have demonstrated remarkable success in Multimodal Large Language Models (MLLMs); however, this dynamic reasoning paradigm has not yet been extended to video reasoning tasks. In this paper, we propose Video-Thinker, which empowers MLLMs to think with videos by autonomously leveraging their intrinsic "grounding" and "captioning" capabilities to generate reasoning clues throughout the inference process. To spark this capability, we construct Video-Thinker-10K, a curated dataset featuring autonomous tool usage within chain-of-thought reasoning sequences. Our training strategy begins with Supervised Fine-Tuning (SFT) to learn the reasoning format, followed by Group Relative Policy Optimization (GRPO) to strengthen this reasoning capability. Through this approach, Video-Thinker enables MLLMs to autonomously navigate grounding and captioning tasks for video reasoning, eliminating the need for constructing and calling external tools. Extensive experiments demonstrate that Video-Thinker achieves significant performance gains on both in-domain tasks and challenging out-of-domain video reasoning benchmarks, including Video-Holmes, CG-Bench-Reasoning, and VRBench. Our Video-Thinker-7B substantially outperforms existing baselines such as Video-R1 and establishes state-of-the-art performance among 7B-sized MLLMs.</p> + https://arxiv.org/abs/2510.23473 + Mon, 27 Oct 2025 16:10:45 +0000 - Quantile Advantage Estimation for Entropy-Safe Reasoning - https://arxiv.org/abs/2509.22611 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.22611.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junkang Wu, Kexin Huang, Jiancan Wu, An Zhang, Xiang Wang, Xiangnan He</p><p><b>Upvotes:</b> 108</p><p><b>Summary:</b> Reinforcement Learning with Verifiable Rewards (RLVR) strengthens LLM reasoning, but training often oscillates between {entropy collapse} and {entropy explosion}. We trace both hazards to the mean baseline used in value-free RL (e.g., GRPO and DAPO), which improperly penalizes negative-advantage samples under reward outliers. We propose {Quantile Advantage Estimation} (QAE), replacing the mean with a group-wise K-quantile baseline. QAE induces a response-level, two-regime gate: on hard queries (p <= 1 - K) it reinforces rare successes, while on easy queries (p > 1 - K) it targets remaining failures. Under first-order softmax updates, we prove {two-sided entropy safety}, giving lower and upper bounds on one-step entropy change that curb explosion and prevent collapse. Empirically, this minimal modification stabilizes entropy, sparsifies credit assignment (with tuned K, roughly 80% of responses receive zero advantage), and yields sustained pass@1 gains on Qwen3-8B/14B-Base across AIME 2024/2025 and AMC 2023. These results identify {baseline design} -- rather than token-level heuristics -- as the primary mechanism for scaling RLVR.</p> - https://arxiv.org/abs/2509.22611 - Fri, 26 Sep 2025 17:37:52 +0000 + JanusCoder: Towards a Foundational Visual-Programmatic Interface for Code Intelligence + https://arxiv.org/abs/2510.23538 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.23538.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qiushi Sun, Jingyang Gong, Yang Liu, Qiaosheng Chen, Lei Li, Kai Chen, Qipeng Guo, Ben Kao, Fei Yuan</p><p><b>Upvotes:</b> 88</p><p><b>Summary:</b> The scope of neural code intelligence is rapidly expanding beyond text-based source code to encompass the rich visual outputs that programs generate. This visual dimension is critical for advanced applications like flexible content generation and precise, program-driven editing of visualizations. However, progress has been impeded by the scarcity of high-quality multimodal code data, a bottleneck stemming from challenges in synthesis and quality assessment. To address these challenges, we make contributions from both a data and modeling perspective. We first introduce a complete synthesis toolkit that leverages reciprocal synergies between data modalities to efficiently produce a large-scale, high-quality corpus spanning from standard charts to complex interactive web UIs and code-driven animations. Leveraging this toolkit, we construct JanusCode-800K, the largest multimodal code corpus to date. This powers the training of our models, JanusCoder and JanusCoderV, which establish a visual-programmatic interface for generating code from textual instructions, visual inputs, or a combination of both. Our unified model is a departure from existing approaches that build specialized models for isolated tasks. Extensive experiments on both text-centric and vision-centric coding tasks demonstrate the superior performance of the JanusCoder series, with our 7B to 14B scale models approaching or even exceeding the performance of commercial models. Furthermore, extensive analysis provides key insights into harmonizing programmatic logic with its visual expression. Our code and checkpoints will are available at https://github.com/InternLM/JanusCoder.</p> + https://arxiv.org/abs/2510.23538 + Mon, 27 Oct 2025 17:13:49 +0000 - LongLive: Real-time Interactive Long Video Generation - https://arxiv.org/abs/2509.22622 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.22622.