diff --git a/feed_weekly.xml b/feed_weekly.xml index 2c58c71..6637531 100644 --- a/feed_weekly.xml +++ b/feed_weekly.xml @@ -7,741 +7,741 @@ http://www.rssboard.org/rss-specification python-feedgen en - Mon, 02 Mar 2026 00:15:47 +0000 + Mon, 09 Mar 2026 00:15:39 +0000 - Does Your Reasoning Model Implicitly Know When to Stop Thinking? - https://arxiv.org/abs/2602.08354 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.08354.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zixuan Huang, Xin Xia, Yuxi Ren, Jianbin Zheng, Xuanda Wang, Zhixia Zhang, Hongyan Xie, Songshi Liang, Zehao Chen, Xuefeng Xiao, Fuzhen Zhuang, Jianxin Li, Yikun Ban, Deqing Wang</p><p><b>Upvotes:</b> 248</p><p><b>Summary:</b> Recent advancements in large reasoning models (LRMs) have greatly improved their capabilities on complex reasoning tasks through Long Chains of Thought (CoTs). However, this approach often results in substantial redundancy, impairing computational efficiency and causing significant delays in real-time applications. Recent studies show that longer reasoning chains are frequently uncorrelated with correctness and can even be detrimental to accuracy. In a further in-depth analysis of this phenomenon, we surprisingly uncover and empirically verify that LRMs implicitly know the appropriate time to stop thinking, while this capability is obscured by current sampling paradigms. Motivated by this, we introduce SAGE (Self-Aware Guided Efficient Reasoning), a novel sampling paradigm that unleashes this efficient reasoning potential. Furthermore, integrating SAGE as mixed sampling into group-based reinforcement learning (SAGE-RL) enables SAGE-RL to effectively incorporate SAGE-discovered efficient reasoning patterns into standard pass@1 inference, markedly enhancing both the reasoning accuracy and efficiency of LRMs across multiple challenging mathematical benchmarks.</p> - https://arxiv.org/abs/2602.08354 - Mon, 09 Feb 2026 07:38:22 +0000 + Spilled Energy in Large Language Models + https://arxiv.org/abs/2602.18671 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.18671.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Adrian Robert Minut, Hazem Dewidar, Iacopo Masi</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> We reinterpret the final Large Language Model (LLM) softmax classifier as an Energy-Based Model (EBM), decomposing the sequence-to-sequence probability chain into multiple interacting EBMs at inference. This principled approach allows us to track "energy spills" during decoding, which we empirically show correlate with factual errors, biases, and failures. Similar to Orgad et al. (2025), our method localizes the exact answer token and subsequently tests for hallucinations. Crucially, however, we achieve this without requiring trained probe classifiers or activation ablations. Instead, we introduce two completely training-free metrics derived directly from output logits: spilled energy, which captures the discrepancy between energy values across consecutive generation steps that should theoretically match, and marginalized energy, which is measurable at a single step. Evaluated on nine benchmarks across state-of-the-art LLMs (including LLaMA, Mistral, and Gemma) and on synthetic algebraic operations (Qwen3), our approach demonstrates robust, competitive hallucination detection and cross-task generalization. Notably, these results hold for both pretrained and instruction-tuned variants without introducing any training overhead. Code available at: github.com/OmnAI-Lab/spilled-energy</p> + https://arxiv.org/abs/2602.18671 + Sat, 21 Feb 2026 00:38:47 +0000 - VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training - https://arxiv.org/abs/2602.10693 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.10693.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Guobin Shen, Chenxiao Zhao, Xiang Cheng, Lei Huang, Xing Yu</p><p><b>Upvotes:</b> 215</p><p><b>Summary:</b> Training stability remains a central challenge in reinforcement learning (RL) for large language models (LLMs). Policy staleness, asynchronous training, and mismatches between training and inference engines all cause the behavior policy to diverge from the current policy, risking training collapse. Importance sampling provides a principled correction for this distribution shift but suffers from high variance; existing remedies such as token-level clipping and sequence-level normalization lack a unified theoretical foundation. We propose Variational sEquence-level Soft Policy Optimization (VESPO). By incorporating variance reduction into a variational formulation over proposal distributions, VESPO derives a closed-form reshaping kernel that operates directly on sequence-level importance weights without length normalization. Experiments on mathematical reasoning benchmarks show that VESPO maintains stable training under staleness ratios up to 64x and fully asynchronous execution, and delivers consistent gains across both dense and Mixture-of-Experts models. Code is available at https://github.com/FloyedShen/VESPO</p> - https://arxiv.org/abs/2602.10693 - Wed, 11 Feb 2026 09:48:08 +0000 + Classroom Final Exam: An Instructor-Tested Reasoning Benchmark + https://arxiv.org/abs/2602.19517 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.19517.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chongyang Gao, Diji Yang, Shuyan Zhou, Xichen Yan, Luchuan Song, Shuo Li, Kezhen Chen</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> We introduce (Classroom Final Exam), a multimodal benchmark for evaluating the reasoning capabilities of large language models across more than 20 STEM domains. is curated from repeatedly used, authentic university homework and exam problems, together with reference solutions provided by course instructors. presents a significant challenge even for frontier models: the newly released Gemini-3.1-pro-preview achieves an overall accuracy of 59.69\%, while the second-best model, Gemini-3-flash-preview, reaches 55.46\%, leaving considerable room for improvement. Beyond leaderboard results, we perform a diagnostic analysis by decomposing reference solutions into reasoning flows. We find that although frontier models can often answer intermediate sub-questions correctly, they struggle to reliably derive and maintain correct intermediate states throughout multi-step solutions. We further observe that model-generated solutions typically have more reasoning steps than those provided by the instructor, indicating suboptimal step efficiency and a higher risk of error accumulation. The data and code are available at https://github.com/Analogy-AI/CFE_Bench.</p> + https://arxiv.org/abs/2602.19517 + Mon, 23 Feb 2026 05:17:41 +0000 - AssetFormer: Modular 3D Assets Generation with Autoregressive Transformer - https://arxiv.org/abs/2602.12100 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.12100.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lingting Zhu, Shengju Qian, Haidi Fan, Jiayu Dong, Zhenchao Jin, Siwei Zhou, Gen Dong, Xin Wang, Lequan Yu</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> The digital industry demands high-quality, diverse modular 3D assets, especially for user-generated content~(UGC). In this work, we introduce AssetFormer, an autoregressive Transformer-based model designed to generate modular 3D assets from textual descriptions. Our pilot study leverages real-world modular assets collected from online platforms. AssetFormer tackles the challenge of creating assets composed of primitives that adhere to constrained design parameters for various applications. By innovatively adapting module sequencing and decoding techniques inspired by language models, our approach enhances asset generation quality through autoregressive modeling. Initial results indicate the effectiveness of AssetFormer in streamlining asset creation for professional development and UGC scenarios. This work presents a flexible framework extendable to various types of modular 3D assets, contributing to the broader field of 3D content generation. The code is available at https://github.com/Advocate99/AssetFormer.</p> - https://arxiv.org/abs/2602.12100 - Thu, 12 Feb 2026 15:55:21 +0000 + From Scale to Speed: Adaptive Test-Time Scaling for Image Editing + https://arxiv.org/abs/2603.00141 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.00141.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiangyan Qu, Zhenlong Yuan, Jing Tang, Rui Chen, Datao Tang, Meng Yu, Lei Sun, Yancheng Bai, Xiangxiang Chu, Gaopeng Gou, Gang Xiong, Yujun Cai</p><p><b>Upvotes:</b> 130</p><p><b>Summary:</b> Image Chain-of-Thought (Image-CoT) is a test-time scaling paradigm that improves image generation by extending inference time. Most Image-CoT methods focus on text-to-image (T2I) generation. Unlike T2I generation, image editing is goal-directed: the solution space is constrained by the source image and instruction. This mismatch causes three challenges when applying Image-CoT to editing: inefficient resource allocation with fixed sampling budgets, unreliable early-stage verification using general MLLM scores, and redundant edited results from large-scale sampling. To address this, we propose ADaptive Edit-CoT (ADE-CoT), an on-demand test-time scaling framework to enhance editing efficiency and performance. It incorporates three key strategies: (1) a difficulty-aware resource allocation that assigns dynamic budgets based on estimated edit difficulty; (2) edit-specific verification in early pruning that uses region localization and caption consistency to select promising candidates; and (3) depth-first opportunistic stopping, guided by an instance-specific verifier, that terminates when intent-aligned results are found. Extensive experiments on three SOTA editing models (Step1X-Edit, BAGEL, FLUX.1 Kontext) across three benchmarks show that ADE-CoT achieves superior performance-efficiency trade-offs. With comparable sampling budgets, ADE-CoT obtains better performance with more than 2x speedup over Best-of-N.</p> + https://arxiv.org/abs/2603.00141 + Tue, 24 Feb 2026 09:13:16 +0000 - DreamID-Omni: Unified Framework for Controllable Human-Centric Audio-Video Generation - https://arxiv.org/abs/2602.12160 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.12160.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xu Guo, Fulong Ye, Qichao Sun, Liyang Chen, Bingchuan Li, Pengze Zhang, Jiawei Liu, Songtao Zhao, Qian He, Xiangwang Hou</p><p><b>Upvotes:</b> 37</p><p><b>Summary:</b> Recent advancements in foundation models have revolutionized joint audio-video generation. However, existing approaches typically treat human-centric tasks including reference-based audio-video generation (R2AV), video editing (RV2AV) and audio-driven video animation (RA2V) as isolated objectives. Furthermore, achieving precise, disentangled control over multiple character identities and voice timbres within a single framework remains an open challenge. In this paper, we propose DreamID-Omni, a unified framework for controllable human-centric audio-video generation. Specifically, we design a Symmetric Conditional Diffusion Transformer that integrates heterogeneous conditioning signals via a symmetric conditional injection scheme. To resolve the pervasive identity-timbre binding failures and speaker confusion in multi-person scenarios, we introduce a Dual-Level Disentanglement strategy: Synchronized RoPE at the signal level to ensure rigid attention-space binding, and Structured Captions at the semantic level to establish explicit attribute-subject mappings. Furthermore, we devise a Multi-Task Progressive Training scheme that leverages weakly-constrained generative priors to regularize strongly-constrained tasks, preventing overfitting and harmonizing disparate objectives. Extensive experiments demonstrate that DreamID-Omni achieves comprehensive state-of-the-art performance across video, audio, and audio-visual consistency, even outperforming leading proprietary commercial models. We will release our code to bridge the gap between academic research and commercial-grade applications.</p> - https://arxiv.org/abs/2602.12160 - Thu, 12 Feb 2026 16:41:52 +0000 + LongVideo-R1: Smart Navigation for Low-cost Long Video Understanding + https://arxiv.org/abs/2602.20913 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.20913.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jihao Qiu, Lingxi Xie, Xinyue Huo, Qi Tian, Qixiang Ye</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> This paper addresses the critical and underexplored challenge of long video understanding with low computational budgets. We propose LongVideo-R1, an active, reasoning-equipped multimodal large language model (MLLM) agent designed for efficient video context navigation, avoiding the redundancy of exhaustive search. At the core of LongVideo-R1 lies a reasoning module that leverages high-level visual cues to infer the most informative video clip for subsequent processing. During inference, the agent initiates traversal from top-level visual summaries and iteratively refines its focus, immediately halting the exploration process upon acquiring sufficient knowledge to answer the query. To facilitate training, we first extract hierarchical video captions from CGBench, a video corpus with grounding annotations, and guide GPT-5 to generate 33K high-quality chain-of-thought-with-tool trajectories. The LongVideo-R1 agent is fine-tuned upon the Qwen-3-8B model through a two-stage paradigm: supervised fine-tuning (SFT) followed by reinforcement learning (RL), where RL employs a specifically designed reward function to maximize selective and efficient clip navigation. Experiments on multiple long video benchmarks validate the effectiveness of name, which enjoys superior tradeoff between QA accuracy and efficiency. All curated data and source code are provided in the supplementary material and will be made publicly available. Code and data are available at: https://github.com/qiujihao19/LongVideo-R1</p> + https://arxiv.org/abs/2602.20913 + Tue, 24 Feb 2026 13:49:47 +0000 - Query-focused and Memory-aware Reranker for Long Context Processing - https://arxiv.org/abs/2602.12192 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.12192.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuqing Li, Jiangnan Li, Mo Yu, Guoxuan Ding, Zheng Lin, Weiping Wang, Jie Zhou</p><p><b>Upvotes:</b> 51</p><p><b>Summary:</b> Built upon the existing analysis of retrieval heads in large language models, we propose an alternative reranking framework that trains models to estimate passage-query relevance using the attention scores of selected heads. This approach provides a listwise solution that leverages holistic information within the entire candidate shortlist during ranking. At the same time, it naturally produces continuous relevance scores, enabling training on arbitrary retrieval datasets without requiring Likert-scale supervision. Our framework is lightweight and effective, requiring only small-scale models (e.g., 4B parameters) to achieve strong performance. Extensive experiments demonstrate that our method outperforms existing state-of-the-art pointwise and listwise rerankers across multiple domains, including Wikipedia and long narrative datasets. It further establishes a new state-of-the-art on the LoCoMo benchmark that assesses the capabilities of dialogue understanding and memory usage. We further demonstrate that our framework supports flexible extensions. For example, augmenting candidate passages with contextual information further improves ranking accuracy, while training attention heads from middle layers enhances efficiency without sacrificing performance.</p> - https://arxiv.org/abs/2602.12192 - Thu, 12 Feb 2026 17:23:38 +0000 + Shared Nature, Unique Nurture: PRISM for Pluralistic Reasoning via In-context Structure Modeling + https://arxiv.org/abs/2602.21317 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.21317.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Guancheng Tu, Shiyang Zhang, Tianyu Zhang, Yi Zhang, Diji Yang</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Large Language Models (LLMs) are converging towards a singular Artificial Hivemind, where shared Nature (pre-training priors) result in a profound collapse of distributional diversity, limiting the distinct perspectives necessary for creative exploration and scientific discovery. To address this, we propose to equip models with inference-time Nurture (individualized epistemic trajectories) using Epistemic Evolution paradigm, progressing through explore, internalize, and express. We instantiate this via PRISM (Pluralistic Reasoning via In-context Structure Modeling), a model-agnostic system that augments LLM with dynamic On-the-fly Epistemic Graphs. On three creativity benchmarks, PRISM achieves state-of-the-art novelty and significantly expands distributional diversity. Moreover, we evaluate the real-world utility via a challenging rare-disease diagnosis benchmark. Results demonstrate that PRISM successfully uncovers correct long-tail diagnoses that standard LLM miss, confirming that its divergence stems from meaningful exploration rather than incoherent noise. Overall, this work establishes a new paradigm for Pluralistic AI, moving beyond monolithic consensus toward a diverse ecosystem of unique cognitive individuals capable of collective, multi-perspective discovery.