bot: update RSS feed
This commit is contained in:
github-actions[bot]
230
feed.xml
230
feed.xml
@@ -7,146 +7,174 @@
|
|||||||
<docs>http://www.rssboard.org/rss-specification</docs>
|
<docs>http://www.rssboard.org/rss-specification</docs>
|
||||||
<generator>python-feedgen</generator>
|
<generator>python-feedgen</generator>
|
||||||
<language>en</language>
|
<language>en</language>
|
||||||
<lastBuildDate>Tue, 18 Nov 2025 00:02:38 +0000</lastBuildDate>
|
<lastBuildDate>Wed, 19 Nov 2025 00:02:47 +0000</lastBuildDate>
|
||||||
<item>
|
<item>
|
||||||
<title>Large Language Models for Scientific Idea Generation: A Creativity-Centered Survey</title>
|
<title>Dynamic Reflections: Probing Video Representations with Text Alignment</title>
|
||||||
<link>https://arxiv.org/abs/2511.07448</link>
|
<link>https://arxiv.org/abs/2511.02767</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.07448.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fatemeh Shahhosseini, Arash Marioriyad, Ali Momen, Mahdieh Soleymani Baghshah, Mohammad Hossein Rohban, Shaghayegh Haghjooy Javanmard</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Scientific idea generation lies at the heart of scientific discovery and has driven human progress-whether by solving unsolved problems or proposing novel hypotheses to explain unknown phenomena. Unlike standard scientific reasoning or general creative generation, idea generation in science is a multi-objective and open-ended task, where the novelty of a contribution is as essential as its empirical soundness. Large language models (LLMs) have recently emerged as promising generators of scientific ideas, capable of producing coherent and factual outputs with surprising intuition and acceptable reasoning, yet their creative capacity remains inconsistent and poorly understood. This survey provides a structured synthesis of methods for LLM-driven scientific ideation, examining how different approaches balance creativity with scientific soundness. We categorize existing methods into five complementary families: External knowledge augmentation, Prompt-based distributional steering, Inference-time scaling, Multi-agent collaboration, and Parameter-level adaptation. To interpret their contributions, we employ two complementary frameworks: Boden's taxonomy of Combinatorial, Exploratory and Transformational creativity to characterize the level of ideas each family expected to generate, and Rhodes' 4Ps framework-Person, Process, Press, and Product-to locate the aspect or source of creativity that each method emphasizes. By aligning methodological advances with creativity frameworks, this survey clarifies the state of the field and outlines key directions toward reliable, systematic, and transformative applications of LLMs in scientific discovery.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.02767.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tyler Zhu, Tengda Han, Leonidas Guibas, Viorica Pătrăucean, Maks Ovsjanikov</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> The alignment of representations from different modalities has recently been shown to provide insights on the structural similarities and downstream capabilities of different encoders across diverse data types. While significant progress has been made in aligning images with text, the temporal nature of video data remains largely unexplored in this context. In this work, we conduct the first comprehensive study of video-text representation alignment, probing the capabilities of modern video and language encoders. Our findings reveal several key insights. First, we demonstrate that cross-modal alignment highly depends on the richness of both visual (static images vs. multi-frame videos) and text (single caption vs. a collection) data provided at test time, especially when using state-of-the-art video encoders. We propose parametric test-time scaling laws that capture this behavior and show remarkable predictive power against empirical observations. Secondly, we investigate the correlation between semantic alignment and performance on both semantic and non-semantic downstream tasks, providing initial evidence that strong alignment against text encoders may be linked to general-purpose video representation and understanding. Finally, we correlate temporal reasoning with cross-modal alignment providing a challenging test-bed for vision and language models. Overall, our work introduces video-text alignment as an informative zero-shot way to probe the representation power of different encoders for spatio-temporal data. Project page can be found at https://video-prh.github.io/</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2511.07448</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2511.02767</guid>
|
||||||
<pubDate>Wed, 05 Nov 2025 07:50:43 +0000</pubDate>
|
<pubDate>Tue, 04 Nov 2025 17:52:14 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>SpatialThinker: Reinforcing 3D Reasoning in Multimodal LLMs via Spatial Rewards</title>
|
<title>GroupRank: A Groupwise Reranking Paradigm Driven by Reinforcement Learning</title>
|
||||||
<link>https://arxiv.org/abs/2511.07403</link>
|
<link>https://arxiv.org/abs/2511.11653</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.07403.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hunar Batra, Haoqin Tu, Hardy Chen, Yuanze Lin, Cihang Xie, Ronald Clark</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Multimodal large language models (MLLMs) have achieved remarkable progress in vision-language tasks, but they continue to struggle with spatial understanding. Existing spatial MLLMs often rely on explicit 3D inputs or architecture-specific modifications, and remain constrained by large-scale datasets or sparse supervision. To address these limitations, we introduce SpatialThinker, a 3D-aware MLLM trained with RL to integrate structured spatial grounding with multi-step reasoning. The model simulates human-like spatial perception by constructing a scene graph of task-relevant objects and spatial relations, and reasoning towards an answer via dense spatial rewards. SpatialThinker consists of two key contributions: (1) a data synthesis pipeline that generates STVQA-7K, a high-quality spatial VQA dataset, and (2) online RL with a multi-objective dense spatial reward enforcing spatial grounding. SpatialThinker-7B outperforms supervised fine-tuning and the sparse RL baseline on spatial understanding and real-world VQA benchmarks, nearly doubling the base-model gain compared to sparse RL, and surpassing GPT-4o. These results showcase the effectiveness of combining spatial supervision with reward-aligned reasoning in enabling robust 3D spatial understanding with limited data and advancing MLLMs towards human-level visual reasoning.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.11653.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Duolin Sun, Meixiu Long, Dan Yang, Yihan Jiao, Zhehao Tan, Jie Feng, Junjie Wang, Yue Shen, Peng Wei, Jian Wang, Jinjie Gu</p><p><b>Upvotes:</b> 40</p><p><b>Summary:</b> Large Language Models have shown strong potential as rerankers to enhance the overall performance of RAG systems. However, existing reranking paradigms are constrained by a core theoretical and practical dilemma: Pointwise methods, while simple and highly flexible, evaluate documents independently, making them prone to the Ranking Myopia Trap, overlooking the relative importance between documents. In contrast, Listwise methods can perceive the global ranking context, but suffer from inherent List Rigidity, leading to severe scalability and flexibility issues when handling large candidate sets. To address these challenges, we propose Groupwise, a novel reranking paradigm. In this approach, the query and a group of candidate documents are jointly fed into the model, which performs within-group comparisons to assign individual relevance scores to each document. This design retains the flexibility of Pointwise methods while enabling the comparative capability of Listwise methods. We further adopt GRPO for model training, equipped with a heterogeneous reward function that integrates ranking metrics with a distributional reward aimed at aligning score distributions across groups. To overcome the bottleneck caused by the scarcity of high quality labeled data, we further propose an innovative pipeline for synthesizing high quality retrieval and ranking data. The resulting data can be leveraged not only for training the reranker but also for training the retriever. Extensive experiments validate the effectiveness of our approach. On two reasoning intensive retrieval benchmarks, BRIGHT and R2MED.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2511.07403</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2511.11653</guid>
|
||||||
<pubDate>Mon, 10 Nov 2025 18:52:47 +0000</pubDate>
|
<pubDate>Mon, 10 Nov 2025 15:25:31 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>UI2Code^N: A Visual Language Model for Test-Time Scalable Interactive UI-to-Code Generation</title>
|
<title>A Decentralized Retrieval Augmented Generation System with Source Reliabilities Secured on Blockchain</title>
|
||||||
<link>https://arxiv.org/abs/2511.08195</link>
|
<link>https://arxiv.org/abs/2511.07577</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.08195.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhen Yang, Wenyi Hong, Mingde Xu, Xinyue Fan, Weihan Wang, Jiele Cheng, Xiaotao Gu, Jie Tang</p><p><b>Upvotes:</b> 28</p><p><b>Summary:</b> User interface (UI) programming is a core yet highly complex part of modern software development. Recent advances in visual language models (VLMs) highlight the potential of automatic UI coding, but current approaches face two key limitations: multimodal coding capabilities remain underdeveloped, and single-turn paradigms make little use of iterative visual feedback. We address these challenges with an interactive UI-to-code paradigm that better reflects real-world workflows and raises the upper bound of achievable performance. Under this paradigm, we present UI2Code^N, a visual language model trained through staged pretraining, fine-tuning, and reinforcement learning to achieve foundational improvements in multimodal coding. The model unifies three key capabilities: UI-to-code generation, UI editing, and UI polishing. We further explore test-time scaling for interactive generation, enabling systematic use of multi-turn feedback. Experiments on UI-to-code and UI polishing benchmarks show that UI2Code^N establishes a new state of the art among open-source models and achieves performance comparable to leading closed-source models such as Claude-4-Sonnet and GPT-5. Our code and models are available at https://github.com/zai-org/UI2Code_N.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.07577.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yining Lu, Wenyi Tang, Max Johnson, Taeho Jung, Meng Jiang</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Existing retrieval-augmented generation (RAG) systems typically use a centralized architecture, causing a high cost of data collection, integration, and management, as well as privacy concerns. There is a great need for a decentralized RAG system that enables foundation models to utilize information directly from data owners who maintain full control over their sources. However, decentralization brings a challenge: the numerous independent data sources vary significantly in reliability, which can diminish retrieval accuracy and response quality. To address this, our decentralized RAG system has a novel reliability scoring mechanism that dynamically evaluates each source based on the quality of responses it contributes to generate and prioritizes high-quality sources during retrieval. To ensure transparency and trust, the scoring process is securely managed through blockchain-based smart contracts, creating verifiable and tamper-proof reliability records without relying on a central authority. We evaluate our decentralized system with two Llama models (3B and 8B) in two simulated environments where six data sources have different levels of reliability. Our system achieves a +10.7\% performance improvement over its centralized counterpart in the real world-like unreliable data environments. Notably, it approaches the upper-bound performance of centralized systems under ideally reliable data environments. The decentralized infrastructure enables secure and trustworthy scoring management, achieving approximately 56\% marginal cost savings through batched update operations. Our code and system are open-sourced at github.com/yining610/Reliable-dRAG.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2511.08195</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2511.07577</guid>