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shuai Yang, Wei Huang, Ruihang Chu, Yicheng Xiao, Yuyang Zhao, Xianbang Wang, Muyang Li, Enze Xie, Yingcong Chen, Yao Lu, Song Han, Yukang Chen</p><p><b>Upvotes:</b> 157</p><p><b>Summary:</b> We present LongLive, a frame-level autoregressive (AR) framework for real-time and interactive long video generation. Long video generation presents challenges in both efficiency and quality. Diffusion and Diffusion-Forcing models can produce high-quality videos but suffer from low efficiency due to bidirectional attention. Causal attention AR models support KV caching for faster inference, but often degrade in quality on long videos due to memory challenges during long-video training. In addition, beyond static prompt-based generation, interactive capabilities, such as streaming prompt inputs, are critical for dynamic content creation, enabling users to guide narratives in real time. This interactive requirement significantly increases complexity, especially in ensuring visual consistency and semantic coherence during prompt transitions. To address these challenges, LongLive adopts a causal, frame-level AR design that integrates a KV-recache mechanism that refreshes cached states with new prompts for smooth, adherent switches; streaming long tuning to enable long video training and to align training and inference (train-long-test-long); and short window attention paired with a frame-level attention sink, shorten as frame sink, preserving long-range consistency while enabling faster generation. With these key designs, LongLive fine-tunes a 1.3B-parameter short-clip model to minute-long generation in just 32 GPU-days. At inference, LongLive sustains 20.7 FPS on a single NVIDIA H100, achieves strong performance on VBench in both short and long videos. LongLive supports up to 240-second videos on a single H100 GPU. LongLive further supports INT8-quantized inference with only marginal quality loss.</p> - https://arxiv.org/abs/2509.22622 - Fri, 26 Sep 2025 17:48:24 +0000 + ReCode: Unify Plan and Action for Universal Granularity Control + https://arxiv.org/abs/2510.23564 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.23564.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhaoyang Yu, Jiayi Zhang, Huixue Su, Yufan Zhao, Yifan Wu, Mingyi Deng, Jinyu Xiang, Yizhang Lin, Lingxiao Tang, Yingchao Li, Yuyu Luo, Bang Liu, Chenglin Wu</p><p><b>Upvotes:</b> 115</p><p><b>Summary:</b> Real-world tasks require decisions at varying granularities, and humans excel at this by leveraging a unified cognitive representation where planning is fundamentally understood as a high-level form of action. However, current Large Language Model (LLM)-based agents lack this crucial capability to operate fluidly across decision granularities. This limitation stems from existing paradigms that enforce a rigid separation between high-level planning and low-level action, which impairs dynamic adaptability and limits generalization. We propose ReCode (Recursive Code Generation), a novel paradigm that addresses this limitation by unifying planning and action within a single code representation. In this representation, ReCode treats high-level plans as abstract placeholder functions, which the agent then recursively decomposes into finer-grained sub-functions until reaching primitive actions. This recursive approach dissolves the rigid boundary between plan and action, enabling the agent to dynamically control its decision granularity. Furthermore, the recursive structure inherently generates rich, multi-granularity training data, enabling models to learn hierarchical decision-making processes. Extensive experiments show ReCode significantly surpasses advanced baselines in inference performance and demonstrates exceptional data efficiency in training, validating our core insight that unifying planning and action through recursive code generation is a powerful and effective approach to achieving universal granularity control. The code is available at https://github.com/FoundationAgents/ReCode.</p> + https://arxiv.org/abs/2510.23564 + Mon, 27 Oct 2025 17:35:15 +0000 - Variational Reasoning for Language Models - https://arxiv.org/abs/2509.22637 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.22637.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiangxin Zhou, Zichen Liu, Haonan Wang, Chao Du, Min Lin, Chongxuan Li, Liang Wang, Tianyu Pang</p><p><b>Upvotes:</b> 58</p><p><b>Summary:</b> We introduce a variational reasoning framework for language models that treats thinking traces as latent variables and optimizes them through variational inference. Starting from the evidence lower bound (ELBO), we extend it to a multi-trace objective for tighter bounds and propose a forward-KL formulation that stabilizes the training of the variational posterior. We further show that rejection sampling finetuning and binary-reward RL, including GRPO, can be interpreted as local forward-KL objectives, where an implicit weighting by model accuracy naturally arises from the derivation and reveals a previously unnoticed bias toward easier questions. We empirically validate our method on the Qwen 2.5 and Qwen 3 model families across a wide range of reasoning tasks. Overall, our work provides a principled probabilistic perspective that unifies variational inference with RL-style methods and yields stable objectives for improving the reasoning ability of language models. Our code is available at https://github.com/sail-sg/variational-reasoning.</p> - https://arxiv.org/abs/2509.22637 - Fri, 26 Sep 2025 17:58:10 +0000 + Game-TARS: Pretrained Foundation Models for Scalable Generalist Multimodal Game Agents + https://arxiv.org/abs/2510.23691 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.23691.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zihao Wang, Xujing Li, Yining Ye, Junjie Fang, Haoming Wang, Longxiang Liu, Shihao Liang, Junting Lu, Zhiyong Wu, Jiazhan Feng, Wanjun Zhong, Zili Li, Yu Wang, Yu Miao, Bo Zhou, Yuanfan Li, Hao Wang, Zhongkai Zhao, Faming Wu, Zhengxuan Jiang, Weihao Tan, Heyuan Yao, Shi Yan, Xiangyang Li, Yitao Liang, Yujia Qin, Guang Shi</p><p><b>Upvotes:</b> 49</p><p><b>Summary:</b> We present Game-TARS, a generalist game agent trained with a unified, scalable action space anchored to human-aligned native keyboard-mouse inputs. Unlike API- or GUI-based approaches, this paradigm enables large-scale continual pre-training across heterogeneous domains, including OS, web, and simulation games. Game-TARS is pre-trained on over 500B tokens with diverse trajectories and multimodal data. Key techniques include a decaying continual loss to reduce causal confusion and an efficient Sparse-Thinking strategy that balances reasoning depth and inference cost. Experiments show that Game-TARS achieves about 2 times the success rate over the previous sota model on open-world Minecraft tasks, is close to the generality of fresh humans in unseen web 3d games, and outperforms GPT-5, Gemini-2.5-Pro, and Claude-4-Sonnet in FPS benchmarks. Scaling results on training-time and test-time confirm that the unified action space sustains improvements when scaled to cross-game and multimodal data. Our results demonstrate that simple, scalable action representations combined with large-scale pre-training provide a promising path toward generalist agents with broad computer-use abilities.