</p> + https://arxiv.org/abs/2602.21317 + Tue, 24 Feb 2026 19:38:31 +0000 - LongCLI-Bench: A Preliminary Benchmark and Study for Long-horizon Agentic Programming in Command-Line Interfaces - https://arxiv.org/abs/2602.14337 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.14337.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yukang Feng, Jianwen Sun, Zelai Yang, Jiaxin Ai, Chuanhao Li, Zizhen Li, Fanrui Zhang, Kang He, Rui Ma, Jifan Lin, Jie Sun, Yang Xiao, Sizhuo Zhou, Wenxiao Wu, Yiming Liu, Pengfei Liu, Yu Qiao, Shenglin Zhang, Kaipeng Zhang</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Recent advances in AI-assisted programming have empowered agents to execute complex workflows via command-line interfaces, however, existing benchmarks are limited by short task horizons, data contamination from GitHub scraping, and a lack of fine-grained evaluation metrics, fail to rigorously evaluate the long-horizon planning and execution capabilities essential for realistic software engineering. To address these gaps, we introduce LongCLI-Bench, a comprehensive benchmark designed to evaluate agentic capabilities across long-horizon, realistic tasks. We curated 20 high-quality, long-horizon tasks from over 1,000 computer science assignments and real-world workflows, covering four engineering categories: from scratch, feature addition, bug fixing, and refactoring. We propose a dual-set testing protocol for LongCLI-Bench, which measures requirement fulfillment (fail-to-pass) and regression avoidance (pass-to-pass), and incorporates step-level scoring to pinpoint execution failures. Extensive experiments reveal that even state-of-the-art agents achieve pass rates below 20% in LongCLI-Bench. Step-level analysis further indicates that the majority of tasks stall at less than 30% completion, highlighting that critical failures often occur in the early stages. Although self-correction offers marginal gains, human-agent collaboration through plan injection and interactive guidance yields significantly higher improvements. These results highlight that future research must emphasize the development of synergistic human-agent workflows alongside advances in agents' planning and execution capabilities to overcome key challenges in long-horizon task performance.</p> - https://arxiv.org/abs/2602.14337 - Sun, 15 Feb 2026 23:12:57 +0000 + Tool-R0: Self-Evolving LLM Agents for Tool-Learning from Zero Data + https://arxiv.org/abs/2602.21320 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.21320.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Emre Can Acikgoz, Cheng Qian, Jonas Hübotter, Heng Ji, Dilek Hakkani-Tür, Gokhan Tur</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Large language models (LLMs) are becoming the foundation for autonomous agents that can use tools to solve complex tasks. Reinforcement learning (RL) has emerged as a common approach for injecting such agentic capabilities, but typically under tightly controlled training setups. It often depends on carefully constructed task-solution pairs and substantial human supervision, which creates a fundamental obstacle to open-ended self-evolution toward superintelligent systems. In this paper, we propose Tool-R0 framework for training general purpose tool-calling agents from scratch with self-play RL, under a zero-data assumption. Initialized from the same base LLM, Tool-R0 co-evolves a Generator and a Solver with complementary rewards: one proposes targeted challenging tasks at the other's competence frontier and the other learns to solve them with real-world tool calls. This creates a self-evolving cycle that requires no pre-existing tasks or datasets. Evaluation on different tool-use benchmarks show that Tool-R0 yields 92.5 relative improvement over the base model and surpasses fully supervised tool-calling baselines under the same setting. Our work further provides empirical insights into self-play LLM agents by analyzing co-evolution, curriculum dynamics, and scaling behavior.</p> + https://arxiv.org/abs/2602.21320 + Tue, 24 Feb 2026 19:41:18 +0000 - Model Context Protocol (MCP) Tool Descriptions Are Smelly! Towards Improving AI Agent Efficiency with Augmented MCP Tool Descriptions - https://arxiv.org/abs/2602.14878 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.14878.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mohammed Mehedi Hasan, Hao Li, Gopi Krishnan Rajbahadur, Bram Adams, Ahmed E. Hassan</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> The Model Context Protocol (MCP) introduces a standard specification that defines how Foundation Model (FM)-based agents should interact with external systems by invoking tools. However, to understand a tool's purpose and features, FMs rely on natural-language tool descriptions, making these descriptions a critical component in guiding FMs to select the optimal tool for a given (sub)task and to pass the right arguments to the tool. While defects or smells in these descriptions can misguide FM-based agents, their prevalence and consequences in the MCP ecosystem remain unclear. Hence, we examine 856 tools spread across 103 MCP servers empirically, assess their description quality, and their impact on agent performance. We identify six components of tool descriptions from the literature, develop a scoring rubric utilizing these components, and then formalize tool description smells based on this rubric. By operationalizing this rubric through an FM-based scanner, we find that 97.1% of the analyzed tool descriptions contain at least one smell, with 56% failing to state their purpose clearly. While augmenting these descriptions for all components improves task success rates by a median of 5.85 percentage points and improves partial goal completion by 15.12%, it also increases the number of execution steps by 67.46% and regresses performance in 16.67% of cases. These results indicate that achieving performance gains is not straightforward; while execution cost can act as a trade-off, execution context can also impact. Furthermore, component ablations show that compact variants of different component combinations often preserve behavioral reliability while reducing unnecessary token overhead, enabling more efficient use of the FM context window and lower execution costs.</p> - https://arxiv.org/abs/2602.14878 - Mon, 16 Feb 2026 16:10:11 +0000 + How to Take a Memorable Picture? Empowering Users with Actionable Feedback + https://arxiv.org/abs/2602.21877 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.21877.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Francesco Laiti, Davide Talon, Jacopo Staiano, Elisa Ricci</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Image memorability, i.e., how likely an image is to be remembered, has traditionally been studied in computer vision either as a passive prediction task, with models regressing a scalar score, or with generative methods altering the visual input to boost the image likelihood of being remembered. Yet, none of these paradigms supports users at capture time, when the crucial question is how to improve a photo memorability. We introduce the task of Memorability Feedback (MemFeed), where an automated model should provide actionable, human-interpretable guidance to users with the goal to enhance an image future recall. We also present MemCoach, the first approach designed to provide concrete suggestions in natural language for memorability improvement (e.g., "emphasize facial expression," "bring the subject forward"). Our method, based on Multimodal Large Language Models (MLLMs), is training-free and employs a teacher-student steering strategy, aligning the model internal activations toward more memorable patterns learned from a teacher model progressing along least-to-most memorable samples. To enable systematic evaluation on this novel task, we further introduce MemBench, a new benchmark featuring sequence-aligned photoshoots with annotated memorability scores. Our experiments, considering multiple MLLMs, demonstrate the effectiveness of MemCoach, showing consistently improved performance over several zero-shot models. The results indicate that memorability can not only be predicted but also taught and instructed, shifting the focus from mere prediction to actionable feedback for human creators.</p> + https://arxiv.org/abs/2602.21877 + Wed, 25 Feb 2026 13:02:35 +0000 - Image Generation with a Sphere Encoder - https://arxiv.org/abs/2602.15030 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.15030.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kaiyu Yue, Menglin Jia, Ji Hou, Tom Goldstein</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> We introduce the Sphere Encoder, an efficient generative framework capable of producing images in a single forward pass and competing with many-step diffusion models using fewer than five steps. Our approach works by learning an encoder that maps natural images uniformly onto a spherical latent space, and a decoder that maps random latent vectors back to the image space. Trained solely through image reconstruction losses, the model generates an image by simply decoding a random point on the sphere. Our architecture naturally supports conditional generation, and looping the encoder/decoder a few times can further enhance image quality. Across several datasets, the sphere encoder approach yields performance competitive with state of the art diffusions, but with a small fraction of the inference cost. Project page is available at https://sphere-encoder.github.io .</p> - https://arxiv.org/abs/2602.15030 - Mon, 16 Feb 2026 18:59:57 +0000 + Recovered in Translation: Efficient Pipeline for Automated Translation of Benchmarks and Datasets + https://arxiv.org/abs/2602.22207 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.22207.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hanna Yukhymenko, Anton Alexandrov, Martin Vechev</p><p><b>Upvotes:</b> 39</p><p><b>Summary:</b> The reliability of multilingual Large Language Model (LLM) evaluation is currently compromised by the inconsistent quality of translated benchmarks. Existing resources often suffer from semantic drift and context loss, which can lead to misleading performance metrics. In this work, we present a fully automated framework designed to address these challenges by enabling scalable, high-quality translation of datasets and benchmarks. We demonstrate that adapting test-time compute scaling strategies, specifically Universal Self-Improvement (USI) and our proposed multi-round ranking method, T-RANK, allows for significantly higher quality outputs compared to traditional pipelines. Our framework ensures that benchmarks preserve their original task structure and linguistic nuances during localization. We apply this approach to translate popular benchmarks and datasets into eight Eastern and Southern European languages (Ukrainian, Bulgarian, Slovak, Romanian, Lithuanian, Estonian, Turkish, Greek). Evaluations using both reference-based metrics and LLM-as-a-judge show that our translations surpass existing resources, resulting in more accurate downstream model assessment. We release both the framework and the improved benchmarks to facilitate robust and reproducible multilingual AI development.</p> + https://arxiv.org/abs/2602.22207 + Wed, 25 Feb 2026 18:58:25 +0000 - Spanning the Visual Analogy Space with a Weight Basis of LoRAs - https://arxiv.org/abs/2602.15727 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.15727.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hila Manor, Rinon Gal, Haggai Maron, Tomer Michaeli, Gal Chechik</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Visual analogy learning enables image manipulation through demonstration rather than textual description, allowing users to specify complex transformations difficult to articulate in words. Given a triplet {a, a', b}, the goal is to generate b' such that a : a' :: b : b'. Recent methods adapt text-to-image models to this task using a single Low-Rank Adaptation (LoRA) module, but they face a fundamental limitation: attempting to capture the diverse space of visual transformations within a fixed adaptation module constrains generalization capabilities. Inspired by recent work showing that LoRAs in constrained domains span meaningful, interpolatable semantic spaces, we propose LoRWeB, a novel approach that specializes the model for each analogy task at inference time through dynamic composition of learned transformation primitives, informally, choosing a point in a "space of LoRAs". We introduce two key components: (1) a learnable basis of LoRA modules, to span the space of different visual transformations, and (2) a lightweight encoder that dynamically selects and weighs these basis LoRAs based on the input analogy pair. Comprehensive evaluations demonstrate our approach achieves state-of-the-art performance and significantly improves generalization to unseen visual transformations. Our findings suggest that LoRA basis decompositions are a promising direction for flexible visual manipulation. Code and data are in https://research.nvidia.com/labs/par/lorweb</p> - https://arxiv.org/abs/2602.15727 - Tue, 17 Feb 2026 17:02:38 +0000 + dLLM: Simple Diffusion Language Modeling + https://arxiv.org/abs/2602.22661 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.22661.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhanhui Zhou, Lingjie Chen, Hanghang Tong, Dawn Song</p><p><b>Upvotes:</b> 121</p><p><b>Summary:</b> Although diffusion language models (DLMs) are evolving quickly, many recent models converge on a set of shared components. These components, however, are distributed across ad-hoc research codebases or lack transparent implementations, making them difficult to reproduce or extend. As the field accelerates, there is a clear need for a unified framework that standardizes these common components while remaining flexible enough to support new methods and architectures. To address this gap, we introduce dLLM, an open-source framework that unifies the core components of diffusion language modeling -- training, inference, and evaluation -- and makes them easy to customize for new designs. With dLLM, users can reproduce, finetune, deploy, and evaluate open-source large DLMs such as LLaDA and Dream through a standardized pipeline. The framework also provides minimal, reproducible recipes for building small DLMs from scratch with accessible compute, including converting any BERT-style encoder or autoregressive LM into a DLM. We also release the checkpoints of these small DLMs to make DLMs more accessible and accelerate future research.</p> + https://arxiv.org/abs/2602.22661 + Thu, 26 Feb 2026 06:26:02 +0000 - DeepVision-103K: A Visually Diverse, Broad-Coverage, and Verifiable Mathematical Dataset for Multimodal Reasoning - https://arxiv.org/abs/2602.16742 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.16742.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haoxiang Sun, Lizhen Xu, Bing Zhao, Wotao Yin, Wei Wang, Boyu Yang, Rui Wang, Hu Wei</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Reinforcement Learning with Verifiable Rewards (RLVR) has been shown effective in enhancing the visual reflection and reasoning capabilities of Large Multimodal Models (LMMs). However, existing datasets are predominantly derived from either small-scale manual construction or recombination of prior resources, which limits data diversity and coverage, thereby constraining further gains in model performance. To this end, we introduce DeepVision-103K, a comprehensive dataset for RLVR training that covers diverse K12 mathematical topics, extensive knowledge points, and rich visual elements. Models trained on DeepVision achieve strong performance on multimodal mathematical benchmarks, and generalize effectively to general multimodal reasoning tasks. Further analysis reveals enhanced visual perception, reflection and reasoning capabilities in trained models, validating DeepVision's effectiveness for advancing multimodal reasoning. Data: https://huggingface.co/datasets/skylenage/DeepVision-103K{this url}.