|
||||||
<pubDate>Tue, 11 Nov 2025 13:00:09 +0000</pubDate>
|
<pubDate>Mon, 10 Nov 2025 19:40:30 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Simulating the Visual World with Artificial Intelligence: A Roadmap</title>
|
<title>MMaDA-Parallel: Multimodal Large Diffusion Language Models for Thinking-Aware Editing and Generation</title>
|
||||||
<link>https://arxiv.org/abs/2511.08585</link>
|
<link>https://arxiv.org/abs/2511.09611</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.08585.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jingtong Yue, Ziqi Huang, Zhaoxi Chen, Xintao Wang, Pengfei Wan, Ziwei Liu</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> The landscape of video generation is shifting, from a focus on generating visually appealing clips to building virtual environments that support interaction and maintain physical plausibility. These developments point toward the emergence of video foundation models that function not only as visual generators but also as implicit world models, models that simulate the physical dynamics, agent-environment interactions, and task planning that govern real or imagined worlds. This survey provides a systematic overview of this evolution, conceptualizing modern video foundation models as the combination of two core components: an implicit world model and a video renderer. The world model encodes structured knowledge about the world, including physical laws, interaction dynamics, and agent behavior. It serves as a latent simulation engine that enables coherent visual reasoning, long-term temporal consistency, and goal-driven planning. The video renderer transforms this latent simulation into realistic visual observations, effectively producing videos as a "window" into the simulated world. We trace the progression of video generation through four generations, in which the core capabilities advance step by step, ultimately culminating in a world model, built upon a video generation model, that embodies intrinsic physical plausibility, real-time multimodal interaction, and planning capabilities spanning multiple spatiotemporal scales. For each generation, we define its core characteristics, highlight representative works, and examine their application domains such as robotics, autonomous driving, and interactive gaming. Finally, we discuss open challenges and design principles for next-generation world models, including the role of agent intelligence in shaping and evaluating these systems. An up-to-date list of related works is maintained at this link.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.09611.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ye Tian, Ling Yang, Jiongfan Yang, Anran Wang, Yu Tian, Jiani Zheng, Haochen Wang, Zhiyang Teng, Zhuochen Wang, Yinjie Wang, Yunhai Tong, Mengdi Wang, Xiangtai Li</p><p><b>Upvotes:</b> 43</p><p><b>Summary:</b> While thinking-aware generation aims to improve performance on complex tasks, we identify a critical failure mode where existing sequential, autoregressive approaches can paradoxically degrade performance due to error propagation. To systematically analyze this issue, we propose ParaBench, a new benchmark designed to evaluate both text and image output modalities. Our analysis using ParaBench reveals that this performance degradation is strongly correlated with poor alignment between the generated reasoning and the final image. To resolve this, we propose a parallel multimodal diffusion framework, MMaDA-Parallel, that enables continuous, bidirectional interaction between text and images throughout the entire denoising trajectory. MMaDA-Parallel is trained with supervised finetuning and then further optimized by Parallel Reinforcement Learning (ParaRL), a novel strategy that applies semantic rewards along the trajectory to enforce cross-modal consistency. Experiments validate that our model significantly improves cross-modal alignment and semantic consistency, achieving a 6.9\% improvement in Output Alignment on ParaBench compared to the state-of-the-art model, Bagel, establishing a more robust paradigm for thinking-aware image synthesis. Our code is open-sourced at https://github.com/tyfeld/MMaDA-Parallel</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2511.08585</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2511.09611</guid>
|
||||||
<pubDate>Tue, 11 Nov 2025 18:59:50 +0000</pubDate>
|
<pubDate>Wed, 12 Nov 2025 18:58:21 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>DoPE: Denoising Rotary Position Embedding</title>
|
<title>Test-Time Spectrum-Aware Latent Steering for Zero-Shot Generalization in Vision-Language Models</title>
|
||||||
<link>https://arxiv.org/abs/2511.09146</link>
|
<link>https://arxiv.org/abs/2511.09809</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.09146.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jing Xiong, Liyang Fan, Hui Shen, Zunhai Su, Min Yang, Lingpeng Kong, Ngai Wong</p><p><b>Upvotes:</b> 59</p><p><b>Summary:</b> Rotary Position Embedding (RoPE) in Transformer models has inherent limits that weaken length extrapolation. We reinterpret the attention map with positional encoding as a noisy feature map, and propose Denoising Positional Encoding (DoPE), a training-free method based on truncated matrix entropy to detect outlier frequency bands in the feature map. Leveraging the noise characteristics of the feature map, we further reparameterize it with a parameter-free Gaussian distribution to achieve robust extrapolation. Our method theoretically reveals the underlying cause of the attention sink phenomenon and its connection to truncated matrix entropy. Experiments on needle-in-a-haystack and many-shot in-context learning tasks demonstrate that DoPE significantly improves retrieval accuracy and reasoning stability across extended contexts (up to 64K tokens). The results show that the denoising strategy for positional embeddings effectively mitigates attention sinks and restores balanced attention patterns, providing a simple yet powerful solution for improving length generalization. Our project page is Project: https://The-physical-picture-of-LLMs.github.io</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.09809.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Konstantinos M. Dafnis, Dimitris N. Metaxas</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Vision-Language Models (VLMs) excel at zero-shot inference but often degrade under test-time domain shifts. For this reason, episodic test-time adaptation strategies have recently emerged as powerful techniques for adapting VLMs to a single unlabeled image. However, existing adaptation strategies, such as test-time prompt tuning, typically require backpropagating through large encoder weights or altering core model components. In this work, we introduce Spectrum-Aware Test-Time Steering (STS), a lightweight adaptation framework that extracts a spectral subspace from the textual embeddings to define principal semantic directions and learns to steer latent representations in a spectrum-aware manner by adapting a small number of per-sample shift parameters to minimize entropy across augmented views. STS operates entirely at inference in the latent space, without backpropagation through or modification of the frozen encoders. Building on standard evaluation protocols, our comprehensive experiments demonstrate that STS largely surpasses or compares favorably against state-of-the-art test-time adaptation methods, while introducing only a handful of additional parameters and achieving inference speeds up to 8x faster with a 12x smaller memory footprint than conventional test-time prompt tuning. The code is available at https://github.com/kdafnis/STS.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2511.09146</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2511.09809</guid>
|
||||||
<pubDate>Wed, 12 Nov 2025 09:32:35 +0000</pubDate>
|
<pubDate>Wed, 12 Nov 2025 23:25:58 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>RF-DETR: Neural Architecture Search for Real-Time Detection Transformers</title>
|
<title>Instella: Fully Open Language Models with Stellar Performance</title>
|
||||||
<link>https://arxiv.org/abs/2511.09554</link>
|