</p> + https://arxiv.org/abs/2510.23691 + Mon, 27 Oct 2025 17:43:51 +0000 - Language Models Can Learn from Verbal Feedback Without Scalar Rewards - https://arxiv.org/abs/2509.22638 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.22638.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Renjie Luo, Zichen Liu, Xiangyan Liu, Chao Du, Min Lin, Wenhu Chen, Wei Lu, Tianyu Pang</p><p><b>Upvotes:</b> 57</p><p><b>Summary:</b> LLMs are often trained with RL from human or AI feedback, yet such methods typically compress nuanced feedback into scalar rewards, discarding much of their richness and inducing scale imbalance. We propose treating verbal feedback as a conditioning signal. Inspired by language priors in text-to-image generation, which enable novel outputs from unseen prompts, we introduce the feedback-conditional policy (FCP). FCP learns directly from response-feedback pairs, approximating the feedback-conditional posterior through maximum likelihood training on offline data. We further develop an online bootstrapping stage where the policy generates under positive conditions and receives fresh feedback to refine itself. This reframes feedback-driven learning as conditional generation rather than reward optimization, offering a more expressive way for LLMs to directly learn from verbal feedback. Our code is available at https://github.com/sail-sg/feedback-conditional-policy.</p> - https://arxiv.org/abs/2509.22638 - Fri, 26 Sep 2025 17:58:27 +0000 + A Survey of Data Agents: Emerging Paradigm or Overstated Hype? + https://arxiv.org/abs/2510.23587 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.23587.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yizhang Zhu, Liangwei Wang, Chenyu Yang, Xiaotian Lin, Boyan Li, Wei Zhou, Xinyu Liu, Zhangyang Peng, Tianqi Luo, Yu Li, Chengliang Chai, Chong Chen, Shimin Di, Ju Fan, Ji Sun, Nan Tang, Fugee Tsung, Jiannan Wang, Chenglin Wu, Yanwei Xu, Shaolei Zhang, Yong Zhang, Xuanhe Zhou, Guoliang Li, Yuyu Luo</p><p><b>Upvotes:</b> 62</p><p><b>Summary:</b> The rapid advancement of large language models (LLMs) has spurred the emergence of data agents--autonomous systems designed to orchestrate Data + AI ecosystems for tackling complex data-related tasks. However, the term "data agent" currently suffers from terminological ambiguity and inconsistent adoption, conflating simple query responders with sophisticated autonomous architectures. This terminological ambiguity fosters mismatched user expectations, accountability challenges, and barriers to industry growth. Inspired by the SAE J3016 standard for driving automation, this survey introduces the first systematic hierarchical taxonomy for data agents, comprising six levels that delineate and trace progressive shifts in autonomy, from manual operations (L0) to a vision of generative, fully autonomous data agents (L5), thereby clarifying capability boundaries and responsibility allocation. Through this lens, we offer a structured review of existing research arranged by increasing autonomy, encompassing specialized data agents for data management, preparation, and analysis, alongside emerging efforts toward versatile, comprehensive systems with enhanced autonomy. We further analyze critical evolutionary leaps and technical gaps for advancing data agents, especially the ongoing L2-to-L3 transition, where data agents evolve from procedural execution to autonomous orchestration. Finally, we conclude with a forward-looking roadmap, envisioning the advent of proactive, generative data agents.</p> + https://arxiv.org/abs/2510.23587 + Mon, 27 Oct 2025 17:54:07 +0000 - Multiplayer Nash Preference Optimization - https://arxiv.org/abs/2509.23102 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.23102.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fang Wu, Xu Huang, Weihao Xuan, Zhiwei Zhang, Yijia Xiao, Guancheng Wan, Xiaomin Li, Bing Hu, Peng Xia, Jure Leskovec, Yejin Choi</p><p><b>Upvotes:</b> 52</p><p><b>Summary:</b> Reinforcement learning from human feedback (RLHF) has emerged as the standard paradigm for aligning large language models (LLMs) with human preferences. However, reward-based methods built on the Bradley-Terry assumption struggle to capture the non-transitive and heterogeneous nature of real-world preferences. To address this, recent studies have reframed alignment as a two-player Nash game, giving rise to Nash learning from human feedback (NLHF). While this perspective has inspired algorithms such as INPO, ONPO, and EGPO with strong theoretical and empirical guarantees, they remain fundamentally restricted to two-player interactions, creating a single-opponent bias that fails to capture the full complexity of realistic preference structures. In this work, we introduce Multiplayer Nash Preference Optimization (MNPO), a novel framework that generalizes NLHF to the multiplayer regime. It formulates alignment as an n-player game, where each policy competes against a population of opponents while being regularized toward a reference model. Our framework establishes well-defined Nash equilibria in multiplayer settings and extends the concept of duality gap to quantify approximation quality. We demonstrate that MNPO inherits the equilibrium guarantees of two-player methods while enabling richer competitive dynamics and improved coverage of diverse preference structures. Through comprehensive empirical evaluation, we show that MNPO consistently outperforms existing NLHF baselines on instruction-following benchmarks, achieving superior alignment quality under heterogeneous annotator conditions and mixed-policy evaluation scenarios. Together, these results establish MNPO as a principled and scalable framework for aligning LLMs with complex, non-transitive human preferences. Code is available at https://github.com/smiles724/MNPO.