</p> - https://arxiv.org/abs/2602.16742 - Wed, 18 Feb 2026 01:51:21 +0000 + Towards Simulating Social Media Users with LLMs: Evaluating the Operational Validity of Conditioned Comment Prediction + https://arxiv.org/abs/2602.22752 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.22752.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Nils Schwager, Simon Münker, Alistair Plum, Achim Rettinger</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> The transition of Large Language Models (LLMs) from exploratory tools to active "silicon subjects" in social science lacks extensive validation of operational validity. This study introduces Conditioned Comment Prediction (CCP), a task in which a model predicts how a user would comment on a given stimulus by comparing generated outputs with authentic digital traces. This framework enables a rigorous evaluation of current LLM capabilities with respect to the simulation of social media user behavior. We evaluated open-weight 8B models (Llama3.1, Qwen3, Ministral) in English, German, and Luxembourgish language scenarios. By systematically comparing prompting strategies (explicit vs. implicit) and the impact of Supervised Fine-Tuning (SFT), we identify a critical form vs. content decoupling in low-resource settings: while SFT aligns the surface structure of the text output (length and syntax), it degrades semantic grounding. Furthermore, we demonstrate that explicit conditioning (generated biographies) becomes redundant under fine-tuning, as models successfully perform latent inference directly from behavioral histories. Our findings challenge current "naive prompting" paradigms and offer operational guidelines prioritizing authentic behavioral traces over descriptive personas for high-fidelity simulation.</p> + https://arxiv.org/abs/2602.22752 + Thu, 26 Feb 2026 08:40:21 +0000 - PETS: A Principled Framework Towards Optimal Trajectory Allocation for Efficient Test-Time Self-Consistency - https://arxiv.org/abs/2602.16745 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.16745.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhangyi Liu, Huaizhi Qu, Xiaowei Yin, He Sun, Yanjun Han, Tianlong Chen, Zhun Deng</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Test-time scaling can improve model performance by aggregating stochastic reasoning trajectories. However, achieving sample-efficient test-time self-consistency under a limited budget remains an open challenge. We introduce PETS (Principled and Efficient Test-TimeSelf-Consistency), which initiates a principled study of trajectory allocation through an optimization framework. Central to our approach is the self-consistency rate, a new measure defined as agreement with the infinite-budget majority vote. This formulation makes sample-efficient test-time allocation theoretically grounded and amenable to rigorous analysis. We study both offline and online settings. In the offline regime, where all questions are known in advance, we connect trajectory allocation to crowdsourcing, a classic and well-developed area, by modeling reasoning traces as workers. This perspective allows us to leverage rich existing theory, yielding theoretical guarantees and an efficient majority-voting-based allocation algorithm. In the online streaming regime, where questions arrive sequentially and allocations must be made on the fly, we propose a novel method inspired by the offline framework. Our approach adapts budgets to question difficulty while preserving strong theoretical guarantees and computational efficiency. Experiments show that PETS consistently outperforms uniform allocation. On GPQA, PETS achieves perfect self-consistency in both settings while reducing the sampling budget by up to 75% (offline) and 55% (online) relative to uniform allocation. Code is available at https://github.com/ZDCSlab/PETS.</p> - https://arxiv.org/abs/2602.16745 - Wed, 18 Feb 2026 03:28:23 +0000 + SkillNet: Create, Evaluate, and Connect AI Skills + https://arxiv.org/abs/2603.04448 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.04448.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuan Liang, Ruobin Zhong, Haoming Xu, Chen Jiang, Yi Zhong, Runnan Fang, Jia-Chen Gu, Shumin Deng, Yunzhi Yao, Mengru Wang, Shuofei Qiao, Xin Xu, Tongtong Wu, Kun Wang, Yang Liu, Zhen Bi, Jungang Lou, Yuchen Eleanor Jiang, Hangcheng Zhu, Gang Yu, Haiwen Hong, Longtao Huang, Hui Xue, Chenxi Wang, Yijun Wang, Zifei Shan, Xi Chen, Zhaopeng Tu, Feiyu Xiong, Xin Xie, Peng Zhang, Zhengke Gui, Lei Liang, Jun Zhou, Chiyu Wu, Jin Shang, Yu Gong, Junyu Lin, Changliang Xu, Hongjie Deng, Wen Zhang, Keyan Ding, Qiang Zhang, Fei Huang, Ningyu Zhang, Jeff Z. Pan, Guilin Qi, Haofen Wang, Huajun Chen</p><p><b>Upvotes:</b> 64</p><p><b>Summary:</b> Current AI agents can flexibly invoke tools and execute complex tasks, yet their long-term advancement is hindered by the lack of systematic accumulation and transfer of skills. Without a unified mechanism for skill consolidation, agents frequently ``reinvent the wheel'', rediscovering solutions in isolated contexts without leveraging prior strategies. To overcome this limitation, we introduce SkillNet, an open infrastructure designed to create, evaluate, and organize AI skills at scale. SkillNet structures skills within a unified ontology that supports creating skills from heterogeneous sources, establishing rich relational connections, and performing multi-dimensional evaluation across Safety, Completeness, Executability, Maintainability, and Cost-awareness. Our infrastructure integrates a repository of over 200,000 skills, an interactive platform, and a versatile Python toolkit. Experimental evaluations on ALFWorld, WebShop, and ScienceWorld demonstrate that SkillNet significantly enhances agent performance, improving average rewards by 40% and reducing execution steps by 30% across multiple backbone models. By formalizing skills as evolving, composable assets, SkillNet provides a robust foundation for agents to move from transient experience to durable mastery.</p> + https://arxiv.org/abs/2603.04448 + Thu, 26 Feb 2026 14:24:02 +0000 - One-step Language Modeling via Continuous Denoising - https://arxiv.org/abs/2602.16813 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.16813.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chanhyuk Lee, Jaehoon Yoo, Manan Agarwal, Sheel Shah, Jerry Huang, Aditi Raghunathan, Seunghoon Hong, Nicholas M. Boffi, Jinwoo Kim</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Language models based on discrete diffusion have attracted widespread interest for their potential to provide faster generation than autoregressive models. In practice, however, they exhibit a sharp degradation of sample quality in the few-step regime, failing to realize this promise. Here we show that language models leveraging flow-based continuous denoising can outperform discrete diffusion in both quality and speed. By revisiting the fundamentals of flows over discrete modalities, we build a flow-based language model (FLM) that performs Euclidean denoising over one-hot token encodings. We show that the model can be trained by predicting the clean data via a cross entropy objective, where we introduce a simple time reparameterization that greatly improves training stability and generation quality. By distilling FLM into its associated flow map, we obtain a distilled flow map language model (FMLM) capable of few-step generation. On the LM1B and OWT language datasets, FLM attains generation quality matching state-of-the-art discrete diffusion models. With FMLM, our approach outperforms recent few-step language models across the board, with one-step generation exceeding their 8-step quality. Our work calls into question the widely held hypothesis that discrete diffusion processes are necessary for generative modeling over discrete modalities, and paves the way toward accelerated flow-based language modeling at scale. Code is available at https://github.com/david3684/flm.</p> - https://arxiv.org/abs/2602.16813 - Wed, 18 Feb 2026 19:23:07 +0000 + AgentVista: Evaluating Multimodal Agents in Ultra-Challenging Realistic Visual Scenarios + https://arxiv.org/abs/2602.23166 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.23166.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhaochen Su, Jincheng Gao, Hangyu Guo, Zhenhua Liu, Lueyang Zhang, Xinyu Geng, Shijue Huang, Peng Xia, Guanyu Jiang, Cheng Wang, Yue Zhang, Yi R. Fung, Junxian He</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> Real-world multimodal agents solve multi-step workflows grounded in visual evidence. For example, an agent can troubleshoot a device by linking a wiring photo to a schematic and validating the fix with online documentation, or plan a trip by interpreting a transit map and checking schedules under routing constraints. However, existing multimodal benchmarks mainly evaluate single-turn visual reasoning or specific tool skills, and they do not fully capture the realism, visual subtlety, and long-horizon tool use that practical agents require. We introduce AgentVista, a benchmark for generalist multimodal agents that spans 25 sub-domains across 7 categories, pairing realistic and detail-rich visual scenarios with natural hybrid tool use. Tasks require long-horizon tool interactions across modalities, including web search, image search, page navigation, and code-based operations for both image processing and general programming. Comprehensive evaluation of state-of-the-art models exposes significant gaps in their ability to carry out long-horizon multimodal tool use. Even the best model in our evaluation, Gemini-3-Pro with tools, achieves only 27.3% overall accuracy, and hard instances can require more than 25 tool-calling turns. We expect AgentVista to accelerate the development of more capable and reliable multimodal agents for realistic and ultra-challenging problem solving.</p> + https://arxiv.org/abs/2602.23166 + Thu, 26 Feb 2026 16:30:46 +0000 - SimToolReal: An Object-Centric Policy for Zero-Shot Dexterous Tool Manipulation - https://arxiv.org/abs/2602.16863 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.16863.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kushal Kedia, Tyler Ga Wei Lum, Jeannette Bohg, C. Karen Liu</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> The ability to manipulate tools significantly expands the set of tasks a robot can perform. Yet, tool manipulation represents a challenging class of dexterity, requiring grasping thin objects, in-hand object rotations, and forceful interactions. Since collecting teleoperation data for these behaviors is challenging, sim-to-real reinforcement learning (RL) is a promising alternative. However, prior approaches typically require substantial engineering effort to model objects and tune reward functions for each task. In this work, we propose SimToolReal, taking a step towards generalizing sim-to-real RL policies for tool manipulation. Instead of focusing on a single object and task, we procedurally generate a large variety of tool-like object primitives in simulation and train a single RL policy with the universal goal of manipulating each object to random goal poses. This approach enables SimToolReal to perform general dexterous tool manipulation at test-time without any object or task-specific training. We demonstrate that SimToolReal outperforms prior retargeting and fixed-grasp methods by 37% while matching the performance of specialist RL policies trained on specific target objects and tasks. Finally, we show that SimToolReal generalizes across a diverse set of everyday tools, achieving strong zero-shot performance over 120 real-world rollouts spanning 24 tasks, 12 object instances, and 6 tool categories.</p> - https://arxiv.org/abs/2602.16863 - Wed, 18 Feb 2026 20:42:39 +0000 + Large Multimodal Models as General In-Context Classifiers + https://arxiv.org/abs/2602.23229 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.23229.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Marco Garosi, Matteo Farina, Alessandro Conti, Massimiliano Mancini, Elisa Ricci</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Which multimodal model should we use for classification? Previous studies suggest that the answer lies in CLIP-like contrastive Vision-Language Models (VLMs), due to their remarkable performance in zero-shot classification. In contrast, Large Multimodal Models (LMM) are more suitable for complex tasks. In this work, we argue that this answer overlooks an important capability of LMMs: in-context learning. We benchmark state-of-the-art LMMs on diverse datasets for closed-world classification and find that, although their zero-shot performance is lower than CLIP's, LMMs with a few in-context examples can match or even surpass contrastive VLMs with cache-based adapters, their "in-context" equivalent. We extend this analysis to the open-world setting, where the generative nature of LMMs makes them more suitable for the task. In this challenging scenario, LMMs struggle whenever provided with imperfect context information. To address this issue, we propose CIRCLE, a simple training-free method that assigns pseudo-labels to in-context examples, iteratively refining them with the available context itself. Through extensive experiments, we show that CIRCLE establishes a robust baseline for open-world classification, surpassing VLM counterparts and highlighting the potential of LMMs to serve as unified classifiers, and a flexible alternative to specialized models.</p> + https://arxiv.org/abs/2602.23229 + Thu, 26 Feb 2026 17:08:18 +0000 - DODO: Discrete OCR Diffusion Models - https://arxiv.org/abs/2602.16872 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.16872.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sean Man, Roy Ganz, Roi Ronen, Shahar Tsiper, Shai Mazor, Niv Nayman</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Optical Character Recognition (OCR) is a fundamental task for digitizing information, serving as a critical bridge between visual data and textual understanding. While modern Vision-Language Models (VLM) have achieved high accuracy in this domain, they predominantly rely on autoregressive decoding, which becomes computationally expensive and slow for long documents as it requires a sequential forward pass for every generated token. We identify a key opportunity to overcome this bottleneck: unlike open-ended generation, OCR is a highly deterministic task where the visual input strictly dictates a unique output sequence, theoretically enabling efficient, parallel decoding via diffusion models. However, we show that existing masked diffusion models fail to harness this potential; those introduce structural instabilities that are benign in flexible tasks, like captioning, but catastrophic for the rigid, exact-match requirements of OCR. To bridge this gap, we introduce DODO, the first VLM to utilize block discrete diffusion and unlock its speedup potential for OCR. By decomposing generation into blocks, DODO mitigates the synchronization errors of global diffusion. Empirically, our method achieves near state-of-the-art accuracy while enabling up to 3x faster inference compared to autoregressive baselines.</p> - https://arxiv.org/abs/2602.16872 - Wed, 18 Feb 2026 20:59:22 +0000 + Truncated Step-Level Sampling with Process Rewards for Retrieval-Augmented Reasoning + https://arxiv.org/abs/2602.23440 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.23440.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chris Samarinas, Haw-Shiuan Chang, Hamed Zamani</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Training large language models to reason with search engines via reinforcement learning is hindered by a fundamental credit assignment problem: existing methods such as Search-R1 provide only a sparse outcome reward after an entire multi-step trajectory, making it infeasible to attribute success or failure to individual reasoning and retrieval decisions. Process-reward methods like StepSearch alleviate this by introducing step-level supervision, but rely on heuristic rewards such as TF-IDF overlap with gold documents, and still sample k complete trajectories per example, retaining high gradient variance. We propose SLATE, a framework built on two complementary ideas: (1) truncated step-level sampling, which generates k trajectories that share a common prefix and differ only at the next step, and (2) dense LLM-as-judge rewards, which replace heuristic scoring with a capable LLM evaluator that assesses the quality of each reasoning step, search query, and answer, providing richer and more reliable supervision. We theoretically prove that under the same dense reward structure, truncated sampling reduces the variance of advantage estimates by up to a factor of T compared to full-trajectory sampling for T-step trajectories, yielding lower-variance, better-targeted policy gradients. Experiments on seven QA benchmarks confirm that SLATE consistently outperforms both sparse-reward and process-reward baselines, with the largest gains on harder multi-hop tasks and smaller models.