<link>https://arxiv.org/abs/2511.10628</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.09554.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Isaac Robinson, Peter Robicheaux, Matvei Popov, Deva Ramanan, Neehar Peri</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Open-vocabulary detectors achieve impressive performance on COCO, but often fail to generalize to real-world datasets with out-of-distribution classes not typically found in their pre-training. Rather than simply fine-tuning a heavy-weight vision-language model (VLM) for new domains, we introduce RF-DETR, a light-weight specialist detection transformer that discovers accuracy-latency Pareto curves for any target dataset with weight-sharing neural architecture search (NAS). Our approach fine-tunes a pre-trained base network on a target dataset and evaluates thousands of network configurations with different accuracy-latency tradeoffs without re-training. Further, we revisit the "tunable knobs" for NAS to improve the transferability of DETRs to diverse target domains. Notably, RF-DETR significantly improves on prior state-of-the-art real-time methods on COCO and Roboflow100-VL. RF-DETR (nano) achieves 48.0 AP on COCO, beating D-FINE (nano) by 5.3 AP at similar latency, and RF-DETR (2x-large) outperforms GroundingDINO (tiny) by 1.2 AP on Roboflow100-VL while running 20x as fast. To the best of our knowledge, RF-DETR (2x-large) is the first real-time detector to surpass 60 AP on COCO. Our code is at https://github.com/roboflow/rf-detr</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.10628.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiang Liu, Jialian Wu, Xiaodong Yu, Yusheng Su, Prakamya Mishra, Gowtham Ramesh, Sudhanshu Ranjan, Chaitanya Manem, Ximeng Sun, Ze Wang, Pratik Prabhanjan Brahma, Zicheng Liu, Emad Barsoum</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Large language models (LLMs) have demonstrated remarkable performance across a wide range of tasks, yet the majority of high-performing models remain closed-source or partially open, limiting transparency and reproducibility. In this work, we introduce Instella, a family of fully open three billion parameter language models trained entirely on openly available data and codebase. Powered by AMD Instinct MI300X GPUs, Instella is developed through large-scale pre-training, general-purpose instruction tuning, and alignment with human preferences. Despite using substantially fewer pre-training tokens than many contemporaries, Instella achieves state-of-the-art results among fully open models and is competitive with leading open-weight models of comparable size. We further release two specialized variants: Instella-Long, capable of handling context lengths up to 128K tokens, and Instella-Math, a reasoning-focused model enhanced through supervised fine-tuning and reinforcement learning on mathematical tasks. Together, these contributions establish Instella as a transparent, performant, and versatile alternative for the community, advancing the goal of open and reproducible language modeling research.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2511.09554</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2511.10628</guid>
|
||||||
<pubDate>Wed, 12 Nov 2025 18:58:39 +0000</pubDate>
|
<pubDate>Thu, 13 Nov 2025 18:52:46 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>HI-TransPA: Hearing Impairments Translation Personal Assistant</title>
|
<title>UFO^3: Weaving the Digital Agent Galaxy</title>
|
||||||
<link>https://arxiv.org/abs/2511.09915</link>
|
<link>https://arxiv.org/abs/2511.11332</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.09915.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhiming Ma, Shiyu Gan, Junhao Zhao, Xianming Li, Qingyun Pan, Peidong Wang, Mingjun Pan, Yuhao Mo, Jiajie Cheng, Chengxin Chen, Zhonglun Cao, Chonghan Liu, Shi Cheng</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> To provide a unified and flexible solution for daily communication among hearing-impaired individuals, we introduce the Omni-Model paradigm into assistive technology and present HI-TransPA, an instruction-driven audio-visual personal assistant. The model fuses indistinct speech with high-frame-rate lip dynamics, enabling both translation and dialogue within a single multimodal framework. To tackle the challenges of noisy and heterogeneous raw data and the limited adaptability of existing Omni-Models to hearing-impaired speech, we construct a comprehensive preprocessing and curation pipeline that detects facial landmarks, isolates and stabilizes the lip region, and quantitatively assesses multimodal sample quality. These quality scores guide a curriculum learning strategy that first trains on clean, high-confidence samples and progressively incorporates harder cases to strengthen model robustness. We further adopt a SigLIP encoder combined with a Unified 3D-Resampler to efficiently encode high-frame-rate lip motion. Experiments on our purpose-built HI-Dialogue dataset show that HI-TransPA achieves state-of-the-art performance in both literal accuracy and semantic fidelity. This work establishes a foundation for applying Omni-Models to assistive communication technology, providing an end-to-end modeling framework and essential processing tools for future research.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.11332.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chaoyun Zhang, Liqun Li, He Huang, Chiming Ni, Bo Qiao, Si Qin, Yu Kang, Minghua Ma, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Large language model (LLM)-powered agents are transforming digital devices from passive tools into proactive intelligent collaborators. However, most existing frameworks remain confined to a single OS or device, making cross-device workflows brittle and largely manual. We present UFO^3, a system that unifies heterogeneous endpoints, desktops, servers, mobile devices, and edge, into a single orchestration fabric. UFO^3 models each user request as a mutable TaskConstellation: a distributed DAG of atomic subtasks (TaskStars) with explicit control and data dependencies (TaskStarLines). The TaskConstellation continuously evolves as results stream in from distributed devices, enabling asynchronous execution, adaptive recovery, and dynamic optimization. A Constellation Orchestrator} executes tasks safely and asynchronously while applying dynamic DAG updates, and the Agent Interaction Protocol (AIP) provides persistent, low-latency channels for reliable task dispatch and result streaming. These designs dissolve the traditional boundaries between devices and platforms, allowing agents to collaborate seamlessly and amplify their collective intelligence. We evaluate UFO^3 on NebulaBench, a benchmark of 55 cross-device tasks across 5 machines and 10 categories. UFO^3 achieves 83.3% subtask completion, 70.9% task success, exposes parallelism with an average width of 1.72, and reduces end-to-end latency by 31% relative to a sequential baseline. Fault-injection experiments demonstrate graceful degradation and recovery under transient and permanent agent failures. These results show that UFO^3 achieves accurate, efficient, and resilient task orchestration across heterogeneous devices, uniting isolated agents into a coherent, adaptive computing fabric that extends across the landscape of ubiquitous computing.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2511.09915</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2511.11332</guid>
|
||||||
<pubDate>Thu, 13 Nov 2025 03:27:39 +0000</pubDate>
|
<pubDate>Fri, 14 Nov 2025 14:05:31 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Workload Schedulers -- Genesis, Algorithms and Differences</title>
|
<title>MicroVQA++: High-Quality Microscopy Reasoning Dataset with Weakly Supervised Graphs for Multimodal Large Language Model</title>
|
||||||
<link>https://arxiv.org/abs/2511.10258</link>
|
<link>https://arxiv.org/abs/2511.11407</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.10258.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Leszek Sliwko, Vladimir Getov</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> This paper presents a novel approach to categorization of modern workload schedulers. We provide descriptions of three classes of schedulers: Operating Systems Process Schedulers, Cluster Systems Jobs Schedulers and Big Data Schedulers. We describe their evolution from early adoptions to modern implementations, considering both the use and features of algorithms. In summary, we discuss differences between all presented classes of schedulers and discuss their chronological development. In conclusion we highlight similarities in the focus of scheduling strategies design, applicable to both local and distributed systems.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.11407.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Manyu Li, Ruian He, Chenxi Ma, Weimin Tan, Bo Yan</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Multimodal Large Language Models are increasingly applied to biomedical imaging, yet scientific reasoning for microscopy remains limited by the scarcity of large-scale, high-quality training data. We introduce MicroVQA++, a three-stage, large-scale and high-quality microscopy VQA corpus derived from the BIOMEDICA archive. Stage one bootstraps supervision from expert-validated figure-caption pairs sourced from peer-reviewed articles. Stage two applies HiCQA-Graph, a novel heterogeneous graph over images, captions, and QAs that fuses NLI-based textual entailment, CLIP-based vision-language alignment, and agent signals to identify and filter inconsistent samples. Stage three uses a MultiModal Large Language Model (MLLM) agent to generate multiple-choice questions (MCQ) followed by human screening. The resulting release comprises a large training split and a human-checked test split whose Bloom's level hard-sample distribution exceeds the MicroVQA benchmark. Our work delivers (i) a quality-controlled dataset that couples expert literature with graph-based filtering and human refinement; (ii) HiCQA-Graph, the first graph that jointly models (image, caption, QA) for cross-modal consistency filtering; (iii) evidence that careful data construction enables 4B-scale MLLMs to reach competitive microscopy reasoning performance (e.g., GPT-5) and achieve state-of-the-art performance among open-source MLLMs. Code and dataset will be released after the review process concludes.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2511.10258</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2511.11407</guid>
|
||||||
<pubDate>Thu, 13 Nov 2025 12:46:01 +0000</pubDate>
|
<pubDate>Fri, 14 Nov 2025 15:35:43 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Don't Waste It: Guiding Generative Recommenders with Structured Human Priors via Multi-head Decoding</title>
|
<title>OpenUS: A Fully Open-Source Foundation Model for Ultrasound Image Analysis via Self-Adaptive Masked Contrastive Learning</title>
|
||||||
<link>https://arxiv.org/abs/2511.10492</link>
|