</p> - https://arxiv.org/abs/2509.23102 - Sat, 27 Sep 2025 04:18:33 +0000 + Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations + https://arxiv.org/abs/2510.23607 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.23607.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yujia Zhang, Xiaoyang Wu, Yixing Lao, Chengyao Wang, Zhuotao Tian, Naiyan Wang, Hengshuang Zhao</p><p><b>Upvotes:</b> 166</p><p><b>Summary:</b> Humans learn abstract concepts through multisensory synergy, and once formed, such representations can often be recalled from a single modality. Inspired by this principle, we introduce Concerto, a minimalist simulation of human concept learning for spatial cognition, combining 3D intra-modal self-distillation with 2D-3D cross-modal joint embedding. Despite its simplicity, Concerto learns more coherent and informative spatial features, as demonstrated by zero-shot visualizations. It outperforms both standalone SOTA 2D and 3D self-supervised models by 14.2% and 4.8%, respectively, as well as their feature concatenation, in linear probing for 3D scene perception. With full fine-tuning, Concerto sets new SOTA results across multiple scene understanding benchmarks (e.g., 80.7% mIoU on ScanNet). We further present a variant of Concerto tailored for video-lifted point cloud spatial understanding, and a translator that linearly projects Concerto representations into CLIP's language space, enabling open-world perception. These results highlight that Concerto emerges spatial representations with superior fine-grained geometric and semantic consistency.</p> + https://arxiv.org/abs/2510.23607 + Mon, 27 Oct 2025 17:59:59 +0000 - Democratizing AI scientists using ToolUniverse - https://arxiv.org/abs/2509.23426 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.23426.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shanghua Gao, Richard Zhu, Pengwei Sui, Zhenglun Kong, Sufian Aldogom, Yepeng Huang, Ayush Noori, Reza Shamji, Krishna Parvataneni, Theodoros Tsiligkaridis, Marinka Zitnik</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> AI scientists are emerging computational systems that serve as collaborative partners in discovery. These systems remain difficult to build because they are bespoke, tied to rigid workflows, and lack shared environments that unify tools, data, and analyses into a common ecosystem. In omics, unified ecosystems have transformed research by enabling interoperability, reuse, and community-driven development; AI scientists require comparable infrastructure. We present ToolUniverse, an ecosystem for building AI scientists from any language or reasoning model, whether open or closed. TOOLUNIVERSE standardizes how AI scientists identify and call tools, integrating more than 600 machine learning models, datasets, APIs, and scientific packages for data analysis, knowledge retrieval, and experimental design. It automatically refines tool interfaces for correct use by AI scientists, creates new tools from natural language descriptions, iteratively optimizes tool specifications, and composes tools into agentic workflows. In a case study of hypercholesterolemia, ToolUniverse was used to create an AI scientist to identify a potent analog of a drug with favorable predicted properties. The open-source ToolUniverse is available at https://aiscientist.tools.</p> - https://arxiv.org/abs/2509.23426 - Sat, 27 Sep 2025 17:38:53 +0000 + RoboOmni: Proactive Robot Manipulation in Omni-modal Context + https://arxiv.org/abs/2510.23763 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.23763.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Siyin Wang, Jinlan Fu, Feihong Liu, Xinzhe He, Huangxuan Wu, Junhao Shi, Kexin Huang, Zhaoye Fei, Jingjing Gong, Zuxuan Wu, Yugang Jiang, See-Kiong Ng, Tat-Seng Chua, Xipeng Qiu</p><p><b>Upvotes:</b> 52</p><p><b>Summary:</b> Recent advances in Multimodal Large Language Models (MLLMs) have driven rapid progress in Vision-Language-Action (VLA) models for robotic manipulation. Although effective in many scenarios, current approaches largely rely on explicit instructions, whereas in real-world interactions, humans rarely issue instructions directly. Effective collaboration requires robots to infer user intentions proactively. In this work, we introduce cross-modal contextual instructions, a new setting where intent is derived from spoken dialogue, environmental sounds, and visual cues rather than explicit commands. To address this new setting, we present RoboOmni, a Perceiver-Thinker-Talker-Executor framework based on end-to-end omni-modal LLMs that unifies intention recognition, interaction confirmation, and action execution. RoboOmni fuses auditory and visual signals spatiotemporally for robust intention recognition, while supporting direct speech interaction. To address the absence of training data for proactive intention recognition in robotic manipulation, we build OmniAction, comprising 140k episodes, 5k+ speakers, 2.4k event sounds, 640 backgrounds, and six contextual instruction types. Experiments in simulation and real-world settings show that RoboOmni surpasses text- and ASR-based baselines in success rate, inference speed, intention recognition, and proactive assistance.</p> + https://arxiv.org/abs/2510.23763 + Mon, 27 Oct 2025 18:49:03 +0000 - Beyond the Exploration-Exploitation Trade-off: A Hidden State Approach for LLM Reasoning in RLVR - https://arxiv.org/abs/2509.23808 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.23808.