</p> + https://arxiv.org/abs/2602.23440 + Thu, 26 Feb 2026 19:05:40 +0000 - RankEvolve: Automating the Discovery of Retrieval Algorithms via LLM-Driven Evolution - https://arxiv.org/abs/2602.16932 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.16932.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jinming Nian, Fangchen Li, Dae Hoon Park, Yi Fang</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Retrieval algorithms like BM25 and query likelihood with Dirichlet smoothing remain strong and efficient first-stage rankers, yet improvements have mostly relied on parameter tuning and human intuition. We investigate whether a large language model, guided by an evaluator and evolutionary search, can automatically discover improved lexical retrieval algorithms. We introduce RankEvolve, a program evolution setup based on AlphaEvolve, in which candidate ranking algorithms are represented as executable code and iteratively mutated, recombined, and selected based on retrieval performance across 12 IR datasets from BEIR and BRIGHT. RankEvolve starts from two seed programs: BM25 and query likelihood with Dirichlet smoothing. The evolved algorithms are novel, effective, and show promising transfer to the full BEIR and BRIGHT benchmarks as well as TREC DL 19 and 20. Our results suggest that evaluator-guided LLM program evolution is a practical path towards automatic discovery of novel ranking algorithms.</p> - https://arxiv.org/abs/2602.16932 - Wed, 18 Feb 2026 22:53:18 +0000 + CiteAudit: You Cited It, But Did You Read It? A Benchmark for Verifying Scientific References in the LLM Era + https://arxiv.org/abs/2602.23452 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.23452.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhengqing Yuan, Kaiwen Shi, Zheyuan Zhang, Lichao Sun, Nitesh V. Chawla, Yanfang Ye</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Scientific research relies on accurate citation for attribution and integrity, yet large language models (LLMs) introduce a new risk: fabricated references that appear plausible but correspond to no real publications. Such hallucinated citations have already been observed in submissions and accepted papers at major machine learning venues, exposing vulnerabilities in peer review. Meanwhile, rapidly growing reference lists make manual verification impractical, and existing automated tools remain fragile to noisy and heterogeneous citation formats and lack standardized evaluation. We present the first comprehensive benchmark and detection framework for hallucinated citations in scientific writing. Our multi-agent verification pipeline decomposes citation checking into claim extraction, evidence retrieval, passage matching, reasoning, and calibrated judgment to assess whether a cited source truly supports its claim. We construct a large-scale human-validated dataset across domains and define unified metrics for citation faithfulness and evidence alignment. Experiments with state-of-the-art LLMs reveal substantial citation errors and show that our framework significantly outperforms prior methods in both accuracy and interpretability. This work provides the first scalable infrastructure for auditing citations in the LLM era and practical tools to improve the trustworthiness of scientific references.</p> + https://arxiv.org/abs/2602.23452 + Thu, 26 Feb 2026 19:17:39 +0000 - Conv-FinRe: A Conversational and Longitudinal Benchmark for Utility-Grounded Financial Recommendation - https://arxiv.org/abs/2602.16990 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.16990.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yan Wang, Yi Han, Lingfei Qian, Yueru He, Xueqing Peng, Dongji Feng, Zhuohan Xie, Vincent Jim Zhang, Rosie Guo, Fengran Mo, Jimin Huang, Yankai Chen, Xue Liu, Jian-Yun Nie</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Most recommendation benchmarks evaluate how well a model imitates user behavior. In financial advisory, however, observed actions can be noisy or short-sighted under market volatility and may conflict with a user's long-term goals. Treating what users chose as the sole ground truth, therefore, conflates behavioral imitation with decision quality. We introduce Conv-FinRe, a conversational and longitudinal benchmark for stock recommendation that evaluates LLMs beyond behavior matching. Given an onboarding interview, step-wise market context, and advisory dialogues, models must generate rankings over a fixed investment horizon. Crucially, Conv-FinRe provides multi-view references that distinguish descriptive behavior from normative utility grounded in investor-specific risk preferences, enabling diagnosis of whether an LLM follows rational analysis, mimics user noise, or is driven by market momentum. We build the benchmark from real market data and human decision trajectories, instantiate controlled advisory conversations, and evaluate a suite of state-of-the-art LLMs. Results reveal a persistent tension between rational decision quality and behavioral alignment: models that perform well on utility-based ranking often fail to match user choices, whereas behaviorally aligned models can overfit short-term noise. The dataset is publicly released on Hugging Face, and the codebase is available on GitHub.</p> - https://arxiv.org/abs/2602.16990 - Thu, 19 Feb 2026 01:29:50 +0000 + Humans and LLMs Diverge on Probabilistic Inferences + https://arxiv.org/abs/2602.23546 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.23546.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Gaurav Kamath, Sreenath Madathil, Sebastian Schuster, Marie-Catherine de Marneffe, Siva Reddy</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Human reasoning often involves working over limited information to arrive at probabilistic conclusions. In its simplest form, this involves making an inference that is not strictly entailed by a premise, but rather only likely given the premise. While reasoning LLMs have demonstrated strong performance on logical and mathematical tasks, their behavior on such open-ended, non-deterministic inferences remains largely unexplored. We introduce ProbCOPA, a dataset of 210 handcrafted probabilistic inferences in English, each annotated for inference likelihood by 25--30 human participants. We find that human responses are graded and varied, revealing probabilistic judgments of the inferences in our dataset. Comparing these judgments with responses from eight state-of-the-art reasoning LLMs, we show that models consistently fail to produce human-like distributions. Finally, analyzing LLM reasoning chains, we find evidence of a common reasoning pattern used to evaluate such inferences. Our findings reveal persistent differences between humans and LLMs, and underscore the need to evaluate reasoning beyond deterministic settings.</p> + https://arxiv.org/abs/2602.23546 + Thu, 26 Feb 2026 23:00:41 +0000 - Adam Improves Muon: Adaptive Moment Estimation with Orthogonalized Momentum - https://arxiv.org/abs/2602.17080 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.17080.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Minxin Zhang, Yuxuan Liu, Hayden Scheaffer</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Efficient stochastic optimization typically integrates an update direction that performs well in the deterministic regime with a mechanism adapting to stochastic perturbations. While Adam uses adaptive moment estimates to promote stability, Muon utilizes the weight layers' matrix structure via orthogonalized momentum, showing superior performance in large language model training. We propose a new optimizer and a diagonal extension, NAMO and NAMO-D, providing the first principled integration of orthogonalized momentum with norm-based Adam-type noise adaptation. NAMO scales orthogonalized momentum using a single adaptive stepsize, preserving orthogonality while improving upon Muon at negligible additional cost. NAMO-D instead right-multiplies orthogonalized momentum by a diagonal matrix with clamped entries. This design enables neuron-wise noise adaptation and aligns with the common near block-diagonal Hessian structure. Under standard assumptions, we establish optimal convergence rates for both algorithms in the deterministic setting and show that, in the stochastic setting, their convergence guarantees adapt to the noise level of stochastic gradients. Experiments on pretraining GPT-2 models demonstrate improved performance of both NAMO and NAMO-D compared to the AdamW and Muon baselines, with NAMO-D achieving further gains over NAMO via an additional clamping hyperparameter that balances the competing goals of maintaining a well-conditioned update direction and leveraging fine-grained noise adaptation.</p> - https://arxiv.org/abs/2602.17080 - Thu, 19 Feb 2026 05:00:39 +0000 + SWE-rebench V2: Language-Agnostic SWE Task Collection at Scale + https://arxiv.org/abs/2602.23866 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.23866.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ibragim Badertdinov, Maksim Nekrashevich, Anton Shevtsov, Alexander Golubev</p><p><b>Upvotes:</b> 76</p><p><b>Summary:</b> Software engineering agents (SWE) are improving rapidly, with recent gains largely driven by reinforcement learning (RL). However, RL training is constrained by the scarcity of large-scale task collections with reproducible execution environments and reliable test suites. Although a growing number of benchmarks have emerged, datasets suitable for training remain limited in scale and diversity or often target a limited set of high-resource language ecosystems. We introduce SWE-rebench V2, a language-agnostic automated pipeline for harvesting executable real-world SWE tasks and constructing RL training environments at scale. The pipeline synthesizes repository-specific installation and test procedures via an interactive setup agent, and filters unsound instances using an ensemble of LLM judges, validated against human-verified SWE-bench annotations. Using this pipeline, we construct a dataset of 32,000+ tasks spanning 20 languages and 3,600+ repositories, with pre-built images for reproducible execution. To further scale training data, we additionally release 120,000+ tasks with installation instructions, fail-to-pass tests and rich metadata, where the problem statement is generated based on the original pull request description. We validate the collected instances through a diagnostic study that covers a subset of tasks in five programming languages across seven popular models, and provide instance-level metadata that flags common confounders such as overly restrictive tests and underspecified descriptions. We release the datasets, the collection and execution code, and associated artifacts to enable large-scale training of SWE agents across diverse languages and repositories.</p> + https://arxiv.org/abs/2602.23866 + Fri, 27 Feb 2026 10:06:10 +0000 - Selective Training for Large Vision Language Models via Visual Information Gain - https://arxiv.org/abs/2602.17186 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.17186.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Seulbi Lee, Sangheum Hwang</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Large Vision Language Models (LVLMs) have achieved remarkable progress, yet they often suffer from language bias, producing answers without relying on visual evidence. While prior work attempts to mitigate this issue through decoding strategies, architectural modifications, or curated instruction data, they typically lack a quantitative measure of how much individual training samples or tokens actually benefit from the image. In this work, we introduce Visual Information Gain (VIG), a perplexity-based metric that measures the reduction in prediction uncertainty provided by visual input. VIG enables fine-grained analysis at both sample and token levels, effectively highlighting visually grounded elements such as colors, spatial relations, and attributes. Leveraging this, we propose a VIG-guided selective training scheme that prioritizes high-VIG samples and tokens. This approach improves visual grounding and mitigates language bias, achieving superior performance with significantly reduced supervision by focusing exclusively on visually informative samples and tokens.</p> - https://arxiv.org/abs/2602.17186 - Thu, 19 Feb 2026 09:12:21 +0000 + LK Losses: Direct Acceptance Rate Optimization for Speculative Decoding + https://arxiv.org/abs/2602.23881 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.23881.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Alexander Samarin, Sergei Krutikov, Anton Shevtsov, Sergei Skvortsov, Filipp Fisin, Alexander Golubev</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> Speculative decoding accelerates autoregressive large language model (LLM) inference by using a lightweight draft model to propose candidate tokens that are then verified in parallel by the target model. The speedup is significantly determined by the acceptance rate, yet standard training minimizes Kullback-Leibler (KL) divergence as a proxy objective. While KL divergence and acceptance rate share the same global optimum, small draft models, having limited capacity, typically converge to suboptimal solutions where minimizing KL does not guarantee maximizing acceptance rate. To address this issue, we propose LK losses, special training objectives that directly target acceptance rate. Comprehensive experiments across four draft architectures and six target models, ranging from 8B to 685B parameters, demonstrate consistent improvements in acceptance metrics across all configurations compared to the standard KL-based training. We evaluate our approach on general, coding and math domains and report gains of up to 8-10% in average acceptance length. LK losses are easy to implement, introduce no computational overhead and can be directly integrated into any existing speculator training framework, making them a compelling alternative to the existing draft training objectives.</p> + https://arxiv.org/abs/2602.23881 + Fri, 27 Feb 2026 10:20:11 +0000 - AI Gamestore: Scalable, Open-Ended Evaluation of Machine General Intelligence with Human Games - https://arxiv.org/abs/2602.17594 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.17594.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lance Ying, Ryan Truong, Prafull Sharma, Kaiya Ivy Zhao, Nathan Cloos, Kelsey R. Allen, Thomas L. Griffiths, Katherine M. Collins, José Hernández-Orallo, Phillip Isola, Samuel J. Gershman, Joshua B. Tenenbaum</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Rigorously evaluating machine intelligence against the broad spectrum of human general intelligence has become increasingly important and challenging in this era of rapid technological advance. Conventional AI benchmarks typically assess only narrow capabilities in a limited range of human activity. Most are also static, quickly saturating as developers explicitly or implicitly optimize for them. We propose that a more promising way to evaluate human-like general intelligence in AI systems is through a particularly strong form of general game playing: studying how and how well they play and learn to play all conceivable human games, in comparison to human players with the same level of experience, time, or other resources. We define a "human game" to be a game designed by humans for humans, and argue for the evaluative suitability of this space of all such games people can imagine and enjoy -- the "Multiverse of Human Games". Taking a first step towards this vision, we introduce the AI GameStore, a scalable and open-ended platform that uses LLMs with humans-in-the-loop to synthesize new representative human games, by automatically sourcing and adapting standardized and containerized variants of game environments from popular human digital gaming platforms. As a proof of concept, we generated 100 such games based on the top charts of Apple App Store and Steam, and evaluated seven frontier vision-language models (VLMs) on short episodes of play. The best models achieved less than 10\% of the human average score on the majority of the games, and especially struggled with games that challenge world-model learning, memory and planning. We conclude with a set of next steps for building out the AI GameStore as a practical way to measure and drive progress toward human-like general intelligence in machines.