<link>https://arxiv.org/abs/2511.11510</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.10492.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yunkai Zhang, Qiang Zhang, Feng, Lin, Ruizhong Qiu, Hanchao Yu, Jason Liu, Yinglong Xia, Zhuoran Yu, Zeyu Zheng, Diji Yang</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Optimizing recommender systems for objectives beyond accuracy, such as diversity, novelty, and personalization, is crucial for long-term user satisfaction. To this end, industrial practitioners have accumulated vast amounts of structured domain knowledge, which we term human priors (e.g., item taxonomies, temporal patterns). This knowledge is typically applied through post-hoc adjustments during ranking or post-ranking. However, this approach remains decoupled from the core model learning, which is particularly undesirable as the industry shifts to end-to-end generative recommendation foundation models. On the other hand, many methods targeting these beyond-accuracy objectives often require architecture-specific modifications and discard these valuable human priors by learning user intent in a fully unsupervised manner. Instead of discarding the human priors accumulated over years of practice, we introduce a backbone-agnostic framework that seamlessly integrates these human priors directly into the end-to-end training of generative recommenders. With lightweight, prior-conditioned adapter heads inspired by efficient LLM decoding strategies, our approach guides the model to disentangle user intent along human-understandable axes (e.g., interaction types, long- vs. short-term interests). We also introduce a hierarchical composition strategy for modeling complex interactions across different prior types. Extensive experiments on three large-scale datasets demonstrate that our method significantly enhances both accuracy and beyond-accuracy objectives. We also show that human priors allow the backbone model to more effectively leverage longer context lengths and larger model sizes.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.11510.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiaoyu Zheng, Xu Chen, Awais Rauf, Qifan Fu, Benedetta Monosi, Felice Rivellese, Myles J. Lewis, Shaogang Gong, Gregory Slabaugh</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Ultrasound (US) is one of the most widely used medical imaging modalities, thanks to its low cost, portability, real-time feedback, and absence of ionizing radiation. However, US image interpretation remains highly operator-dependent and varies significantly across anatomical regions, acquisition protocols, and device types. These variations, along with unique challenges such as speckle, low contrast, and limited standardized annotations, hinder the development of generalizable, label-efficient ultrasound AI models. In this paper, we propose OpenUS, the first reproducible, open-source ultrasound foundation model built on a large collection of public data. OpenUS employs a vision Mamba backbone, capturing both local and global long-range dependencies across the image. To extract rich features during pre-training, we introduce a novel self-adaptive masking framework that combines contrastive learning with masked image modeling. This strategy integrates the teacher's attention map with student reconstruction loss, adaptively refining clinically-relevant masking to enhance pre-training effectiveness. OpenUS also applies a dynamic learning schedule to progressively adjust the difficulty of the pre-training process. To develop the foundation model, we compile the largest to-date public ultrasound dataset comprising over 308K images from 42 publicly available datasets, covering diverse anatomical regions, institutions, imaging devices, and disease types. Our pre-trained OpenUS model can be easily adapted to specific downstream tasks by serving as a backbone for label-efficient fine-tuning. Code is available at https://github.com/XZheng0427/OpenUS.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2511.10492</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2511.11510</guid>
|
||||||
<pubDate>Thu, 13 Nov 2025 16:59:22 +0000</pubDate>
|
<pubDate>Fri, 14 Nov 2025 17:31:18 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>DiscoX: Benchmarking Discourse-Level Translation task in Expert Domains</title>
|
<title>MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling</title>
|
||||||
<link>https://arxiv.org/abs/2511.10984</link>
|
<link>https://arxiv.org/abs/2511.11793</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.10984.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiying Zhao, Zhoufutu Wen, Zhixuan Chen, Jingzhe Ding, Jianpeng Jiao, Shuai Li, Xi Li, Danni Liang, Shengda Long, Qianqian Liu, Xianbo Wu, Hongwan Gao, Xiang Gao, Liang Hu, Jiashuo Liu, Mengyun Liu, Weiran Shi, Chenghao Yang, Qianyu Yang, Xuanliang Zhang, Ge Zhang, Wenhao Huang</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> The evaluation of discourse-level translation in expert domains remains inadequate, despite its centrality to knowledge dissemination and cross-lingual scholarly communication. While these translations demand discourse-level coherence and strict terminological precision, current evaluation methods predominantly focus on segment-level accuracy and fluency. To address this limitation, we introduce DiscoX, a new benchmark for discourse-level and expert-level Chinese-English translation. It comprises 200 professionally-curated texts from 7 domains, with an average length exceeding 1700 tokens. To evaluate performance on DiscoX, we also develop Metric-S, a reference-free system that provides fine-grained automatic assessments across accuracy, fluency, and appropriateness. Metric-S demonstrates strong consistency with human judgments, significantly outperforming existing metrics. Our experiments reveal a remarkable performance gap: even the most advanced LLMs still trail human experts on these tasks. This finding validates the difficulty of DiscoX and underscores the challenges that remain in achieving professional-grade machine translation. The proposed benchmark and evaluation system provide a robust framework for more rigorous evaluation, facilitating future advancements in LLM-based translation.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.11793.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> MiroMind Team, Song Bai, Lidong Bing, Carson Chen, Guanzheng Chen, Yuntao Chen, Zhe Chen, Ziyi Chen, Jifeng Dai, Xuan Dong, Yue Deng, Yunjie Fu, Junqi Ge, Chenxia Han, Tammy Huang, Zhenhang Huang, Jerry Jiao, Shilei Jiang, Tianyu Jiao, Xiaoqi Jian, Lei Lei, Ruilin Li, Ryan Luo, Tiantong Li, Xiang Lin, Ziyuan Liu, Zhiqi Li, Jie Ni, Qiang Ren, Pax Sun, Shiqian Su, Chenxin Tao, Bin Wang, Hellen Wang, Haonan Wang, James Wang, Jin Wang, Jojo Wang, Letian Wang, Shizun Wang, Weizhi Wang, Zixuan Wang, Jinfan Xu, Sen Xing, Chenyu Yang, Hai Ye, Jiaheng Yu, Yue Yu, Muyan Zhong, Tianchen Zhao, Xizhou Zhu, Yanpeng Zhou, Yifan Zhang, Zhi Zhu</p><p><b>Upvotes:</b> 79</p><p><b>Summary:</b> We present MiroThinker v1.0, an open-source research agent designed to advance tool-augmented reasoning and information-seeking capabilities. Unlike previous agents that only scale up model size or context length, MiroThinker explores interaction scaling at the model level, systematically training the model to handle deeper and more frequent agent-environment interactions as a third dimension of performance improvement. Unlike LLM test-time scaling, which operates in isolation and risks degradation with longer reasoning chains, interactive scaling leverages environment feedback and external information acquisition to correct errors and refine trajectories. Through reinforcement learning, the model achieves efficient interaction scaling: with a 256K context window, it can perform up to 600 tool calls per task, enabling sustained multi-turn reasoning and complex real-world research workflows. Across four representative benchmarks-GAIA, HLE, BrowseComp, and BrowseComp-ZH-the 72B variant achieves up to 81.9%, 37.7%, 47.1%, and 55.6% accuracy respectively, surpassing previous open-source agents and approaching commercial counterparts such as GPT-5-high. Our analysis reveals that MiroThinker benefits from interactive scaling consistently: research performance improves predictably as the model engages in deeper and more frequent agent-environment interactions, demonstrating that interaction depth exhibits scaling behaviors analogous to model size and context length. These findings establish interaction scaling as a third critical dimension for building next-generation open research agents, complementing model capacity and context windows.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2511.10984</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2511.11793</guid>
|
||||||
<pubDate>Fri, 14 Nov 2025 06:09:37 +0000</pubDate>
|
<pubDate>Fri, 14 Nov 2025 18:52:07 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>EmoVid: A Multimodal Emotion Video Dataset for Emotion-Centric Video Understanding and Generation</title>
|
<title>Assessing LLMs for Serendipity Discovery in Knowledge Graphs: A Case for Drug Repurposing</title>
|
||||||
<link>https://arxiv.org/abs/2511.11002</link>
|
<link>https://arxiv.org/abs/2511.12472</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.11002.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zongyang Qiu, Bingyuan Wang, Xingbei Chen, Yingqing He, Zeyu Wang</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Emotion plays a pivotal role in video-based expression, but existing video generation systems predominantly focus on low-level visual metrics while neglecting affective dimensions. Although emotion analysis has made progress in the visual domain, the video community lacks dedicated resources to bridge emotion understanding with generative tasks, particularly for stylized and non-realistic contexts. To address this gap, we introduce EmoVid, the first multimodal, emotion-annotated video dataset specifically designed for creative media, which includes cartoon animations, movie clips, and animated stickers. Each video is annotated with emotion labels, visual attributes (brightness, colorfulness, hue), and text captions. Through systematic analysis, we uncover spatial and temporal patterns linking visual features to emotional perceptions across diverse video forms. Building on these insights, we develop an emotion-conditioned video generation technique by fine-tuning the Wan2.1 model. The results show a significant improvement in both quantitative metrics and the visual quality of generated videos for text-to-video and image-to-video tasks. EmoVid establishes a new benchmark for affective video computing. Our work not only offers valuable insights into visual emotion analysis in artistically styled videos, but also provides practical methods for enhancing emotional expression in video generation.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.12472.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mengying Wang, Chenhui Ma, Ao Jiao, Tuo Liang, Pengjun Lu, Shrinidhi Hegde, Yu Yin, Evren Gurkan-Cavusoglu, Yinghui Wu</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Large Language Models (LLMs) have greatly advanced knowledge graph question answering (KGQA), yet existing systems are typically optimized for returning highly relevant but predictable answers. A missing yet desired capacity is to exploit LLMs to suggest surprise and novel ("serendipitious") answers. In this paper, we formally define the serendipity-aware KGQA task and propose the SerenQA framework to evaluate LLMs' ability to uncover unexpected insights in scientific KGQA tasks. SerenQA includes a rigorous serendipity metric based on relevance, novelty, and surprise, along with an expert-annotated benchmark derived from the Clinical Knowledge Graph, focused on drug repurposing. Additionally, it features a structured evaluation pipeline encompassing three subtasks: knowledge retrieval, subgraph reasoning, and serendipity exploration. Our experiments reveal that while state-of-the-art LLMs perform well on retrieval, they still struggle to identify genuinely surprising and valuable discoveries, underscoring a significant room for future improvements. Our curated resources and extended version are released at: https://cwru-db-group.github.io/serenQA.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2511.11002</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2511.12472</guid>
|
||||||
<pubDate>Fri, 14 Nov 2025 06:44:21 +0000</pubDate>
|