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fanding Huang, Guanbo Huang, Xiao Fan, Yi He, Xiao Liang, Xiao Chen, Qinting Jiang, Faisal Nadeem Khan, Jingyan Jiang, Zhi Wang</p><p><b>Upvotes:</b> 38</p><p><b>Summary:</b> A prevailing view in Reinforcement Learning for Verifiable Rewards (RLVR) interprets recent progress through the lens of an exploration-exploitation trade-off, a perspective largely shaped by token-level metrics. We re-examine this perspective, proposing that this perceived trade-off may not be a fundamental constraint but rather an artifact of the measurement level. To investigate this, we shift the analysis to the semantically rich hidden-state space, adopting Effective Rank (ER) to quantify exploration and proposing its novel first- and second-order derivatives, named Effective Rank Velocity (ERV) and Effective Rank Acceleration (ERA), to capture exploitation dynamics. Our analysis reveals that at the hidden-state level, exploration and exploitation could be decoupled (Sec. 4). This finding reveals an opportunity to enhance both capacities simultaneously. This insight motivates our method, Velocity-Exploiting Rank-Learning (VERL), the first to operationalize the principle of synergistic exploration-exploitation enhancement by directly shaping the RL advantage function. The key innovation is leveraging the theoretically stable ERA as a predictive meta-controller to create a synergistic, dual-channel incentive structure. Instead of forcing a trade-off, VERL prospectively amplifies rewards for exploration to preempt overconfidence and reinforces exploitative gains to consolidate reasoning. Experiments across diverse LLMs and reasoning benchmarks show consistent gains, including up to 21.4% absolute accuracy improvement on the challenging Gaokao 2024 dataset.</p> - https://arxiv.org/abs/2509.23808 - Sun, 28 Sep 2025 11:14:58 +0000 + ReForm: Reflective Autoformalization with Prospective Bounded Sequence Optimization + https://arxiv.org/abs/2510.24592 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.24592.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Guoxin Chen, Jing Wu, Xinjie Chen, Wayne Xin Zhao, Ruihua Song, Chengxi Li, Kai Fan, Dayiheng Liu, Minpeng Liao</p><p><b>Upvotes:</b> 48</p><p><b>Summary:</b> Autoformalization, which translates natural language mathematics into machine-verifiable formal statements, is critical for using formal mathematical reasoning to solve math problems stated in natural language. While Large Language Models can generate syntactically correct formal statements, they often fail to preserve the original problem's semantic intent. This limitation arises from the LLM approaches' treating autoformalization as a simplistic translation task which lacks mechanisms for self-reflection and iterative refinement that human experts naturally employ. To address these issues, we propose ReForm, a Reflective Autoformalization method that tightly integrates semantic consistency evaluation into the autoformalization process. This enables the model to iteratively generate formal statements, assess its semantic fidelity, and self-correct identified errors through progressive refinement. To effectively train this reflective model, we introduce Prospective Bounded Sequence Optimization (PBSO), which employs different rewards at different sequence positions to ensure that the model develops both accurate autoformalization and correct semantic validations, preventing superficial critiques that would undermine the purpose of reflection. Extensive experiments across four autoformalization benchmarks demonstrate that ReForm achieves an average improvement of 17.2 percentage points over the strongest baselines. To further ensure evaluation reliability, we introduce ConsistencyCheck, a benchmark of 859 expert-annotated items that not only validates LLMs as judges but also reveals that autoformalization is inherently difficult: even human experts produce semantic errors in up to 38.5% of cases.</p> + https://arxiv.org/abs/2510.24592 + Tue, 28 Oct 2025 16:22:54 +0000 - SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse-Linear Attention - https://arxiv.org/abs/2509.24006 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.24006.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jintao Zhang, Haoxu Wang, Kai Jiang, Shuo Yang, Kaiwen Zheng, Haocheng Xi, Ziteng Wang, Hongzhou Zhu, Min Zhao, Ion Stoica, Joseph E. Gonzalez, Jun Zhu, Jianfei Chen</p><p><b>Upvotes:</b> 98</p><p><b>Summary:</b> In Diffusion Transformer (DiT) models, particularly for video generation, attention latency is a major bottleneck due to the long sequence length and the quadratic complexity. We find that attention weights can be separated into two parts: a small fraction of large weights with high rank and the remaining weights with very low rank. This naturally suggests applying sparse acceleration to the first part and low-rank acceleration to the second. Based on this finding, we propose SLA (Sparse-Linear Attention), a trainable attention method that fuses sparse and linear attention to accelerate diffusion models. SLA classifies attention weights into critical, marginal, and negligible categories, applying O(N^2) attention to critical weights, O(N) attention to marginal weights, and skipping negligible ones. SLA combines these computations into a single GPU kernel and supports both forward and backward passes. With only a few fine-tuning steps using SLA, DiT models achieve a 20x reduction in attention computation, resulting in significant acceleration without loss of generation quality. Experiments show that SLA reduces attention computation by 95% without degrading end-to-end generation quality, outperforming baseline methods. In addition, we implement an efficient GPU kernel for SLA, which yields a 13.7x speedup in attention computation and a 2.2x end-to-end speedup in video generation on Wan2.1-1.3B.</p> - https://arxiv.org/abs/2509.24006 - Sun, 28 Sep 2025 17:58:59 +0000 + InteractComp: Evaluating Search Agents With Ambiguous Queries + https://arxiv.org/abs/2510.24668 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.24668.