</p> - https://arxiv.org/abs/2602.17594 - Thu, 19 Feb 2026 18:17:25 +0000 + Ref-Adv: Exploring MLLM Visual Reasoning in Referring Expression Tasks + https://arxiv.org/abs/2602.23898 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.23898.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qihua Dong, Kuo Yang, Lin Ju, Handong Zhao, Yitian Zhang, Yizhou Wang, Huimin Zeng, Jianglin Lu, Yun Fu</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Referring Expression Comprehension (REC) links language to region level visual perception. Standard benchmarks (RefCOCO, RefCOCO+, RefCOCOg) have progressed rapidly with multimodal LLMs but remain weak tests of visual reasoning and grounding: (i) many expressions are very short, leaving little reasoning demand; (ii) images often contain few distractors, making the target easy to find; and (iii) redundant descriptors enable shortcut solutions that bypass genuine text understanding and visual reasoning. We introduce Ref-Adv, a modern REC benchmark that suppresses shortcuts by pairing linguistically nontrivial expressions with only the information necessary to uniquely identify the target. The dataset contains referring expressions on real images, curated with hard distractors and annotated with reasoning facets including negation. We conduct comprehensive ablations (word order perturbations and descriptor deletion sufficiency) to show that solving Ref-Adv requires reasoning beyond simple cues, and we evaluate a broad suite of contemporary multimodal LLMs on Ref-Adv. Despite strong results on RefCOCO, RefCOCO+, and RefCOCOg, models drop markedly on Ref-Adv, revealing reliance on shortcuts and gaps in visual reasoning and grounding. We provide an in depth failure analysis and aim for Ref-Adv to guide future work on visual reasoning and grounding in MLLMs.</p> + https://arxiv.org/abs/2602.23898 + Fri, 27 Feb 2026 10:47:26 +0000 - MolHIT: Advancing Molecular-Graph Generation with Hierarchical Discrete Diffusion Models - https://arxiv.org/abs/2602.17602 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.17602.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hojung Jung, Rodrigo Hormazabal, Jaehyeong Jo, Youngrok Park, Kyunggeun Roh, Se-Young Yun, Sehui Han, Dae-Woong Jeong</p><p><b>Upvotes:</b> 53</p><p><b>Summary:</b> Molecular generation with diffusion models has emerged as a promising direction for AI-driven drug discovery and materials science. While graph diffusion models have been widely adopted due to the discrete nature of 2D molecular graphs, existing models suffer from low chemical validity and struggle to meet the desired properties compared to 1D modeling. In this work, we introduce MolHIT, a powerful molecular graph generation framework that overcomes long-standing performance limitations in existing methods. MolHIT is based on the Hierarchical Discrete Diffusion Model, which generalizes discrete diffusion to additional categories that encode chemical priors, and decoupled atom encoding that splits the atom types according to their chemical roles. Overall, MolHIT achieves new state-of-the-art performance on the MOSES dataset with near-perfect validity for the first time in graph diffusion, surpassing strong 1D baselines across multiple metrics. We further demonstrate strong performance in downstream tasks, including multi-property guided generation and scaffold extension.</p> - https://arxiv.org/abs/2602.17602 - Thu, 19 Feb 2026 18:27:11 +0000 + Half-Truths Break Similarity-Based Retrieval + https://arxiv.org/abs/2602.23906 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.23906.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bora Kargi, Arnas Uselis, Seong Joon Oh</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> When a text description is extended with an additional detail, image-text similarity should drop if that detail is wrong. We show that CLIP-style dual encoders often violate this intuition: appending a plausible but incorrect object or relation to an otherwise correct description can increase the similarity score. We call such cases half-truths. On COCO, CLIP prefers the correct shorter description only 40.6% of the time, and performance drops to 32.9% when the added detail is a relation. We trace this vulnerability to weak supervision on caption parts: contrastive training aligns full sentences but does not explicitly enforce that individual entities and relations are grounded. We propose CS-CLIP (Component-Supervised CLIP), which decomposes captions into entity and relation units, constructs a minimally edited foil for each unit, and fine-tunes the model to score the correct unit above its foil while preserving standard dual-encoder inference. CS-CLIP raises half-truth accuracy to 69.3% and improves average performance on established compositional benchmarks by 5.7 points, suggesting that reducing half-truth errors aligns with broader gains in compositional understanding. Code is publicly available at: https://github.com/kargibora/CS-CLIP</p> + https://arxiv.org/abs/2602.23906 + Fri, 27 Feb 2026 10:56:31 +0000 - Sink-Aware Pruning for Diffusion Language Models - https://arxiv.org/abs/2602.17664 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.17664.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Aidar Myrzakhan, Tianyi Li, Bowei Guo, Shengkun Tang, Zhiqiang Shen</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Diffusion Language Models (DLMs) incur high inference cost due to iterative denoising, motivating efficient pruning. Existing pruning heuristics largely inherited from autoregressive (AR) LLMs, typically preserve attention sink tokens because AR sinks serve as stable global anchors. We show that this assumption does not hold for DLMs: the attention-sink position exhibits substantially higher variance over the full generation trajectory (measured by how the dominant sink locations shift across timesteps), indicating that sinks are often transient and less structurally essential than in AR models. Based on this observation, we propose {bf Sink-Aware Pruning}, which automatically identifies and prunes unstable sinks in DLMs (prior studies usually keep sinks for AR LLMs). Without retraining, our method achieves a better quality-efficiency trade-off and outperforms strong prior pruning baselines under matched compute. Our code is available at https://github.com/VILA-Lab/Sink-Aware-Pruning.</p> - https://arxiv.org/abs/2602.17664 - Thu, 19 Feb 2026 18:59:50 +0000 + Accelerating Masked Image Generation by Learning Latent Controlled Dynamics + https://arxiv.org/abs/2602.23996 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.23996.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kaiwen Zhu, Quansheng Zeng, Yuandong Pu, Shuo Cao, Xiaohui Li, Yi Xin, Qi Qin, Jiayang Li, Yu Qiao, Jinjin Gu, Yihao Liu</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Masked Image Generation Models (MIGMs) have achieved great success, yet their efficiency is hampered by the multiple steps of bi-directional attention. In fact, there exists notable redundancy in their computation: when sampling discrete tokens, the rich semantics contained in the continuous features are lost. Some existing works attempt to cache the features to approximate future features. However, they exhibit considerable approximation error under aggressive acceleration rates. We attribute this to their limited expressivity and the failure to account for sampling information. To fill this gap, we propose to learn a lightweight model that incorporates both previous features and sampled tokens, and regresses the average velocity field of feature evolution. The model has moderate complexity that suffices to capture the subtle dynamics while keeping lightweight compared to the original base model. We apply our method, MIGM-Shortcut, to two representative MIGM architectures and tasks. In particular, on the state-of-the-art Lumina-DiMOO, it achieves over 4x acceleration of text-to-image generation while maintaining quality, significantly pushing the Pareto frontier of masked image generation. The code and model weights are available at https://github.com/Kaiwen-Zhu/MIGM-Shortcut.</p> + https://arxiv.org/abs/2602.23996 + Fri, 27 Feb 2026 13:16:58 +0000 - VidEoMT: Your ViT is Secretly Also a Video Segmentation Model - https://arxiv.org/abs/2602.17807 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.17807.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Narges Norouzi, Idil Esen Zulfikar, Niccol`o Cavagnero, Tommie Kerssies, Bastian Leibe, Gijs Dubbelman, Daan de Geus</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Existing online video segmentation models typically combine a per-frame segmenter with complex specialized tracking modules. While effective, these modules introduce significant architectural complexity and computational overhead. Recent studies suggest that plain Vision Transformer (ViT) encoders, when scaled with sufficient capacity and large-scale pre-training, can conduct accurate image segmentation without requiring specialized modules. Motivated by this observation, we propose the Video Encoder-only Mask Transformer (VidEoMT), a simple encoder-only video segmentation model that eliminates the need for dedicated tracking modules. To enable temporal modeling in an encoder-only ViT, VidEoMT introduces a lightweight query propagation mechanism that carries information across frames by reusing queries from the previous frame. To balance this with adaptability to new content, it employs a query fusion strategy that combines the propagated queries with a set of temporally-agnostic learned queries. As a result, VidEoMT attains the benefits of a tracker without added complexity, achieving competitive accuracy while being 5x--10x faster, running at up to 160 FPS with a ViT-L backbone. Code: https://www.tue-mps.org/videomt/</p> - https://arxiv.org/abs/2602.17807 - Thu, 19 Feb 2026 20:14:14 +0000 + InfoNCE Induces Gaussian Distribution + https://arxiv.org/abs/2602.24012 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.24012.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Roy Betser, Eyal Gofer, Meir Yossef Levi, Guy Gilboa</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Contrastive learning has become a cornerstone of modern representation learning, allowing training with massive unlabeled data for both task-specific and general (foundation) models. A prototypical loss in contrastive training is InfoNCE and its variants. In this work, we show that the InfoNCE objective induces Gaussian structure in representations that emerge from contrastive training. We establish this result in two complementary regimes. First, we show that under certain alignment and concentration assumptions, projections of the high-dimensional representation asymptotically approach a multivariate Gaussian distribution. Next, under less strict assumptions, we show that adding a small asymptotically vanishing regularization term that promotes low feature norm and high feature entropy leads to similar asymptotic results. We support our analysis with experiments on synthetic and CIFAR-10 datasets across multiple encoder architectures and sizes, demonstrating consistent Gaussian behavior. This perspective provides a principled explanation for commonly observed Gaussianity in contrastive representations. The resulting Gaussian model enables principled analytical treatment of learned representations and is expected to support a wide range of applications in contrastive learning.</p> + https://arxiv.org/abs/2602.24012 + Fri, 27 Feb 2026 13:35:58 +0000 - EgoPush: Learning End-to-End Egocentric Multi-Object Rearrangement for Mobile Robots - https://arxiv.org/abs/2602.18071 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.18071.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Boyuan An, Zhexiong Wang, Yipeng Wang, Jiaqi Li, Sihang Li, Jing Zhang, Chen Feng</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> Humans can rearrange objects in cluttered environments using egocentric perception, navigating occlusions without global coordinates. Inspired by this capability, we study long-horizon multi-object non-prehensile rearrangement for mobile robots using a single egocentric camera. We introduce EgoPush, a policy learning framework that enables egocentric, perception-driven rearrangement without relying on explicit global state estimation that often fails in dynamic scenes. EgoPush designs an object-centric latent space to encode relative spatial relations among objects, rather than absolute poses. This design enables a privileged reinforcement-learning (RL) teacher to jointly learn latent states and mobile actions from sparse keypoints, which is then distilled into a purely visual student policy. To reduce the supervision gap between the omniscient teacher and the partially observed student, we restrict the teacher's observations to visually accessible cues. This induces active perception behaviors that are recoverable from the student's viewpoint. To address long-horizon credit assignment, we decompose rearrangement into stage-level subproblems using temporally decayed, stage-local completion rewards. Extensive simulation experiments demonstrate that EgoPush significantly outperforms end-to-end RL baselines in success rate, with ablation studies validating each design choice. We further demonstrate zero-shot sim-to-real transfer on a mobile platform in the real world. Code and videos are available at https://ai4ce.github.io/EgoPush/.</p> - https://arxiv.org/abs/2602.18071 - Fri, 20 Feb 2026 08:54:20 +0000 + SenCache: Accelerating Diffusion Model Inference via Sensitivity-Aware Caching + https://arxiv.org/abs/2602.24208 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.24208.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yasaman Haghighi, Alexandre Alahi</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Diffusion models achieve state-of-the-art video generation quality, but their inference remains expensive due to the large number of sequential denoising steps. This has motivated a growing line of research on accelerating diffusion inference. Among training-free acceleration methods, caching reduces computation by reusing previously computed model outputs across timesteps. Existing caching methods rely on heuristic criteria to choose cache/reuse timesteps and require extensive tuning. We address this limitation with a principled sensitivity-aware caching framework. Specifically, we formalize the caching error through an analysis of the model output sensitivity to perturbations in the denoising inputs, i.e., the noisy latent and the timestep, and show that this sensitivity is a key predictor of caching error. Based on this analysis, we propose Sensitivity-Aware Caching (SenCache), a dynamic caching policy that adaptively selects caching timesteps on a per-sample basis. Our framework provides a theoretical basis for adaptive caching, explains why prior empirical heuristics can be partially effective, and extends them to a dynamic, sample-specific approach. Experiments on Wan 2.1, CogVideoX, and LTX-Video show that SenCache achieves better visual quality than existing caching methods under similar computational budgets.</p> + https://arxiv.org/abs/2602.24208 + Fri, 27 Feb 2026 17:36:09 +0000 - VLANeXt: Recipes for Building Strong VLA Models - https://arxiv.org/abs/2602.18532 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.18532.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiao-Ming Wu, Bin Fan, Kang Liao, Jian-Jian Jiang, Runze Yang, Yihang Luo, Zhonghua Wu, Wei-Shi Zheng, Chen Change Loy</p><p><b>Upvotes:</b> 52</p><p><b>Summary:</b> Following the rise of large foundation models, Vision-Language-Action models (VLAs) emerged, leveraging strong visual and language understanding for general-purpose policy learning. Yet, the current VLA landscape remains fragmented and exploratory. Although many groups have proposed their own VLA models, inconsistencies in training protocols and evaluation settings make it difficult to identify which design choices truly matter. To bring structure to this evolving space, we reexamine the VLA design space under a unified framework and evaluation setup. Starting from a simple VLA baseline similar to RT-2 and OpenVLA, we systematically dissect design choices along three dimensions: foundational components, perception essentials, and action modelling perspectives. From this study, we distill 12 key findings that together form a practical recipe for building strong VLA models. The outcome of this exploration is a simple yet effective model, VLANeXt. VLANeXt outperforms prior state-of-the-art methods on the LIBERO and LIBERO-plus benchmarks and demonstrates strong generalization in real-world experiments. We will release a unified, easy-to-use codebase that serves as a common platform for the community to reproduce our findings, explore the design space, and build new VLA variants on top of a shared foundation.