<pubDate>Sun, 16 Nov 2025 06:19:53 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>LiteAttention: A Temporal Sparse Attention for Diffusion Transformers</title>
|
<title>Uni-MoE-2.0-Omni: Scaling Language-Centric Omnimodal Large Model with Advanced MoE, Training and Data</title>
|
||||||
<link>https://arxiv.org/abs/2511.11062</link>
|
<link>https://arxiv.org/abs/2511.12609</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.11062.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dor Shmilovich, Tony Wu, Aviad Dahan, Yuval Domb</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> Diffusion Transformers, particularly for video generation, achieve remarkable quality but suffer from quadratic attention complexity, leading to prohibitive latency. Existing acceleration methods face a fundamental trade-off: dynamically estimating sparse attention patterns at each denoising step incurs high computational overhead and estimation errors, while static sparsity patterns remain fixed and often suboptimal throughout denoising. We identify a key structural property of diffusion attention, namely, its sparsity patterns exhibit strong temporal coherence across denoising steps. Tiles deemed non-essential at step t typically remain so at step t+δ. Leveraging this observation, we introduce LiteAttention, a method that exploits temporal coherence to enable evolutionary computation skips across the denoising sequence. By marking non-essential tiles early and propagating skip decisions forward, LiteAttention eliminates redundant attention computations without repeated profiling overheads, combining the adaptivity of dynamic methods with the efficiency of static ones. We implement a highly optimized LiteAttention kernel on top of FlashAttention and demonstrate substantial speedups on production video diffusion models, with no degradation in quality. The code and implementation details will be publicly released.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.12609.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yunxin Li, Xinyu Chen, Shenyuan Jiang, Haoyuan Shi, Zhenyu Liu, Xuanyu Zhang, Nanhao Deng, Zhenran Xu, Yicheng Ma, Meishan Zhang, Baotian Hu, Min Zhang</p><p><b>Upvotes:</b> 85</p><p><b>Summary:</b> We present Uni-MoE 2.0 from the Lychee family. As a fully open-source omnimodal large model (OLM), it substantially advances Lychee's Uni-MoE series in language-centric multimodal understanding, reasoning, and generating. Based on the Qwen2.5-7B dense architecture, we build Uni-MoE-2.0-Omni from scratch through three core contributions: dynamic-capacity Mixture-of-Experts (MoE) design, a progressive training strategy enhanced with an iterative reinforcement strategy, and a carefully curated multimodal data matching technique. It is capable of omnimodal understanding, as well as generating images, text, and speech. Architecturally, our new MoE framework balances computational efficiency and capability for 10 cross-modal inputs using shared, routed, and null experts, while our Omni-Modality 3D RoPE ensures spatio-temporal cross-modality alignment in the self-attention layer. For training, following cross-modal pretraining, we use a progressive supervised fine-tuning strategy that activates modality-specific experts and is enhanced by balanced data composition and an iterative GSPO-DPO method to stabilise RL training and improve reasoning. Data-wise, the base model, trained on approximately 75B tokens of open-source multimodal data, is equipped with special speech and image generation tokens, allowing it to learn these generative tasks by conditioning its outputs on linguistic cues. Extensive evaluation across 85 benchmarks demonstrates that our model achieves SOTA or highly competitive performance against leading OLMs, surpassing Qwen2.5-Omni (trained with 1.2T tokens) on over 50 of 76 benchmarks. Key strengths include video understanding (+7% avg. of 8), omnimodallity understanding (+7% avg. of 4), and audiovisual reasoning (+4%). It also advances long-form speech processing (reducing WER by 4.2%) and leads in low-level image processing and controllable generation across 5 metrics.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2511.11062</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2511.12609</guid>
|
||||||
<pubDate>Fri, 14 Nov 2025 08:26:55 +0000</pubDate>
|
<pubDate>Sun, 16 Nov 2025 14:10:55 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>GGBench: A Geometric Generative Reasoning Benchmark for Unified Multimodal Models</title>
|
<title>Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs</title>
|
||||||
<link>https://arxiv.org/abs/2511.11134</link>
|
<link>https://arxiv.org/abs/2511.12710</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.11134.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jingxuan Wei, Caijun Jia, Xi Bai, Xinglong Xu, Siyuan Li, Linzhuang Sun, Bihui Yu, Conghui He, Lijun Wu, Cheng Tan</p><p><b>Upvotes:</b> 29</p><p><b>Summary:</b> The advent of Unified Multimodal Models (UMMs) signals a paradigm shift in artificial intelligence, moving from passive perception to active, cross-modal generation. Despite their unprecedented ability to synthesize information, a critical gap persists in evaluation: existing benchmarks primarily assess discriminative understanding or unconstrained image generation separately, failing to measure the integrated cognitive process of generative reasoning. To bridge this gap, we propose that geometric construction provides an ideal testbed as it inherently demands a fusion of language comprehension and precise visual generation. We introduce GGBench, a benchmark designed specifically to evaluate geometric generative reasoning. It provides a comprehensive framework for systematically diagnosing a model's ability to not only understand and reason but to actively construct a solution, thereby setting a more rigorous standard for the next generation of intelligent systems. Project website: https://opendatalab-raiser.github.io/GGBench/.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.12710.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yunhao Chen, Xin Wang, Juncheng Li, Yixu Wang, Jie Li, Yan Teng, Yingchun Wang, Xingjun Ma</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Automated red teaming frameworks for Large Language Models (LLMs) have become increasingly sophisticated, yet they share a fundamental limitation: their jailbreak logic is confined to selecting, combining, or refining pre-existing attack strategies. This binds their creativity and leaves them unable to autonomously invent entirely new attack mechanisms. To overcome this gap, we introduce EvoSynth, an autonomous framework that shifts the paradigm from attack planning to the evolutionary synthesis of jailbreak methods. Instead of refining prompts, EvoSynth employs a multi-agent system to autonomously engineer, evolve, and execute novel, code-based attack algorithms. Crucially, it features a code-level self-correction loop, allowing it to iteratively rewrite its own attack logic in response to failure. Through extensive experiments, we demonstrate that EvoSynth not only establishes a new state-of-the-art by achieving an 85.5\% Attack Success Rate (ASR) against highly robust models like Claude-Sonnet-4.5, but also generates attacks that are significantly more diverse than those from existing methods. We release our framework to facilitate future research in this new direction of evolutionary synthesis of jailbreak methods. Code is available at: https://github.com/dongdongunique/EvoSynth.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2511.11134</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2511.12710</guid>
|
||||||
<pubDate>Fri, 14 Nov 2025 10:07:53 +0000</pubDate>
|
<pubDate>Sun, 16 Nov 2025 17:52:07 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>CATS-V2V: A Real-World Vehicle-to-Vehicle Cooperative Perception Dataset with Complex Adverse Traffic Scenarios</title>
|
<title>Genomic Next-Token Predictors are In-Context Learners</title>
|
||||||
<link>https://arxiv.org/abs/2511.11168</link>
|
<link>https://arxiv.org/abs/2511.12797</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.11168.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hangyu Li, Bofeng Cao, Zhaohui Liang, Wuzhen Li, Juyoung Oh, Yuxuan Chen, Shixiao Liang, Hang Zhou, Chengyuan Ma, Jiaxi Liu, Zheng Li, Peng Zhang, KeKe Long, Maolin Liu, Jackson Jiang, Chunlei Yu, Shengxiang Liu, Hongkai Yu, Xiaopeng Li</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Vehicle-to-Vehicle (V2V) cooperative perception has great potential to enhance autonomous driving performance by overcoming perception limitations in complex adverse traffic scenarios (CATS). Meanwhile, data serves as the fundamental infrastructure for modern autonomous driving AI. However, due to stringent data collection requirements, existing datasets focus primarily on ordinary traffic scenarios, constraining the benefits of cooperative perception. To address this challenge, we introduce CATS-V2V, the first-of-its-kind real-world dataset for V2V cooperative perception under complex adverse traffic scenarios. The dataset was collected by two hardware time-synchronized vehicles, covering 10 weather and lighting conditions across 10 diverse locations. The 100-clip dataset includes 60K frames of 10 Hz LiDAR point clouds and 1.26M multi-view 30 Hz camera images, along with 750K anonymized yet high-precision RTK-fixed GNSS and IMU records. Correspondingly, we provide time-consistent 3D bounding box annotations for objects, as well as static scenes to construct a 4D BEV representation. On this basis, we propose a target-based temporal alignment method, ensuring that all objects are precisely aligned across all sensor modalities. We hope that CATS-V2V, the largest-scale, most supportive, and highest-quality dataset of its kind to date, will benefit the autonomous driving community in related tasks.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.12797.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Nathan Breslow, Aayush Mishra, Mahler Revsine, Michael C. Schatz, Anqi Liu, Daniel Khashabi</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> In-context learning (ICL) -- the capacity of a model to infer and apply abstract patterns from examples provided within its input -- has been extensively studied in large language models trained for next-token prediction on human text. In fact, prior work often attributes this emergent behavior to distinctive statistical properties in human language. This raises a fundamental question: can ICL arise organically in other sequence domains purely through large-scale predictive training? To explore this, we turn to genomic sequences, an alternative symbolic domain rich in statistical structure. Specifically, we study the Evo2 genomic model, trained predominantly on next-nucleotide (A/T/C/G) prediction, at a scale comparable to mid-sized LLMs. We develop a controlled experimental framework comprising symbolic reasoning tasks instantiated in both linguistic and genomic forms, enabling direct comparison of ICL across genomic and linguistic models. Our results show that genomic models, like their linguistic counterparts, exhibit log-linear gains in pattern induction as the number of in-context demonstrations increases. To the best of our knowledge, this is the first evidence of organically emergent ICL in genomic sequences, supporting the hypothesis that ICL arises as a consequence of large-scale predictive modeling over rich data. These findings extend emergent meta-learning beyond language, pointing toward a unified, modality-agnostic view of in-context learning.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2511.11168</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2511.12797</guid>