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mingyi Deng, Lijun Huang, Yani Fan, Jiayi Zhang, Fashen Ren, Jinyi Bai, Fuzhen Yang, Dayi Miao, Zhaoyang Yu, Yifan Wu, Yanfei Zhang, Fengwei Teng, Yingjia Wan, Song Hu, Yude Li, Xin Jin, Conghao Hu, Haoyu Li, Qirui Fu, Tai Zhong, Xinyu Wang, Xiangru Tang, Nan Tang, Chenglin Wu, Yuyu Luo</p><p><b>Upvotes:</b> 93</p><p><b>Summary:</b> Language agents have demonstrated remarkable potential in web search and information retrieval. However, these search agents assume user queries are complete and unambiguous, an assumption that diverges from reality where users begin with incomplete queries requiring clarification through interaction. Yet most agents lack interactive mechanisms during the search process, and existing benchmarks cannot assess this capability. To address this gap, we introduce InteractComp, a benchmark designed to evaluate whether search agents can recognize query ambiguity and actively interact to resolve it during search. Following the principle of easy to verify, interact to disambiguate, we construct 210 expert-curated questions across 9 domains through a target-distractor methodology that creates genuine ambiguity resolvable only through interaction. Evaluation of 17 models reveals striking failure: the best model achieves only 13.73% accuracy despite 71.50% with complete context, exposing systematic overconfidence rather than reasoning deficits. Forced interaction produces dramatic gains, demonstrating latent capability current strategies fail to engage. Longitudinal analysis shows interaction capabilities stagnated over 15 months while search performance improved seven-fold, revealing a critical blind spot. This stagnation, coupled with the immediate feedback inherent to search tasks, makes InteractComp a valuable resource for both evaluating and training interaction capabilities in search agents. The code is available at https://github.com/FoundationAgents/InteractComp.</p> + https://arxiv.org/abs/2510.24668 + Tue, 28 Oct 2025 17:35:54 +0000 - SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer - https://arxiv.org/abs/2509.24695 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.24695.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junsong Chen, Yuyang Zhao, Jincheng Yu, Ruihang Chu, Junyu Chen, Shuai Yang, Xianbang Wang, Yicheng Pan, Daquan Zhou, Huan Ling, Haozhe Liu, Hongwei Yi, Hao Zhang, Muyang Li, Yukang Chen, Han Cai, Sanja Fidler, Ping Luo, Song Han, Enze Xie</p><p><b>Upvotes:</b> 35</p><p><b>Summary:</b> We introduce SANA-Video, a small diffusion model that can efficiently generate videos up to 720x1280 resolution and minute-length duration. SANA-Video synthesizes high-resolution, high-quality and long videos with strong text-video alignment at a remarkably fast speed, deployable on RTX 5090 GPU. Two core designs ensure our efficient, effective and long video generation: (1) Linear DiT: We leverage linear attention as the core operation, which is more efficient than vanilla attention given the large number of tokens processed in video generation. (2) Constant-Memory KV cache for Block Linear Attention: we design block-wise autoregressive approach for long video generation by employing a constant-memory state, derived from the cumulative properties of linear attention. This KV cache provides the Linear DiT with global context at a fixed memory cost, eliminating the need for a traditional KV cache and enabling efficient, minute-long video generation. In addition, we explore effective data filters and model training strategies, narrowing the training cost to 12 days on 64 H100 GPUs, which is only 1% of the cost of MovieGen. Given its low cost, SANA-Video achieves competitive performance compared to modern state-of-the-art small diffusion models (e.g., Wan 2.1-1.3B and SkyReel-V2-1.3B) while being 16x faster in measured latency. Moreover, SANA-Video can be deployed on RTX 5090 GPUs with NVFP4 precision, accelerating the inference speed of generating a 5-second 720p video from 71s to 29s (2.4x speedup). In summary, SANA-Video enables low-cost, high-quality video generation.</p> - https://arxiv.org/abs/2509.24695 - Mon, 29 Sep 2025 12:28:09 +0000 + AgentFold: Long-Horizon Web Agents with Proactive Context Management + https://arxiv.org/abs/2510.24699 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.24699.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Rui Ye, Zhongwang Zhang, Kuan Li, Huifeng Yin, Zhengwei Tao, Yida Zhao, Liangcai Su, Liwen Zhang, Zile Qiao, Xinyu Wang, Pengjun Xie, Fei Huang, Siheng Chen, Jingren Zhou, Yong Jiang</p><p><b>Upvotes:</b> 60</p><p><b>Summary:</b> LLM-based web agents show immense promise for information seeking, yet their effectiveness on long-horizon tasks is hindered by a fundamental trade-off in context management. Prevailing ReAct-based agents suffer from context saturation as they accumulate noisy, raw histories, while methods that fixedly summarize the full history at each step risk the irreversible loss of critical details. Addressing these, we introduce AgentFold, a novel agent paradigm centered on proactive context management, inspired by the human cognitive process of retrospective consolidation. AgentFold treats its context as a dynamic cognitive workspace to be actively sculpted, rather than a passive log to be filled. At each step, it learns to execute a `folding' operation, which manages its historical trajectory at multiple scales: it can perform granular condensations to preserve vital, fine-grained details, or deep consolidations to abstract away entire multi-step sub-tasks. The results on prominent benchmarks are striking: with simple supervised fine-tuning (without continual pre-training or RL), our AgentFold-30B-A3B agent achieves 36.2% on BrowseComp and 47.3% on BrowseComp-ZH. Notably, this performance not only surpasses or matches open-source models of a dramatically larger scale, such as the DeepSeek-V3.1-671B-A37B, but also surpasses leading proprietary agents like OpenAI's o4-mini.</p> + https://arxiv.org/abs/2510.24699 + Tue, 28 Oct 2025 17:51:50 +0000 - RealUnify: Do Unified Models Truly Benefit from Unification? A Comprehensive Benchmark - https://arxiv.org/abs/2509.24897 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.24897.