</p> - https://arxiv.org/abs/2602.18532 - Fri, 20 Feb 2026 09:26:17 +0000 + Enhancing Spatial Understanding in Image Generation via Reward Modeling + https://arxiv.org/abs/2602.24233 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.24233.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhenyu Tang, Chaoran Feng, Yufan Deng, Jie Wu, Xiaojie Li, Rui Wang, Yunpeng Chen, Daquan Zhou</p><p><b>Upvotes:</b> 49</p><p><b>Summary:</b> Recent progress in text-to-image generation has greatly advanced visual fidelity and creativity, but it has also imposed higher demands on prompt complexity-particularly in encoding intricate spatial relationships. In such cases, achieving satisfactory results often requires multiple sampling attempts. To address this challenge, we introduce a novel method that strengthens the spatial understanding of current image generation models. We first construct the SpatialReward-Dataset with over 80k preference pairs. Building on this dataset, we build SpatialScore, a reward model designed to evaluate the accuracy of spatial relationships in text-to-image generation, achieving performance that even surpasses leading proprietary models on spatial evaluation. We further demonstrate that this reward model effectively enables online reinforcement learning for the complex spatial generation. Extensive experiments across multiple benchmarks show that our specialized reward model yields significant and consistent gains in spatial understanding for image generation.</p> + https://arxiv.org/abs/2602.24233 + Fri, 27 Feb 2026 17:59:57 +0000 - SimVLA: A Simple VLA Baseline for Robotic Manipulation - https://arxiv.org/abs/2602.18224 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.18224.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuankai Luo, Woping Chen, Tong Liang, Baiqiao Wang, Zhenguo Li</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Vision-Language-Action (VLA) models have emerged as a promising paradigm for general-purpose robotic manipulation, leveraging large-scale pre-training to achieve strong performance. The field has rapidly evolved with additional spatial priors and diverse architectural innovations. However, these advancements are often accompanied by varying training recipes and implementation details, which can make it challenging to disentangle the precise source of empirical gains. In this work, we introduce SimVLA, a streamlined baseline designed to establish a transparent reference point for VLA research. By strictly decoupling perception from control, using a standard vision-language backbone and a lightweight action head, and standardizing critical training dynamics, we demonstrate that a minimal design can achieve state-of-the-art performance. Despite having only 0.5B parameters, SimVLA outperforms multi-billion-parameter models on standard simulation benchmarks without robot pretraining. SimVLA also reaches on-par real-robot performance compared to pi0.5. Our results establish SimVLA as a robust, reproducible baseline that enables clear attribution of empirical gains to future architectural innovations. Website: https://frontierrobo.github.io/SimVLA</p> - https://arxiv.org/abs/2602.18224 - Fri, 20 Feb 2026 14:04:27 +0000 + Compositional Generalization Requires Linear, Orthogonal Representations in Vision Embedding Models + https://arxiv.org/abs/2602.24264 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.24264.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Arnas Uselis, Andrea Dittadi, Seong Joon Oh</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Compositional generalization, the ability to recognize familiar parts in novel contexts, is a defining property of intelligent systems. Although modern models are trained on massive datasets, they still cover only a tiny fraction of the combinatorial space of possible inputs, raising the question of what structure representations must have to support generalization to unseen combinations. We formalize three desiderata for compositional generalization under standard training (divisibility, transferability, stability) and show they impose necessary geometric constraints: representations must decompose linearly into per-concept components, and these components must be orthogonal across concepts. This provides theoretical grounding for the Linear Representation Hypothesis: the linear structure widely observed in neural representations is a necessary consequence of compositional generalization. We further derive dimension bounds linking the number of composable concepts to the embedding geometry. Empirically, we evaluate these predictions across modern vision models (CLIP, SigLIP, DINO) and find that representations exhibit partial linear factorization with low-rank, near-orthogonal per-concept factors, and that the degree of this structure correlates with compositional generalization on unseen combinations. As models continue to scale, these conditions predict the representational geometry they may converge to. Code is available at https://github.com/oshapio/necessary-compositionality.</p> + https://arxiv.org/abs/2602.24264 + Fri, 27 Feb 2026 18:32:31 +0000 - MEG-to-MEG Transfer Learning and Cross-Task Speech/Silence Detection with Limited Data - https://arxiv.org/abs/2602.18253 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.18253.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xabier de Zuazo, Vincenzo Verbeni, Eva Navas, Ibon Saratxaga, Mathieu Bourguignon, Nicola Molinaro</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Data-efficient neural decoding is a central challenge for speech brain-computer interfaces. We present the first demonstration of transfer learning and cross-task decoding for MEG-based speech models spanning perception and production. We pre-train a Conformer-based model on 50 hours of single-subject listening data and fine-tune on just 5 minutes per subject across 18 participants. Transfer learning yields consistent improvements, with in-task accuracy gains of 1-4% and larger cross-task gains of up to 5-6%. Not only does pre-training improve performance within each task, but it also enables reliable cross-task decoding between perception and production. Critically, models trained on speech production decode passive listening above chance, confirming that learned representations reflect shared neural processes rather than task-specific motor activity.</p> - https://arxiv.org/abs/2602.18253 - Fri, 20 Feb 2026 14:39:50 +0000 + Memory Caching: RNNs with Growing Memory + https://arxiv.org/abs/2602.24281 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.24281.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ali Behrouz, Zeman Li, Yuan Deng, Peilin Zhong, Meisam Razaviyayn, Vahab Mirrokni</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Transformers have been established as the de-facto backbones for most recent advances in sequence modeling, mainly due to their growing memory capacity that scales with the context length. While plausible for retrieval tasks, it causes quadratic complexity and so has motivated recent studies to explore viable subquadratic recurrent alternatives. Despite showing promising preliminary results in diverse domains, such recurrent architectures underperform Transformers in recall-intensive tasks, often attributed to their fixed-size memory. In this paper, we introduce Memory Caching (MC), a simple yet effective technique that enhances recurrent models by caching checkpoints of their memory states (a.k.a. hidden states). Memory Caching allows the effective memory capacity of RNNs to grow with sequence length, offering a flexible trade-off that interpolates between the fixed memory (i.e., O(L) complexity) of RNNs and the growing memory (i.e., O(L^2) complexity) of Transformers. We propose four variants of MC, including gated aggregation and sparse selective mechanisms, and discuss their implications on both linear and deep memory modules. Our experimental results on language modeling, and long-context understanding tasks show that MC enhances the performance of recurrent models, supporting its effectiveness. The results of in-context recall tasks indicate that while Transformers achieve the best accuracy, our MC variants show competitive performance, close the gap with Transformers, and performs better than state-of-the-art recurrent models.</p> + https://arxiv.org/abs/2602.24281 + Fri, 27 Feb 2026 18:53:41 +0000 - HyTRec: A Hybrid Temporal-Aware Attention Architecture for Long Behavior Sequential Recommendation - https://arxiv.org/abs/2602.18283 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.18283.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lei Xin, Yuhao Zheng, Ke Cheng, Changjiang Jiang, Zifan Zhang, Fanhu Zeng</p><p><b>Upvotes:</b> 53</p><p><b>Summary:</b> Modeling long sequences of user behaviors has emerged as a critical frontier in generative recommendation. However, existing solutions face a dilemma: linear attention mechanisms achieve efficiency at the cost of retrieval precision due to limited state capacity, while softmax attention suffers from prohibitive computational overhead. To address this challenge, we propose HyTRec, a model featuring a Hybrid Attention architecture that explicitly decouples long-term stable preferences from short-term intent spikes. By assigning massive historical sequences to a linear attention branch and reserving a specialized softmax attention branch for recent interactions, our approach restores precise retrieval capabilities within industrial-scale contexts involving ten thousand interactions. To mitigate the lag in capturing rapid interest drifts within the linear layers, we furthermore design Temporal-Aware Delta Network (TADN) to dynamically upweight fresh behavioral signals while effectively suppressing historical noise. Empirical results on industrial-scale datasets confirm the superiority that our model maintains linear inference speed and outperforms strong baselines, notably delivering over 8% improvement in Hit Rate for users with ultra-long sequences with great efficiency.</p> - https://arxiv.org/abs/2602.18283 - Fri, 20 Feb 2026 15:11:40 +0000 + CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation + https://arxiv.org/abs/2602.24286 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.24286.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weinan Dai, Hanlin Wu, Qiying Yu, Huan-ang Gao, Jiahao Li, Chengquan Jiang, Weiqiang Lou, Yufan Song, Hongli Yu, Jiaze Chen, Wei-Ying Ma, Ya-Qin Zhang, Jingjing Liu, Mingxuan Wang, Xin Liu, Hao Zhou</p><p><b>Upvotes:</b> 79</p><p><b>Summary:</b> GPU kernel optimization is fundamental to modern deep learning but remains a highly specialized task requiring deep hardware expertise. Despite strong performance in general programming, large language models (LLMs) remain uncompetitive with compiler-based systems such as torch.compile for CUDA kernel generation. Existing CUDA code generation approaches either rely on training-free refinement or fine-tune models within fixed multi-turn execution-feedback loops, but both paradigms fail to fundamentally improve the model's intrinsic CUDA optimization ability, resulting in limited performance gains. We present CUDA Agent, a large-scale agentic reinforcement learning system that develops CUDA kernel expertise through three components: a scalable data synthesis pipeline, a skill-augmented CUDA development environment with automated verification and profiling to provide reliable reward signals, and reinforcement learning algorithmic techniques enabling stable training. CUDA Agent achieves state-of-the-art results on KernelBench, delivering 100\%, 100\%, and 92\% faster rate over torch.compile on KernelBench Level-1, Level-2, and Level-3 splits, outperforming the strongest proprietary models such as Claude Opus 4.5 and Gemini 3 Pro by about 40\% on the hardest Level-3 setting.</p> + https://arxiv.org/abs/2602.24286 + Fri, 27 Feb 2026 18:58:05 +0000 - Decoding as Optimisation on the Probability Simplex: From Top-K to Top-P (Nucleus) to Best-of-K Samplers - https://arxiv.org/abs/2602.18292 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.18292.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiaotong Ji, Rasul Tutunov, Matthieu Zimmer, Haitham Bou-Ammar</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Decoding sits between a language model and everything we do with it, yet it is still treated as a heuristic knob-tuning exercise. We argue decoding should be understood as a principled optimisation layer: at each token, we solve a regularised problem over the probability simplex that trades off model score against structural preferences and constraints. This single template recovers greedy decoding, Softmax sampling, Top-K, Top-P, and Sparsemax-style sparsity as special cases, and explains their common structure through optimality conditions. More importantly, the framework makes it easy to invent new decoders without folklore. We demonstrate this by designing Best-of-K (BoK), a KL-anchored coverage objective aimed at multi-sample pipelines (self-consistency, reranking, verifier selection). BoK targets the probability of covering good alternatives within a fixed K-sample budget and improves empirical performance. We show that such samples can improve accuracy by, for example, +18.6% for Qwen2.5-Math-7B on MATH500 at high sampling temperatures.</p> - https://arxiv.org/abs/2602.18292 - Fri, 20 Feb 2026 15:38:16 +0000 + Mode Seeking meets Mean Seeking for Fast Long Video Generation + https://arxiv.org/abs/2602.24289 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.24289.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shengqu Cai, Weili Nie, Chao Liu, Julius Berner, Lvmin Zhang, Nanye Ma, Hansheng Chen, Maneesh Agrawala, Leonidas Guibas, Gordon Wetzstein, Arash Vahdat</p><p><b>Upvotes:</b> 38</p><p><b>Summary:</b> Scaling video generation from seconds to minutes faces a critical bottleneck: while short-video data is abundant and high-fidelity, coherent long-form data is scarce and limited to narrow domains. To address this, we propose a training paradigm where Mode Seeking meets Mean Seeking, decoupling local fidelity from long-term coherence based on a unified representation via a Decoupled Diffusion Transformer. Our approach utilizes a global Flow Matching head trained via supervised learning on long videos to capture narrative structure, while simultaneously employing a local Distribution Matching head that aligns sliding windows to a frozen short-video teacher via a mode-seeking reverse-KL divergence. This strategy enables the synthesis of minute-scale videos that learns long-range coherence and motions from limited long videos via supervised flow matching, while inheriting local realism by aligning every sliding-window segment of the student to a frozen short-video teacher, resulting in a few-step fast long video generator. Evaluations show that our method effectively closes the fidelity-horizon gap by jointly improving local sharpness, motion and long-range consistency. Project website: https://primecai.github.io/mmm/.</p> + https://arxiv.org/abs/2602.24289 + Fri, 27 Feb 2026 18:59:02 +0000 - On the "Induction Bias" in Sequence Models - https://arxiv.org/abs/2602.18333 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.18333.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> M. Reza Ebrahimi, Michaël Defferrard, Sunny Panchal, Roland Memisevic</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Despite the remarkable practical success of transformer-based language models, recent work has raised concerns about their ability to perform state tracking. In particular, a growing body of literature has shown this limitation primarily through failures in out-of-distribution (OOD) generalization, such as length extrapolation. In this work, we shift attention to the in-distribution implications of these limitations. We conduct a large-scale experimental study of the data efficiency of transformers and recurrent neural networks (RNNs) across multiple supervision regimes. We find that the amount of training data required by transformers grows much more rapidly with state-space size and sequence length than for RNNs. Furthermore, we analyze the extent to which learned state-tracking mechanisms are shared across different sequence lengths. We show that transformers exhibit negligible or even detrimental weight sharing across lengths, indicating that they learn length-specific solutions in isolation. In contrast, recurrent models exhibit effective amortized learning by sharing weights across lengths, allowing data from one sequence length to improve performance on others. Together, these results demonstrate that state tracking remains a fundamental challenge for transformers, even when training and evaluation distributions match.