|
||||||
<pubDate>Fri, 14 Nov 2025 11:07:04 +0000</pubDate>
|
<pubDate>Sun, 16 Nov 2025 21:56:39 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Virtual Width Networks</title>
|
<title>WebCoach: Self-Evolving Web Agents with Cross-Session Memory Guidance</title>
|
||||||
<link>https://arxiv.org/abs/2511.11238</link>
|
<link>https://arxiv.org/abs/2511.12997</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.11238.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Seed, Baisheng Li, Banggu Wu, Bole Ma, Bowen Xiao, Chaoyi Zhang, Cheng Li, Chengyi Wang, Chenyin Xu, Chi Zhang, Chong Hu, Daoguang Zan, Defa Zhu, Dongyu Xu, Du Li, Faming Wu, Fan Xia, Ge Zhang, Guang Shi, Haobin Chen, Hongyu Zhu, Hongzhi Huang, Huan Zhou, Huanzhang Dou, Jianhui Duan, Jianqiao Lu, Jianyu Jiang, Jiayi Xu, Jiecao Chen, Jin Chen, Jin Ma, Jing Su, Jingji Chen, Jun Wang, Jun Yuan, Juncai Liu, Jundong Zhou, Kai Hua, Kai Shen, Kai Xiang, Kaiyuan Chen, Kang Liu, Ke Shen, Liang Xiang, Lin Yan, Lishu Luo, Mengyao Zhang, Ming Ding, Mofan Zhang, Nianning Liang, Peng Li, Penghao Huang, Pengpeng Mu, Qi Huang, Qianli Ma, Qiyang Min, Qiying Yu, Renming Pang, Ru Zhang, Shen Yan, Shen Yan, Shixiong Zhao, Shuaishuai Cao, Shuang Wu, Siyan Chen, Siyu Li, Siyuan Qiao, Tao Sun, Tian Xin, Tiantian Fan, Ting Huang, Ting-Han Fan, Wei Jia, Wenqiang Zhang, Wenxuan Liu, Xiangzhong Wu, Xiaochen Zuo, Xiaoying Jia, Ximing Yang, Xin Liu, Xin Yu, Xingyan Bin, Xintong Hao, Xiongcai Luo, Xujing Li, Xun Zhou, Yanghua Peng, Yangrui Chen, Yi Lin, Yichong Leng, Yinghao Li, Yingshuan Song, Yiyuan Ma, Yong Shan, Yongan Xiang, Yonghui Wu, Yongtao Zhang, Yongzhen Yao, Yu Bao, Yuehang Yang, Yufeng Yuan, Yunshui Li, Yuqiao Xian, Yutao Zeng, Yuxuan Wang, Zehua Hong, Zehua Wang, Zengzhi Wang, Zeyu Yang, Zhengqiang Yin, Zhenyi Lu, Zhexi Zhang, Zhi Chen, Zhi Zhang, Zhiqi Lin, Zihao Huang, Zilin Xu, Ziyun Wei, Zuo Wang</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> We introduce Virtual Width Networks (VWN), a framework that delivers the benefits of wider representations without incurring the quadratic cost of increasing the hidden size. VWN decouples representational width from backbone width, expanding the embedding space while keeping backbone compute nearly constant. In our large-scale experiment, an 8-times expansion accelerates optimization by over 2 times for next-token and 3 times for next-2-token prediction. The advantage amplifies over training as both the loss gap grows and the convergence-speedup ratio increases, showing that VWN is not only token-efficient but also increasingly effective with scale. Moreover, we identify an approximately log-linear scaling relation between virtual width and loss reduction, offering an initial empirical basis and motivation for exploring virtual-width scaling as a new dimension of large-model efficiency.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.12997.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Genglin Liu, Shijie Geng, Sha Li, Hejie Cui, Sarah Zhang, Xin Liu, Tianyi Liu</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Multimodal LLM-powered agents have recently demonstrated impressive capabilities in web navigation, enabling agents to complete complex browsing tasks across diverse domains. However, current agents struggle with repetitive errors and lack the ability to learn from past experiences across sessions, limiting their long-term robustness and sample efficiency. We introduce WebCoach, a model-agnostic self-evolving framework that equips web browsing agents with persistent cross-session memory, enabling improved long-term planning, reflection, and continual learning without retraining. WebCoach consists of three key components: (1) a WebCondenser, which standardizes raw navigation logs into concise summaries; (2) an External Memory Store, which organizes complete trajectories as episodic experiences; and (3) a Coach, which retrieves relevant experiences based on similarity and recency, and decides whether to inject task-specific advice into the agent via runtime hooks. This design empowers web agents to access long-term memory beyond their native context window, improving robustness in complex browsing tasks. Moreover, WebCoach achieves self-evolution by continuously curating episodic memory from new navigation trajectories, enabling agents to improve over time without retraining. Evaluations on the WebVoyager benchmark demonstrate that WebCoach consistently improves the performance of browser-use agents across three different LLM backbones. With a 38B model, it increases task success rates from 47% to 61% while reducing or maintaining the average number of steps. Notably, smaller base models with WebCoach achieve performance comparable to the same web agent using GPT-4o.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2511.11238</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2511.12997</guid>
|
||||||
<pubDate>Fri, 14 Nov 2025 12:41:57 +0000</pubDate>
|
<pubDate>Mon, 17 Nov 2025 05:38:50 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>AIonopedia: an LLM agent orchestrating multimodal learning for ionic liquid discovery</title>
|
<title>Souper-Model: How Simple Arithmetic Unlocks State-of-the-Art LLM Performance</title>
|
||||||
<link>https://arxiv.org/abs/2511.11257</link>
|
<link>https://arxiv.org/abs/2511.13254</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.11257.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuqi Yin, Yibo Fu, Siyuan Wang, Peng Sun, Hongyu Wang, Xiaohui Wang, Lei Zheng, Zhiyong Li, Zhirong Liu, Jianji Wang, Zhaoxi Sun</p><p><b>Upvotes:</b> 24</p><p><b>Summary:</b> The discovery of novel Ionic Liquids (ILs) is hindered by critical challenges in property prediction, including limited data, poor model accuracy, and fragmented workflows. Leveraging the power of Large Language Models (LLMs), we introduce AIonopedia, to the best of our knowledge, the first LLM agent for IL discovery. Powered by an LLM-augmented multimodal domain foundation model for ILs, AIonopedia enables accurate property predictions and incorporates a hierarchical search architecture for molecular screening and design. Trained and evaluated on a newly curated and comprehensive IL dataset, our model delivers superior performance. Complementing these results, evaluations on literature-reported systems indicate that the agent can perform effective IL modification. Moving beyond offline tests, the practical efficacy was further confirmed through real-world wet-lab validation, in which the agent demonstrated exceptional generalization capabilities on challenging out-of-distribution tasks, underscoring its ability to accelerate real-world IL discovery.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.13254.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shalini Maiti, Amar Budhiraja, Bhavul Gauri, Gaurav Chaurasia, Anton Protopopov, Alexis Audran-Reiss, Michael Slater, Despoina Magka, Tatiana Shavrina, Roberta Raileanu, Yoram Bachrach</p><p><b>Upvotes:</b> 75</p><p><b>Summary:</b> Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse domains, but their training remains resource- and time-intensive, requiring massive compute power and careful orchestration of training procedures. Model souping-the practice of averaging weights from multiple models of the same architecture-has emerged as a promising pre- and post-training technique that can enhance performance without expensive retraining. In this paper, we introduce Soup Of Category Experts (SoCE), a principled approach for model souping that utilizes benchmark composition to identify optimal model candidates and applies non-uniform weighted averaging to maximize performance. Contrary to previous uniform-averaging approaches, our method leverages the observation that benchmark categories often exhibit low inter-correlations in model performance. SoCE identifies "expert" models for each weakly-correlated category cluster and combines them using optimized weighted averaging rather than uniform weights. We demonstrate that the proposed method improves performance and robustness across multiple domains, including multilingual capabilities, tool calling, and math and achieves state-of-the-art results on the Berkeley Function Calling Leaderboard.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2511.11257</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2511.13254</guid>
|
||||||
<pubDate>Fri, 14 Nov 2025 12:53:57 +0000</pubDate>
|
<pubDate>Mon, 17 Nov 2025 11:13:34 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Building the Web for Agents: A Declarative Framework for Agent-Web Interaction</title>
|
<title>P1: Mastering Physics Olympiads with Reinforcement Learning</title>
|
||||||
<link>https://arxiv.org/abs/2511.11287</link>
|
<link>https://arxiv.org/abs/2511.13612</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.11287.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sven Schultze, Meike Verena Kietzmann, Nils-Lucas Schönfeld, Ruth Stock-Homburg</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> The increasing deployment of autonomous AI agents on the web is hampered by a fundamental misalignment: agents must infer affordances from human-oriented user interfaces, leading to brittle, inefficient, and insecure interactions. To address this, we introduce VOIX, a web-native framework that enables websites to expose reliable, auditable, and privacy-preserving capabilities for AI agents through simple, declarative HTML elements. VOIX introduces <tool> and <context> tags, allowing developers to explicitly define available actions and relevant state, thereby creating a clear, machine-readable contract for agent behavior. This approach shifts control to the website developer while preserving user privacy by disconnecting the conversational interactions from the website. We evaluated the framework's practicality, learnability, and expressiveness in a three-day hackathon study with 16 developers. The results demonstrate that participants, regardless of prior experience, were able to rapidly build diverse and functional agent-enabled web applications. Ultimately, this work provides a foundational mechanism for realizing the Agentic Web, enabling a future of seamless and secure human-AI collaboration on the web.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.13612.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiacheng Chen, Qianjia Cheng, Fangchen Yu, Haiyuan Wan, Yuchen Zhang, Shenghe Zheng, Junchi Yao, Qingyang Zhang, Haonan He, Yun Luo, Yufeng Zhao, Futing Wang, Li Sheng, Chengxing Xie, Yuxin Zuo, Yizhuo Li, Wenxauan Zeng, Yulun Wu, Rui Huang, Dongzhan Zhou, Kai Chen, Yu Qiao, Lei Bai, Yu Cheng, Ning Ding, Bowen Zhou, Peng Ye, Ganqu Cui</p><p><b>Upvotes:</b> 106</p><p><b>Summary:</b> Recent progress in large language models (LLMs) has moved the frontier from puzzle-solving to science-grade reasoning-the kind needed to tackle problems whose answers must stand against nature, not merely fit a rubric. Physics is the sharpest test of this shift, which binds symbols to reality in a fundamental way, serving as the cornerstone of most modern technologies. In this work, we manage to advance physics research by developing large language models with exceptional physics reasoning capabilities, especially excel at solving Olympiad-level physics problems. We introduce P1, a family of open-source physics reasoning models trained entirely through reinforcement learning (RL). Among them, P1-235B-A22B is the first open-source model with Gold-medal performance at the latest International Physics Olympiad (IPhO 2025), and wins 12 gold medals out of 13 international/regional physics competitions in 2024/2025. P1-30B-A3B also surpasses almost all other open-source models on IPhO 2025, getting a silver medal. Further equipped with an agentic framework PhysicsMinions, P1-235B-A22B+PhysicsMinions achieves overall No.1 on IPhO 2025, and obtains the highest average score over the 13 physics competitions. Besides physics, P1 models also present great performance on other reasoning tasks like math and coding, showing the great generalibility of P1 series.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2511.11287</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2511.13612</guid>