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yang Shi, Yuhao Dong, Yue Ding, Yuran Wang, Xuanyu Zhu, Sheng Zhou, Wenting Liu, Haochen Tian, Rundong Wang, Huanqian Wang, Zuyan Liu, Bohan Zeng, Ruizhe Chen, Qixun Wang, Zhuoran Zhang, Xinlong Chen, Chengzhuo Tong, Bozhou Li, Chaoyou Fu, Qiang Liu, Haotian Wang, Wenjing Yang, Yuanxing Zhang, Pengfei Wan, Yi-Fan Zhang, Ziwei Liu</p><p><b>Upvotes:</b> 41</p><p><b>Summary:</b> The integration of visual understanding and generation into unified multimodal models represents a significant stride toward general-purpose AI. However, a fundamental question remains unanswered by existing benchmarks: does this architectural unification actually enable synergetic interaction between the constituent capabilities? Existing evaluation paradigms, which primarily assess understanding and generation in isolation, are insufficient for determining whether a unified model can leverage its understanding to enhance its generation, or use generative simulation to facilitate deeper comprehension. To address this critical gap, we introduce RealUnify, a benchmark specifically designed to evaluate bidirectional capability synergy. RealUnify comprises 1,000 meticulously human-annotated instances spanning 10 categories and 32 subtasks. It is structured around two core axes: 1) Understanding Enhances Generation, which requires reasoning (e.g., commonsense, logic) to guide image generation, and 2) Generation Enhances Understanding, which necessitates mental simulation or reconstruction (e.g., of transformed or disordered visual inputs) to solve reasoning tasks. A key contribution is our dual-evaluation protocol, which combines direct end-to-end assessment with a diagnostic stepwise evaluation that decomposes tasks into distinct understanding and generation phases. This protocol allows us to precisely discern whether performance bottlenecks stem from deficiencies in core abilities or from a failure to integrate them. Through large-scale evaluations of 12 leading unified models and 6 specialized baselines, we find that current unified models still struggle to achieve effective synergy, indicating that architectural unification alone is insufficient. These results highlight the need for new training strategies and inductive biases to fully unlock the potential of unified modeling.</p> - https://arxiv.org/abs/2509.24897 - Mon, 29 Sep 2025 15:07:28 +0000 + Tongyi DeepResearch Technical Report + https://arxiv.org/abs/2510.24701 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.24701.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tongyi DeepResearch Team, Baixuan Li, Bo Zhang, Dingchu Zhang, Fei Huang, Guangyu Li, Guoxin Chen, Huifeng Yin, Jialong Wu, Jingren Zhou, Kuan Li, Liangcai Su, Litu Ou, Liwen Zhang, Pengjun Xie, Rui Ye, Wenbiao Yin, Xinmiao Yu, Xinyu Wang, Xixi Wu, Xuanzhong Chen, Yida Zhao, Zhen Zhang, Zhengwei Tao, Zhongwang Zhang, Zile Qiao, Chenxi Wang, Donglei Yu, Gang Fu, Haiyang Shen, Jiayin Yang, Jun Lin, Junkai Zhang, Kui Zeng, Li Yang, Hailong Yin, Maojia Song, Ming Yan, Peng Xia, Qian Xiao, Rui Min, Ruixue Ding, Runnan Fang, Shaowei Chen, Shen Huang, Shihang Wang, Shihao Cai, Weizhou Shen, Xiaobin Wang, Xin Guan, Xinyu Geng, Yingcheng Shi, Yuning Wu, Zhuo Chen, Zijian Li, Yong Jiang</p><p><b>Upvotes:</b> 81</p><p><b>Summary:</b> We present Tongyi DeepResearch, an agentic large language model, which is specifically designed for long-horizon, deep information-seeking research tasks. To incentivize autonomous deep research agency, Tongyi DeepResearch is developed through an end-to-end training framework that combines agentic mid-training and agentic post-training, enabling scalable reasoning and information seeking across complex tasks. We design a highly scalable data synthesis pipeline that is fully automatic, without relying on costly human annotation, and empowers all training stages. By constructing customized environments for each stage, our system enables stable and consistent interactions throughout. Tongyi DeepResearch, featuring 30.5 billion total parameters, with only 3.3 billion activated per token, achieves state-of-the-art performance across a range of agentic deep research benchmarks, including Humanity's Last Exam, BrowseComp, BrowseComp-ZH, WebWalkerQA, xbench-DeepSearch, FRAMES and xbench-DeepSearch-2510. We open-source the model, framework, and complete solutions to empower the community.</p> + https://arxiv.org/abs/2510.24701 + Tue, 28 Oct 2025 17:53:02 +0000 - OpenGPT-4o-Image: A Comprehensive Dataset for Advanced Image Generation and Editing - https://arxiv.org/abs/2509.24900 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.24900.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhihong Chen, Xuehai Bai, Yang Shi, Chaoyou Fu, Huanyu Zhang, Haotian Wang, Xiaoyan Sun, Zhang Zhang, Liang Wang, Yuanxing Zhang, Pengfei Wan, Yi-Fan Zhang</p><p><b>Upvotes:</b> 38</p><p><b>Summary:</b> The performance of unified multimodal models for image generation and editing is fundamentally constrained by the quality and comprehensiveness of their training data. While existing datasets have covered basic tasks like style transfer and simple object manipulation, they often lack the systematic structure and challenging scenarios required for real-world applications. To address this bottleneck, we introduce OpenGPT-4o-Image, a large-scale dataset constructed using a novel methodology that combines hierarchical task taxonomy with automated data generation. Our taxonomy not only includes fundamental capabilities such as text rendering and style control but also introduces highly practical yet challenging categories like scientific imagery for chemistry illustrations and complex instruction editing requiring simultaneous execution of multiple operations. Through an automated pipeline leveraging structured resource pools and GPT-4o, we generate 80k high-quality instruction-image pairs with controlled diversity, covering 11 major domains and 51 subtasks. Extensive experiments show that fine-tuning leading models on our dataset achieves significant performance gains across multiple benchmarks, with improvements of up to 18\% on editing tasks (UniWorld-V1 on ImgEdit-Bench) and 13% on generation tasks (Harmon on GenEval). Our work demonstrates that systematic data construction is key to advancing multimodal AI capabilities.