</p> - https://arxiv.org/abs/2602.18333 - Fri, 20 Feb 2026 16:39:07 +0000 + DreamWorld: Unified World Modeling in Video Generation + https://arxiv.org/abs/2603.00466 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.00466.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Boming Tan, Xiangdong Zhang, Ning Liao, Yuqing Zhang, Shaofeng Zhang, Xue Yang, Qi Fan, Yanyong Zhang</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Despite impressive progress in video generation, existing models remain limited to surface-level plausibility, lacking a coherent and unified understanding of the world. Prior approaches typically incorporate only a single form of world-related knowledge or rely on rigid alignment strategies to introduce additional knowledge. However, aligning the single world knowledge is insufficient to constitute a world model that requires jointly modeling multiple heterogeneous dimensions (e.g., physical commonsense, 3D and temporal consistency). To address this limitation, we introduce DreamWorld, a unified framework that integrates complementary world knowledge into video generators via a Joint World Modeling Paradigm, jointly predicting video pixels and features from foundation models to capture temporal dynamics, spatial geometry, and semantic consistency. However, naively optimizing these heterogeneous objectives can lead to visual instability and temporal flickering. To mitigate this issue, we propose Consistent Constraint Annealing (CCA) to progressively regulate world-level constraints during training, and Multi-Source Inner-Guidance to enforce learned world priors at inference. Extensive evaluations show that DreamWorld improves world consistency, outperforming Wan2.1 by 2.26 points on VBench. Code will be made publicly available at https://github.com/ABU121111/DreamWorld{mypink{Github}}.</p> + https://arxiv.org/abs/2603.00466 + Sat, 28 Feb 2026 05:02:39 +0000 - Generated Reality: Human-centric World Simulation using Interactive Video Generation with Hand and Camera Control - https://arxiv.org/abs/2602.18422 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.18422.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Linxi Xie, Lisong C. Sun, Ashley Neall, Tong Wu, Shengqu Cai, Gordon Wetzstein</p><p><b>Upvotes:</b> 30</p><p><b>Summary:</b> Extended reality (XR) demands generative models that respond to users' tracked real-world motion, yet current video world models accept only coarse control signals such as text or keyboard input, limiting their utility for embodied interaction. We introduce a human-centric video world model that is conditioned on both tracked head pose and joint-level hand poses. For this purpose, we evaluate existing diffusion transformer conditioning strategies and propose an effective mechanism for 3D head and hand control, enabling dexterous hand--object interactions. We train a bidirectional video diffusion model teacher using this strategy and distill it into a causal, interactive system that generates egocentric virtual environments. We evaluate this generated reality system with human subjects and demonstrate improved task performance as well as a significantly higher level of perceived amount of control over the performed actions compared with relevant baselines.</p> - https://arxiv.org/abs/2602.18422 - Fri, 20 Feb 2026 18:45:29 +0000 + Spectral Condition for μP under Width-Depth Scaling + https://arxiv.org/abs/2603.00541 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.00541.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chenyu Zheng, Rongzhen Wang, Xinyu Zhang, Chongxuan Li</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Generative foundation models are increasingly scaled in both width and depth, posing significant challenges for stable feature learning and reliable hyperparameter (HP) transfer across model sizes. While maximal update parameterization (μP) has provided a principled solution to both problems for width scaling, existing extensions to the joint width-depth scaling regime remain fragmented, architecture- and optimizer-specific, and often rely on technically involved theories. In this work, we develop a simple and unified spectral framework for μP under joint width-depth scaling. Considering residual networks of varying block depths, we first introduce a spectral μP condition that precisely characterizes how the norms of weights and their per-step updates should scale with width and depth, unifying previously disparate μP formulations as special cases. Building on this condition, we then derive a general recipe for implementing μP across a broad class of optimizers by mapping the spectral constraints to concrete HP parameterizations. This approach not only recovers existing μP formulations (e.g., for SGD and AdamW) but also naturally extends to a wider range of optimizers. Finally, experiments on GPT-2 style language models demonstrate that the proposed spectral μP condition preserves stable feature learning and enables robust HP transfer under width-depth scaling.</p> + https://arxiv.org/abs/2603.00541 + Sat, 28 Feb 2026 08:38:50 +0000 - SARAH: Spatially Aware Real-time Agentic Humans - https://arxiv.org/abs/2602.18432 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.18432.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Evonne Ng, Siwei Zhang, Zhang Chen, Michael Zollhoefer, Alexander Richard</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> As embodied agents become central to VR, telepresence, and digital human applications, their motion must go beyond speech-aligned gestures: agents should turn toward users, respond to their movement, and maintain natural gaze. Current methods lack this spatial awareness. We close this gap with the first real-time, fully causal method for spatially-aware conversational motion, deployable on a streaming VR headset. Given a user's position and dyadic audio, our approach produces full-body motion that aligns gestures with speech while orienting the agent according to the user. Our architecture combines a causal transformer-based VAE with interleaved latent tokens for streaming inference and a flow matching model conditioned on user trajectory and audio. To support varying gaze preferences, we introduce a gaze scoring mechanism with classifier-free guidance to decouple learning from control: the model captures natural spatial alignment from data, while users can adjust eye contact intensity at inference time. On the Embody 3D dataset, our method achieves state-of-the-art motion quality at over 300 FPS -- 3x faster than non-causal baselines -- while capturing the subtle spatial dynamics of natural conversation. We validate our approach on a live VR system, bringing spatially-aware conversational agents to real-time deployment. Please see https://evonneng.github.io/sarah/ for details.</p> - https://arxiv.org/abs/2602.18432 - Fri, 20 Feb 2026 18:59:35 +0000 + CMI-RewardBench: Evaluating Music Reward Models with Compositional Multimodal Instruction + https://arxiv.org/abs/2603.00610 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.00610.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yinghao Ma, Haiwen Xia, Hewei Gao, Weixiong Chen, Yuxin Ye, Yuchen Yang, Sungkyun Chang, Mingshuo Ding, Yizhi Li, Ruibin Yuan, Simon Dixon, Emmanouil Benetos</p><p><b>Upvotes:</b> 32</p><p><b>Summary:</b> While music generation models have evolved to handle complex multimodal inputs mixing text, lyrics, and reference audio, evaluation mechanisms have lagged behind. In this paper, we bridge this critical gap by establishing a comprehensive ecosystem for music reward modeling under Compositional Multimodal Instruction (CMI), where the generated music may be conditioned on text descriptions, lyrics, and audio prompts. We first introduce CMI-Pref-Pseudo, a large-scale preference dataset comprising 110k pseudo-labeled samples, and CMI-Pref, a high-quality, human-annotated corpus tailored for fine-grained alignment tasks. To unify the evaluation landscape, we propose CMI-RewardBench, a unified benchmark that evaluates music reward models on heterogeneous samples across musicality, text-music alignment, and compositional instruction alignment. Leveraging these resources, we develop CMI reward models (CMI-RMs), a parameter-efficient reward model family capable of processing heterogeneous inputs. We evaluate their correlation with human judgments scores on musicality and alignment on CMI-Pref along with previous datasets. Further experiments demonstrate that CMI-RM not only correlates strongly with human judgments, but also enables effective inference-time scaling via top-k filtering. The necessary training data, benchmarks, and reward models are publicly available.</p> + https://arxiv.org/abs/2603.00610 + Sat, 28 Feb 2026 12:10:58 +0000 - Decoding ML Decision: An Agentic Reasoning Framework for Large-Scale Ranking System - https://arxiv.org/abs/2602.18640 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.18640.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Longfei Yun, Yihan Wu, Haoran Liu, Xiaoxuan Liu, Ziyun Xu, Yi Wang, Yang Xia, Pengfei Wang, Mingze Gao, Yunxiang Wang, Changfan Chen, Junfeng Pan</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Modern large-scale ranking systems operate within a sophisticated landscape of competing objectives, operational constraints, and evolving product requirements. Progress in this domain is increasingly bottlenecked by the engineering context constraint: the arduous process of translating ambiguous product intent into reasonable, executable, verifiable hypotheses, rather than by modeling techniques alone. We present GEARS (Generative Engine for Agentic Ranking Systems), a framework that reframes ranking optimization as an autonomous discovery process within a programmable experimentation environment. Rather than treating optimization as static model selection, GEARS leverages Specialized Agent Skills to encapsulate ranking expert knowledge into reusable reasoning capabilities, enabling operators to steer systems via high-level intent vibe personalization. Furthermore, to ensure production reliability, the framework incorporates validation hooks to enforce statistical robustness and filter out brittle policies that overfit short-term signals. Experimental validation across diverse product surfaces demonstrates that GEARS consistently identifies superior, near-Pareto-efficient policies by synergizing algorithmic signals with deep ranking context while maintaining rigorous deployment stability.</p> - https://arxiv.org/abs/2602.18640 - Fri, 20 Feb 2026 22:24:01 +0000 + InfoPO: Information-Driven Policy Optimization for User-Centric Agents + https://arxiv.org/abs/2603.00656 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.00656.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fanqi Kong, Jiayi Zhang, Mingyi Deng, Chenglin Wu, Yuyu Luo, Bang Liu</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Real-world user requests to LLM agents are often underspecified. Agents must interact to acquire missing information and make correct downstream decisions. However, current multi-turn GRPO-based methods often rely on trajectory-level reward computation, which leads to credit assignment problems and insufficient advantage signals within rollout groups. A feasible approach is to identify valuable interaction turns at a fine granularity to drive more targeted learning. To address this, we introduce InfoPO (Information-Driven Policy Optimization), which frames multi-turn interaction as a process of active uncertainty reduction and computes an information-gain reward that credits turns whose feedback measurably changes the agent's subsequent action distribution compared to a masked-feedback counterfactual. It then combines this signal with task outcomes via an adaptive variance-gated fusion to identify information importance while maintaining task-oriented goal direction. Across diverse tasks, including intent clarification, collaborative coding, and tool-augmented decision making, InfoPO consistently outperforms prompting and multi-turn RL baselines. It also demonstrates robustness under user simulator shifts and generalizes effectively to environment-interactive tasks. Overall, InfoPO provides a principled and scalable mechanism for optimizing complex agent-user collaboration. Code is available at https://github.com/kfq20/InfoPO.</p> + https://arxiv.org/abs/2603.00656 + Sat, 28 Feb 2026 13:58:14 +0000 - RoboCurate: Harnessing Diversity with Action-Verified Neural Trajectory for Robot Learning - https://arxiv.org/abs/2602.18742 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.18742.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Seungku Kim, Suhyeok Jang, Byungjun Yoon, Dongyoung Kim, John Won, Jinwoo Shin</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Synthetic data generated by video generative models has shown promise for robot learning as a scalable pipeline, but it often suffers from inconsistent action quality due to imperfectly generated videos. Recently, vision-language models (VLMs) have been leveraged to validate video quality, but they have limitations in distinguishing physically accurate videos and, even then, cannot directly evaluate the generated actions themselves. To tackle this issue, we introduce RoboCurate, a novel synthetic robot data generation framework that evaluates and filters the quality of annotated actions by comparing them with simulation replay. Specifically, RoboCurate replays the predicted actions in a simulator and assesses action quality by measuring the consistency of motion between the simulator rollout and the generated video. In addition, we unlock observation diversity beyond the available dataset via image-to-image editing and apply action-preserving video-to-video transfer to further augment appearance. We observe RoboCurate's generated data yield substantial relative improvements in success rates compared to using real data only, achieving +70.1% on GR-1 Tabletop (300 demos), +16.1% on DexMimicGen in the pre-training setup, and +179.9% in the challenging real-world ALLEX humanoid dexterous manipulation setting.</p> - https://arxiv.org/abs/2602.18742 - Sat, 21 Feb 2026 07:33:24 +0000 + STMI: Segmentation-Guided Token Modulation with Cross-Modal Hypergraph Interaction for Multi-Modal Object Re-Identification + https://arxiv.org/abs/2603.00695 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.00695.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xingguo Xu, Zhanyu Liu, Weixiang Zhou, Yuansheng Gao, Junjie Cao, Yuhao Wang, Jixiang Luo, Dell Zhang</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Multi-modal object Re-Identification (ReID) aims to exploit complementary information from different modalities to retrieve specific objects. However, existing methods often rely on hard token filtering or simple fusion strategies, which can lead to the loss of discriminative cues and increased background interference. To address these challenges, we propose STMI, a novel multi-modal learning framework consisting of three key components: (1) Segmentation-Guided Feature Modulation (SFM) module leverages SAM-generated masks to enhance foreground representations and suppress background noise through learnable attention modulation; (2) Semantic Token Reallocation (STR) module employs learnable query tokens and an adaptive reallocation mechanism to extract compact and informative representations without discarding any tokens; (3) Cross-Modal Hypergraph Interaction (CHI) module constructs a unified hypergraph across modalities to capture high-order semantic relationships. Extensive experiments on public benchmarks (i.e., RGBNT201, RGBNT100, and MSVR310) demonstrate the effectiveness and robustness of our proposed STMI framework in multi-modal ReID scenarios.</p> + https://arxiv.org/abs/2603.00695 + Sat, 28 Feb 2026 15:07:10 +0000 - DREAM: Deep Research Evaluation with Agentic Metrics - https://arxiv.org/abs/2602.18940 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.18940.