|
||||||
<pubDate>Fri, 14 Nov 2025 13:23:34 +0000</pubDate>
|
<pubDate>Mon, 17 Nov 2025 17:18:13 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>MarsRL: Advancing Multi-Agent Reasoning System via Reinforcement Learning with Agentic Pipeline Parallelism</title>
|
<title>Live-SWE-agent: Can Software Engineering Agents Self-Evolve on the Fly?</title>
|
||||||
<link>https://arxiv.org/abs/2511.11373</link>
|
<link>https://arxiv.org/abs/2511.13646</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.11373.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shulin Liu, Dong Du, Tao Yang, Yang Li, Boyu Qiu</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Recent progress in large language models (LLMs) has been propelled by reinforcement learning with verifiable rewards (RLVR) and test-time scaling. However, the limited output length of LLMs constrains the depth of reasoning attainable in a single inference process. Multi-agent reasoning systems offer a promising alternative by employing multiple agents including Solver, Verifier, and Corrector, to iteratively refine solutions. While effective in closed-source models like Gemini 2.5 Pro, they struggle to generalize to open-source models due to insufficient critic and correction capabilities. To address this, we propose MarsRL, a novel reinforcement learning framework with agentic pipeline parallelism, designed to jointly optimize all agents in the system. MarsRL introduces agent-specific reward mechanisms to mitigate reward noise and employs pipeline-inspired training to enhance efficiency in handling long trajectories. Applied to Qwen3-30B-A3B-Thinking-2507, MarsRL improves AIME2025 accuracy from 86.5% to 93.3% and BeyondAIME from 64.9% to 73.8%, even surpassing Qwen3-235B-A22B-Thinking-2507. These findings highlight the potential of MarsRL to advance multi-agent reasoning systems and broaden their applicability across diverse reasoning tasks.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.13646.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chunqiu Steven Xia, Zhe Wang, Yan Yang, Yuxiang Wei, Lingming Zhang</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Large Language Models (LLMs) are reshaping almost all industries, including software engineering. In recent years, a number of LLM agents have been proposed to solve real-world software problems. Such software agents are typically equipped with a suite of coding tools and can autonomously decide the next actions to form complete trajectories to solve end-to-end software tasks. While promising, they typically require dedicated design and may still be suboptimal, since it can be extremely challenging and costly to exhaust the entire agent scaffold design space. Recognizing that software agents are inherently software themselves that can be further refined/modified, researchers have proposed a number of self-improving software agents recently, including the Darwin-Gödel Machine (DGM). Meanwhile, such self-improving agents require costly offline training on specific benchmarks and may not generalize well across different LLMs or benchmarks. In this paper, we propose Live-SWE-agent, the first live software agent that can autonomously and continuously evolve itself on-the-fly during runtime when solving real-world software problems. More specifically, Live-SWE-agent starts with the most basic agent scaffold with only access to bash tools (e.g., mini-SWE-agent), and autonomously evolves its own scaffold implementation while solving real-world software problems. Our evaluation on the widely studied SWE-bench Verified benchmark shows that Live-SWE-agent can achieve an impressive solve rate of 75.4% without test-time scaling, outperforming all existing open-source software agents and approaching the performance of the best proprietary solution. Moreover, Live-SWE-agent outperforms state-of-the-art manually crafted software agents on the recent SWE-Bench Pro benchmark, achieving the best-known solve rate of 45.8%.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2511.11373</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2511.13646</guid>
|
||||||
<pubDate>Fri, 14 Nov 2025 14:52:34 +0000</pubDate>
|
<pubDate>Mon, 17 Nov 2025 17:58:18 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>WEAVE: Unleashing and Benchmarking the In-context Interleaved Comprehension and Generation</title>
|
<title>Part-X-MLLM: Part-aware 3D Multimodal Large Language Model</title>
|
||||||
<link>https://arxiv.org/abs/2511.11434</link>
|
<link>https://arxiv.org/abs/2511.13647</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.11434.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wei Chow, Jiachun Pan, Yongyuan Liang, Mingze Zhou, Xue Song, Liyu Jia, Saining Zhang, Siliang Tang, Juncheng Li, Fengda Zhang, Weijia Wu, Hanwang Zhang, Tat-Seng Chua</p><p><b>Upvotes:</b> 40</p><p><b>Summary:</b> Recent advances in unified multimodal models (UMMs) have enabled impressive progress in visual comprehension and generation. However, existing datasets and benchmarks focus primarily on single-turn interactions, failing to capture the multi-turn, context-dependent nature of real-world image creation and editing. To address this gap, we present WEAVE, the first suite for in-context interleaved cross-modality comprehension and generation. Our suite consists of two complementary parts. WEAVE-100k is a large-scale dataset of 100K interleaved samples spanning over 370K dialogue turns and 500K images, covering comprehension, editing, and generation tasks that require reasoning over historical context. WEAVEBench is a human-annotated benchmark with 100 tasks based on 480 images, featuring a hybrid VLM judger evaluation framework based on both the reference image and the combination of the original image with editing instructions that assesses models' abilities in multi-turn generation, visual memory, and world-knowledge reasoning across diverse domains. Experiments demonstrate that training on WEAVE-100k enables vision comprehension, image editing, and comprehension-generation collaboration capabilities. Furthermore, it facilitates UMMs to develop emergent visual-memory capabilities, while extensive evaluations on WEAVEBench expose the persistent limitations and challenges of current approaches in multi-turn, context-aware image generation and editing. We believe WEAVE provides a view and foundation for studying in-context interleaved comprehension and generation for multi-modal community.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.13647.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chunshi Wang, Junliang Ye, Yunhan Yang, Yang Li, Zizhuo Lin, Jun Zhu, Zhuo Chen, Yawei Luo, Chunchao Guo</p><p><b>Upvotes:</b> 62</p><p><b>Summary:</b> We introduce Part-X-MLLM, a native 3D multimodal large language model that unifies diverse 3D tasks by formulating them as programs in a structured, executable grammar. Given an RGB point cloud and a natural language prompt, our model autoregressively generates a single, coherent token sequence encoding part-level bounding boxes, semantic descriptions, and edit commands. This structured output serves as a versatile interface to drive downstream geometry-aware modules for part-based generation and editing. By decoupling the symbolic planning from the geometric synthesis, our approach allows any compatible geometry engine to be controlled through a single, language-native frontend. We pre-train a dual-encoder architecture to disentangle structure from semantics and instruction-tune the model on a large-scale, part-centric dataset. Experiments demonstrate that our model excels at producing high-quality, structured plans, enabling state-of-the-art performance in grounded Q\&A, compositional generation, and localized editing through one unified interface. Project page: https://chunshi.wang/Part-X-MLLM/</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2511.11434</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2511.13647</guid>
|
||||||
<pubDate>Fri, 14 Nov 2025 16:02:38 +0000</pubDate>
|
<pubDate>Mon, 17 Nov 2025 17:59:52 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Experience-Guided Adaptation of Inference-Time Reasoning Strategies</title>
|
<title>PhysX-Anything: Simulation-Ready Physical 3D Assets from Single Image</title>
|
||||||
<link>https://arxiv.org/abs/2511.11519</link>
|