</p> - https://arxiv.org/abs/2509.24900 - Mon, 29 Sep 2025 15:11:09 +0000 + Scaling Latent Reasoning via Looped Language Models + https://arxiv.org/abs/2510.25741 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.25741.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Rui-Jie Zhu, Zixuan Wang, Kai Hua, Tianyu Zhang, Ziniu Li, Haoran Que, Boyi Wei, Zixin Wen, Fan Yin, He Xing, Lu Li, Jiajun Shi, Kaijing Ma, Shanda Li, Taylor Kergan, Andrew Smith, Xingwei Qu, Mude Hui, Bohong Wu, Qiyang Min, Hongzhi Huang, Xun Zhou, Wei Ye, Jiaheng Liu, Jian Yang, Yunfeng Shi, Chenghua Lin, Enduo Zhao, Tianle Cai, Ge Zhang, Wenhao Huang, Yoshua Bengio, Jason Eshraghian</p><p><b>Upvotes:</b> 64</p><p><b>Summary:</b> Modern LLMs are trained to "think" primarily via explicit text generation, such as chain-of-thought (CoT), which defers reasoning to post-training and under-leverages pre-training data. We present and open-source Ouro, named after the recursive Ouroboros, a family of pre-trained Looped Language Models (LoopLM) that instead build reasoning into the pre-training phase through (i) iterative computation in latent space, (ii) an entropy-regularized objective for learned depth allocation, and (iii) scaling to 7.7T tokens. Ouro 1.4B and 2.6B models enjoy superior performance that match the results of up to 12B SOTA LLMs across a wide range of benchmarks. Through controlled experiments, we show this advantage stems not from increased knowledge capacity, but from superior knowledge manipulation capabilities. We also show that LoopLM yields reasoning traces more aligned with final outputs than explicit CoT. We hope our results show the potential of LoopLM as a novel scaling direction in the reasoning era. Our model could be found in: http://ouro-llm.github.io.</p> + https://arxiv.org/abs/2510.25741 + Wed, 29 Oct 2025 17:45:42 +0000 - Visual Jigsaw Post-Training Improves MLLMs - https://arxiv.org/abs/2509.25190 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.25190.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Penghao Wu, Yushan Zhang, Haiwen Diao, Bo Li, Lewei Lu, Ziwei Liu</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> Reinforcement learning based post-training has recently emerged as a powerful paradigm for enhancing the alignment and reasoning capabilities of multimodal large language models (MLLMs). While vision-centric post-training is crucial for enhancing MLLMs' intrinsic understanding of visual signals, current post-training paradigms are predominantly text-centric, where dense visual inputs are only leveraged to extract sparse cues for text-based reasoning. There exist a few approaches in this direction, however, they often still rely on text as an intermediate mediator or introduce additional visual generative designs. In this work, we introduce Visual Jigsaw, a generic self-supervised post-training framework designed to strengthen visual understanding in MLLMs. Visual Jigsaw is formulated as a general ordering task: visual inputs are partitioned, shuffled, and the model must reconstruct the visual information by producing the correct permutation in natural language. This naturally aligns with reinforcement learning from verifiable rewards (RLVR), requires no additional visual generative components, and derives its supervisory signal automatically without any annotations. We instantiate Visual Jigsaw across three visual modalities, including images, videos, and 3D data. Extensive experiments demonstrate substantial improvements in fine-grained perception, temporal reasoning, and 3D spatial understanding. Our findings highlight the potential of self-supervised vision-centric tasks in post-training MLLMs and aim to inspire further research on vision-centric pretext designs. Project Page: https://penghao-wu.github.io/visual_jigsaw/</p> - https://arxiv.org/abs/2509.25190 - Mon, 29 Sep 2025 17:59:57 +0000 + Emu3.5: Native Multimodal Models are World Learners + https://arxiv.org/abs/2510.26583 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.26583.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yufeng Cui, Honghao Chen, Haoge Deng, Xu Huang, Xinghang Li, Jirong Liu, Yang Liu, Zhuoyan Luo, Jinsheng Wang, Wenxuan Wang, Yueze Wang, Chengyuan Wang, Fan Zhang, Yingli Zhao, Ting Pan, Xianduo Li, Zecheng Hao, Wenxuan Ma, Zhuo Chen, Yulong Ao, Tiejun Huang, Zhongyuan Wang, Xinlong Wang</p><p><b>Upvotes:</b> 56</p><p><b>Summary:</b> We introduce Emu3.5, a large-scale multimodal world model that natively predicts the next state across vision and language. Emu3.5 is pre-trained end-to-end with a unified next-token prediction objective on a corpus of vision-language interleaved data containing over 10 trillion tokens, primarily derived from sequential frames and transcripts of internet videos. The model naturally accepts interleaved vision-language inputs and generates interleaved vision-language outputs. Emu3.5 is further post-trained with large-scale reinforcement learning to enhance multimodal reasoning and generation. To improve inference efficiency, we propose Discrete Diffusion Adaptation (DiDA), which converts token-by-token decoding into bidirectional parallel prediction, accelerating per-image inference by about 20x without sacrificing performance. Emu3.5 exhibits strong native multimodal capabilities, including long-horizon vision-language generation, any-to-image (X2I) generation, and complex text-rich image generation. It also exhibits generalizable world-modeling abilities, enabling spatiotemporally consistent world exploration and open-world embodied manipulation across diverse scenarios and tasks. For comparison, Emu3.5 achieves performance comparable to Gemini 2.5 Flash Image (Nano Banana) on image generation and editing tasks and demonstrates superior results on a suite of interleaved generation tasks. We open-source Emu3.5 at https://github.com/baaivision/Emu3.5 to support community research.</p> + https://arxiv.org/abs/2510.26583 + Thu, 30 Oct 2025 15:11:16 +0000