<link>https://arxiv.org/abs/2511.13648</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.11519.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Adam Stein, Matthew Trager, Benjamin Bowman, Michael Kleinman, Aditya Chattopadhyay, Wei Xia, Stefano Soatto</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Enabling agentic AI systems to adapt their problem-solving approaches based on post-training interactions remains a fundamental challenge. While systems that update and maintain a memory at inference time have been proposed, existing designs only steer the system by modifying textual input to a language model or agent, which means that they cannot change sampling parameters, remove tools, modify system prompts, or switch between agentic and workflow paradigms. On the other hand, systems that adapt more flexibly require offline optimization and remain static once deployed. We present Experience-Guided Reasoner (EGuR), which generates tailored strategies -- complete computational procedures involving LLM calls, tools, sampling parameters, and control logic -- dynamically at inference time based on accumulated experience. We achieve this using an LLM-based meta-strategy -- a strategy that outputs strategies -- enabling adaptation of all strategy components (prompts, sampling parameters, tool configurations, and control logic). EGuR operates through two components: a Guide generates multiple candidate strategies conditioned on the current problem and structured memory of past experiences, while a Consolidator integrates execution feedback to improve future strategy generation. This produces complete, ready-to-run strategies optimized for each problem, which can be cached, retrieved, and executed as needed without wasting resources. Across five challenging benchmarks (AIME 2025, 3-SAT, and three Big Bench Extra Hard tasks), EGuR achieves up to 14% accuracy improvements over the strongest baselines while reducing computational costs by up to 111x, with both metrics improving as the system gains experience.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.13648.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ziang Cao, Fangzhou Hong, Zhaoxi Chen, Liang Pan, Ziwei Liu</p><p><b>Upvotes:</b> 29</p><p><b>Summary:</b> 3D modeling is shifting from static visual representations toward physical, articulated assets that can be directly used in simulation and interaction. However, most existing 3D generation methods overlook key physical and articulation properties, thereby limiting their utility in embodied AI. To bridge this gap, we introduce PhysX-Anything, the first simulation-ready physical 3D generative framework that, given a single in-the-wild image, produces high-quality sim-ready 3D assets with explicit geometry, articulation, and physical attributes. Specifically, we propose the first VLM-based physical 3D generative model, along with a new 3D representation that efficiently tokenizes geometry. It reduces the number of tokens by 193x, enabling explicit geometry learning within standard VLM token budgets without introducing any special tokens during fine-tuning and significantly improving generative quality. In addition, to overcome the limited diversity of existing physical 3D datasets, we construct a new dataset, PhysX-Mobility, which expands the object categories in prior physical 3D datasets by over 2x and includes more than 2K common real-world objects with rich physical annotations. Extensive experiments on PhysX-Mobility and in-the-wild images demonstrate that PhysX-Anything delivers strong generative performance and robust generalization. Furthermore, simulation-based experiments in a MuJoCo-style environment validate that our sim-ready assets can be directly used for contact-rich robotic policy learning. We believe PhysX-Anything can substantially empower a broad range of downstream applications, especially in embodied AI and physics-based simulation.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2511.11519</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2511.13648</guid>
|
||||||
<pubDate>Fri, 14 Nov 2025 17:45:28 +0000</pubDate>
|
<pubDate>Mon, 17 Nov 2025 17:59:53 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>OlmoEarth: Stable Latent Image Modeling for Multimodal Earth Observation</title>
|
||||||
|
<link>https://arxiv.org/abs/2511.13655</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.13655.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Henry Herzog, Favyen Bastani, Yawen Zhang, Gabriel Tseng, Joseph Redmon, Hadrien Sablon, Ryan Park, Jacob Morrison, Alexandra Buraczynski, Karen Farley, Joshua Hansen, Andrew Howe, Patrick Alan Johnson, Mark Otterlee, Ted Schmitt, Hunter Pitelka, Stephen Daspit, Rachel Ratner, Christopher Wilhelm, Sebastian Wood, Mike Jacobi, Hannah Kerner, Evan Shelhamer, Ali Farhadi, Ranjay Krishna, Patrick Beukema</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Earth observation data presents a unique challenge: it is spatial like images, sequential like video or text, and highly multimodal. We present OlmoEarth: a multimodal, spatio-temporal foundation model that employs a novel self-supervised learning formulation, masking strategy, and loss all designed for the Earth observation domain. OlmoEarth achieves state-of-the-art performance compared to 12 other foundation models across a variety of research benchmarks and real-world tasks from external partners. When evaluating embeddings OlmoEarth achieves the best performance on 15 out of 24 tasks, and with full fine-tuning it is the best on 19 of 29 tasks. We deploy OlmoEarth as the backbone of an end-to-end platform for data collection, labeling, training, and inference of Earth observation models. The OlmoEarth Platform puts frontier foundation models and powerful data management tools into the hands of non-profits and NGOs working to solve the world's biggest problems. OlmoEarth source code, training data, and pre-trained weights are available at https://github.com/allenai/olmoearth_pretrain{https://github.com/allenai/olmoearth_pretrain}.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2511.13655</guid>
|
||||||
|
<pubDate>Mon, 17 Nov 2025 18:06:26 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>TiViBench: Benchmarking Think-in-Video Reasoning for Video Generative Models</title>
|
||||||
|
<link>https://arxiv.org/abs/2511.13704</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.13704.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Harold Haodong Chen, Disen Lan, Wen-Jie Shu, Qingyang Liu, Zihan Wang, Sirui Chen, Wenkai Cheng, Kanghao Chen, Hongfei Zhang, Zixin Zhang, Rongjin Guo, Yu Cheng, Ying-Cong Chen</p><p><b>Upvotes:</b> 39</p><p><b>Summary:</b> The rapid evolution of video generative models has shifted their focus from producing visually plausible outputs to tackling tasks requiring physical plausibility and logical consistency. However, despite recent breakthroughs such as Veo 3's chain-of-frames reasoning, it remains unclear whether these models can exhibit reasoning capabilities similar to large language models (LLMs). Existing benchmarks predominantly evaluate visual fidelity and temporal coherence, failing to capture higher-order reasoning abilities. To bridge this gap, we propose TiViBench, a hierarchical benchmark specifically designed to evaluate the reasoning capabilities of image-to-video (I2V) generation models. TiViBench systematically assesses reasoning across four dimensions: i) Structural Reasoning & Search, ii) Spatial & Visual Pattern Reasoning, iii) Symbolic & Logical Reasoning, and iv) Action Planning & Task Execution, spanning 24 diverse task scenarios across 3 difficulty levels. Through extensive evaluations, we show that commercial models (e.g., Sora 2, Veo 3.1) demonstrate stronger reasoning potential, while open-source models reveal untapped potential that remains hindered by limited training scale and data diversity. To further unlock this potential, we introduce VideoTPO, a simple yet effective test-time strategy inspired by preference optimization. By performing LLM self-analysis on generated candidates to identify strengths and weaknesses, VideoTPO significantly enhances reasoning performance without requiring additional training, data, or reward models. Together, TiViBench and VideoTPO pave the way for evaluating and advancing reasoning in video generation models, setting a foundation for future research in this emerging field.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2511.13704</guid>
|
||||||
|
<pubDate>Mon, 17 Nov 2025 18:52:44 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>UnSAMv2: Self-Supervised Learning Enables Segment Anything at Any Granularity</title>
|
||||||
|
<link>https://arxiv.org/abs/2511.13714</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.13714.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junwei Yu, Trevor Darrell, XuDong Wang</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> The Segment Anything Model (SAM) family has become a widely adopted vision foundation model, but its ability to control segmentation granularity remains limited. Users often need to refine results manually - by adding more prompts or selecting from pre-generated masks - to achieve the desired level of detail. This process can be ambiguous, as the same prompt may correspond to several plausible masks, and collecting dense annotations across all granularities is prohibitively expensive, making supervised solutions infeasible. To address this limitation, we introduce UnSAMv2, which enables segment anything at any granularity without human annotations. UnSAMv2 extends the divide-and-conquer strategy of UnSAM by discovering abundant mask-granularity pairs and introducing a novel granularity control embedding that enables precise, continuous control over segmentation scale. Remarkably, with only 6K unlabeled images and 0.02% additional parameters, UnSAMv2 substantially enhances SAM-2, achieving segment anything at any granularity across interactive, whole-image, and video segmentation tasks. Evaluated on over 11 benchmarks, UnSAMv2 improves NoC_{90} (5.69 rightarrow 4.75), 1-IoU (58.0 rightarrow 73.1), and AR_{1000} (49.6 rightarrow 68.3), showing that small amounts of unlabeled data with a granularity-aware self-supervised learning method can unlock the potential of vision foundation models.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2511.13714</guid>
|
||||||
|
<pubDate>Mon, 17 Nov 2025 18:58:34 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Back to Basics: Let Denoising Generative Models Denoise</title>
|
||||||
|
<link>https://arxiv.org/abs/2511.13720</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.13720.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tianhong Li, Kaiming He</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Today's denoising diffusion models do not "denoise" in the classical sense, i.e., they do not directly predict clean images. Rather, the neural networks predict noise or a noised quantity. In this paper, we suggest that predicting clean data and predicting noised quantities are fundamentally different. According to the manifold assumption, natural data should lie on a low-dimensional manifold, whereas noised quantities do not. With this assumption, we advocate for models that directly predict clean data, which allows apparently under-capacity networks to operate effectively in very high-dimensional spaces. We show that simple, large-patch Transformers on pixels can be strong generative models: using no tokenizer, no pre-training, and no extra loss. Our approach is conceptually nothing more than "Just image Transformers", or JiT, as we call it. We report competitive results using JiT with large patch sizes of 16 and 32 on ImageNet at resolutions of 256 and 512, where predicting high-dimensional noised quantities can fail catastrophically. With our networks mapping back to the basics of the manifold, our research goes back to basics and pursues a self-contained paradigm for Transformer-based diffusion on raw natural data.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2511.13720</guid>
|
||||||
|
<pubDate>Mon, 17 Nov 2025 18:59:57 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
</channel>
|
</channel>
|
||||||
</rss>
|
</rss>
|
||||||
|
|||||||
Reference in New Issue
Block a user