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Elad Ben Avraham, Changhao Li, Ron Dorfman, Roy Ganz, Oren Nuriel, Amir Dudai, Aviad Aberdam, Noah Flynn, Elman Mansimov, Adi Kalyanpur, Ron Litman</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Deep Research Agents generate analyst-grade reports, yet evaluating them remains challenging due to the absence of a single ground truth and the multidimensional nature of research quality. Recent benchmarks propose distinct methodologies, yet they suffer from the Mirage of Synthesis, where strong surface-level fluency and citation alignment can obscure underlying factual and reasoning defects. We characterize this gap by introducing a taxonomy across four verticals that exposes a critical capability mismatch: static evaluators inherently lack the tool-use capabilities required to assess temporal validity and factual correctness. To address this, we propose DREAM (Deep Research Evaluation with Agentic Metrics), a framework that instantiates the principle of capability parity by making evaluation itself agentic. DREAM structures assessment through an evaluation protocol combining query-agnostic metrics with adaptive metrics generated by a tool-calling agent, enabling temporally aware coverage, grounded verification, and systematic reasoning probes. Controlled evaluations demonstrate DREAM is significantly more sensitive to factual and temporal decay than existing benchmarks, offering a scalable, reference-free evaluation paradigm.</p> - https://arxiv.org/abs/2602.18940 - Sat, 21 Feb 2026 19:14:31 +0000 + Qwen3-Coder-Next Technical Report + https://arxiv.org/abs/2603.00729 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.00729.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ruisheng Cao, Mouxiang Chen, Jiawei Chen, Zeyu Cui, Yunlong Feng, Binyuan Hui, Yuheng Jing, Kaixin Li, Mingze Li, Junyang Lin, Zeyao Ma, Kashun Shum, Xuwu Wang, Jinxi Wei, Jiaxi Yang, Jiajun Zhang, Lei Zhang, Zongmeng Zhang, Wenting Zhao, Fan Zhou</p><p><b>Upvotes:</b> 39</p><p><b>Summary:</b> We present Qwen3-Coder-Next, an open-weight language model specialized for coding agents. Qwen3-Coder-Next is an 80-billion-parameter model that activates only 3 billion parameters during inference, enabling strong coding capability with efficient inference. In this work, we explore how far strong training recipes can push the capability limits of models with small parameter footprints. To achieve this, we perform agentic training through large-scale synthesis of verifiable coding tasks paired with executable environments, allowing learning directly from environment feedback via mid-training and reinforcement learning. Across agent-centric benchmarks including SWE-Bench and Terminal-Bench, Qwen3-Coder-Next achieves competitive performance relative to its active parameter count. We release both base and instruction-tuned open-weight versions to support research and real-world coding agent development.</p> + https://arxiv.org/abs/2603.00729 + Sat, 28 Feb 2026 16:25:04 +0000 - SeaCache: Spectral-Evolution-Aware Cache for Accelerating Diffusion Models - https://arxiv.org/abs/2602.18993 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.18993.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiwoo Chung, Sangeek Hyun, MinKyu Lee, Byeongju Han, Geonho Cha, Dongyoon Wee, Youngjun Hong, Jae-Pil Heo</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Diffusion models are a strong backbone for visual generation, but their inherently sequential denoising process leads to slow inference. Previous methods accelerate sampling by caching and reusing intermediate outputs based on feature distances between adjacent timesteps. However, existing caching strategies typically rely on raw feature differences that entangle content and noise. This design overlooks spectral evolution, where low-frequency structure appears early and high-frequency detail is refined later. We introduce Spectral-Evolution-Aware Cache (SeaCache), a training-free cache schedule that bases reuse decisions on a spectrally aligned representation. Through theoretical and empirical analysis, we derive a Spectral-Evolution-Aware (SEA) filter that preserves content-relevant components while suppressing noise. Employing SEA-filtered input features to estimate redundancy leads to dynamic schedules that adapt to content while respecting the spectral priors underlying the diffusion model. Extensive experiments on diverse visual generative models and the baselines show that SeaCache achieves state-of-the-art latency-quality trade-offs.</p> - https://arxiv.org/abs/2602.18993 - Sun, 22 Feb 2026 00:48:03 +0000 + CHIMERA: Compact Synthetic Data for Generalizable LLM Reasoning + https://arxiv.org/abs/2603.00889 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.00889.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xinyu Zhu, Yihao Feng, Yanchao Sun, Xianzhi Du, Pingzhi Li, Olli Saarikivi, Yun Zhu, Yu Meng</p><p><b>Upvotes:</b> 43</p><p><b>Summary:</b> Large Language Models (LLMs) have recently exhibited remarkable reasoning capabilities, largely enabled by supervised fine-tuning (SFT)- and reinforcement learning (RL)-based post-training on high-quality reasoning data. However, reproducing and extending these capabilities in open and scalable settings is hindered by three fundamental data-centric challenges: (1) the cold-start problem, arising from the lack of seed datasets with detailed, long Chain-of-Thought (CoT) trajectories needed to initialize reasoning policies; (2) limited domain coverage, as most existing open-source reasoning datasets are concentrated in mathematics, with limited coverage of broader scientific disciplines; and (3) the annotation bottleneck, where the difficulty of frontier-level reasoning tasks makes reliable human annotation prohibitively expensive or infeasible. To address these challenges, we introduce CHIMERA, a compact synthetic reasoning dataset comprising 9K samples for generalizable cross-domain reasoning. CHIMERA is constructed with three key properties: (1) it provides rich, long CoT reasoning trajectories synthesized by state-of-the-art reasoning models; (2) it has broad and structured coverage, spanning 8 major scientific disciplines and over 1K fine-grained topics organized via a model-generated hierarchical taxonomy; and (3) it employs a fully automated, scalable evaluation pipeline that uses strong reasoning models to cross-validate both problem validity and answer correctness. We use CHIMERA to post-train a 4B Qwen3 model. Despite the dataset's modest size, the resulting model achieves strong performance on a suite of challenging reasoning benchmarks, including GPQA-Diamond, AIME 24/25/26, HMMT 25, and Humanity's Last Exam, approaching or matching the reasoning performance of substantially larger models such as DeepSeek-R1 and Qwen3-235B.</p> + https://arxiv.org/abs/2603.00889 + Sun, 01 Mar 2026 03:23:41 +0000 - Learning Cross-View Object Correspondence via Cycle-Consistent Mask Prediction - https://arxiv.org/abs/2602.18996 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.18996.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shannan Yan, Leqi Zheng, Keyu Lv, Jingchen Ni, Hongyang Wei, Jiajun Zhang, Guangting Wang, Jing Lyu, Chun Yuan, Fengyun Rao</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> We study the task of establishing object-level visual correspondence across different viewpoints in videos, focusing on the challenging egocentric-to-exocentric and exocentric-to-egocentric scenarios. We propose a simple yet effective framework based on conditional binary segmentation, where an object query mask is encoded into a latent representation to guide the localization of the corresponding object in a target video. To encourage robust, view-invariant representations, we introduce a cycle-consistency training objective: the predicted mask in the target view is projected back to the source view to reconstruct the original query mask. This bidirectional constraint provides a strong self-supervisory signal without requiring ground-truth annotations and enables test-time training (TTT) at inference. Experiments on the Ego-Exo4D and HANDAL-X benchmarks demonstrate the effectiveness of our optimization objective and TTT strategy, achieving state-of-the-art performance. The code is available at https://github.com/shannany0606/CCMP.</p> - https://arxiv.org/abs/2602.18996 - Sun, 22 Feb 2026 00:53:03 +0000 + VGGT-Det: Mining VGGT Internal Priors for Sensor-Geometry-Free Multi-View Indoor 3D Object Detection + https://arxiv.org/abs/2603.00912 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.00912.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yang Cao, Feize Wu, Dave Zhenyu Chen, Yingji Zhong, Lanqing Hong, Dan Xu</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> Current multi-view indoor 3D object detectors rely on sensor geometry that is costly to obtain (i.e., precisely calibrated multi-view camera poses) to fuse multi-view information into a global scene representation, limiting deployment in real-world scenes. We target a more practical setting: Sensor-Geometry-Free (SG-Free) multi-view indoor 3D object detection, where there are no sensor-provided geometric inputs (multi-view poses or depth). Recent Visual Geometry Grounded Transformer (VGGT) shows that strong 3D cues can be inferred directly from images. Building on this insight, we present VGGT-Det, the first framework tailored for SG-Free multi-view indoor 3D object detection. Rather than merely consuming VGGT predictions, our method integrates VGGT encoder into a transformer-based pipeline. To effectively leverage both the semantic and geometric priors from inside VGGT, we introduce two novel key components: (i) Attention-Guided Query Generation (AG): exploits VGGT attention maps as semantic priors to initialize object queries, improving localization by focusing on object regions while preserving global spatial structure; (ii) Query-Driven Feature Aggregation (QD): a learnable See-Query interacts with object queries to 'see' what they need, and then dynamically aggregates multi-level geometric features across VGGT layers that progressively lift 2D features into 3D. Experiments show that VGGT-Det significantly surpasses the best-performing method in the SG-Free setting by 4.4 and 8.6 mAP@0.25 on ScanNet and ARKitScenes, respectively. Ablation study shows that VGGT's internally learned semantic and geometric priors can be effectively leveraged by our AG and QD.</p> + https://arxiv.org/abs/2603.00912 + Sun, 01 Mar 2026 04:25:52 +0000 - Benchmark Test-Time Scaling of General LLM Agents - https://arxiv.org/abs/2602.18998 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.18998.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiaochuan Li, Ryan Ming, Pranav Setlur, Abhijay Paladugu, Andy Tang, Hao Kang, Shuai Shao, Rong Jin, Chenyan Xiong</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> LLM agents are increasingly expected to function as general-purpose systems capable of resolving open-ended user requests. While existing benchmarks focus on domain-aware environments for developing specialized agents, evaluating general-purpose agents requires more realistic settings that challenge them to operate across multiple skills and tools within a unified environment. We introduce General AgentBench, a benchmark that provides such a unified framework for evaluating general LLM agents across search, coding, reasoning, and tool-use domains. Using General AgentBench, we systematically study test-time scaling behaviors under sequential scaling (iterative interaction) and parallel scaling (sampling multiple trajectories). Evaluation of ten leading LLM agents reveals a substantial performance degradation when moving from domain-specific evaluations to this general-agent setting. Moreover, we find that neither scaling methodology yields effective performance improvements in practice, due to two fundamental limitations: context ceiling in sequential scaling and verification gap in parallel scaling. Code is publicly available at https://github.com/cxcscmu/General-AgentBench.</p> - https://arxiv.org/abs/2602.18998 - Sun, 22 Feb 2026 01:08:02 +0000 + LLaDA-o: An Effective and Length-Adaptive Omni Diffusion Model + https://arxiv.org/abs/2603.01068 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.01068.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zebin You, Xiaolu Zhang, Jun Zhou, Chongxuan Li, Ji-Rong Wen</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> We present LLaDA-o, an effective and length-adaptive omni diffusion model for multimodal understanding and generation. LLaDA-o is built on a Mixture of Diffusion (MoD) framework that decouples discrete masked diffusion for text understanding and continuous diffusion for visual generation, while coupling them through a shared, simple, and efficient attention backbone that reduces redundant computation for fixed conditions. Building on MoD, we further introduce a data-centric length adaptation strategy that enables flexible-length decoding in multimodal settings without architectural changes. Extensive experiments show that LLaDA-o achieves state-of-the-art performance among omni-diffusion models on multimodal understanding and generation benchmarks, and reaches 87.04 on DPG-Bench for text-to-image generation, supporting the effectiveness of unified omni diffusion modeling. Code is available at https://github.com/ML-GSAI/LLaDA-o.</p> + https://arxiv.org/abs/2603.01068 + Sun, 01 Mar 2026 12:05:06 +0000 - K-Search: LLM Kernel Generation via Co-Evolving Intrinsic World Model - https://arxiv.org/abs/2602.19128 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.19128.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shiyi Cao, Ziming Mao, Joseph E. Gonzalez, Ion Stoica</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Optimizing GPU kernels is critical for efficient modern machine learning systems yet remains challenging due to the complex interplay of design factors and rapid hardware evolution. Existing automated approaches typically treat Large Language Models (LLMs) merely as stochastic code generators within heuristic-guided evolutionary loops. These methods often struggle with complex kernels requiring coordinated, multi-step structural transformations, as they lack explicit planning capabilities and frequently discard promising strategies due to inefficient or incorrect intermediate implementations. To address this, we propose Search via Co-Evolving World Model and build K-Search based on this method. By replacing static search heuristics with a co-evolving world model, our framework leverages LLMs' prior domain knowledge to guide the search, actively exploring the optimization space. This approach explicitly decouples high-level algorithmic planning from low-level program instantiation, enabling the system to navigate non-monotonic optimization paths while remaining resilient to temporary implementation defects. We evaluate K-Search on diverse, complex kernels from FlashInfer, including GQA, MLA, and MoE kernels. Our results show that K-Search significantly outperforms state-of-the-art evolutionary search methods, achieving an average 2.10x improvement and up to a 14.3x gain on complex MoE kernels. On the GPUMode TriMul task, K-Search achieves state-of-the-art performance on H100, reaching 1030us and surpassing both prior evolution and human-designed solutions.</p> - https://arxiv.org/abs/2602.19128 - Sun, 22 Feb 2026 11:06:22 +0000 + Unified Vision-Language Modeling via Concept Space Alignment + https://arxiv.org/abs/2603.01096 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.01096.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yifu Qiu, Paul-Ambroise Duquenne, Holger Schwenk</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> We introduce V-SONAR, a vision-language embedding space extended from the text-only embedding space SONAR (Omnilingual Embeddings Team et al., 2026), which supports 1500 text languages and 177 speech languages. To construct V-SONAR, we propose a post-hoc alignment pipeline that maps the representations of an existing vision encoder into the SONAR space. We thoroughly evaluate V-SONAR and show that its embeddings achieve competitive performance on text-to-video retrieval. Equipped with the OMNISONAR text decoder, V-SONAR further surpasses state-of-the-art vision-language models on video captioning tasks, including DREAM-1K (BLEU 23.9 vs. 19.6) and PE-VIDEO (BLEU 39.0 vs. 30.0). Leveraging V-SONAR, we first demonstrate that the Large Concept Model (LCM; LCM team et al. 2024) operating in SONAR and trained with English text only, can perform both single- and multi-visual concept understanding in a zero-shot manner. Finally, we introduce V-LCM, which extends the LCM with vision-language instruction tuning. V-LCM encodes vision and language inputs into an unified sequence of latent embeddings via V-SONAR and SONAR, and it is trained with the same latent diffusion objective for next-embedding prediction as in LCM's text-only pre-training. Experiments on a large-scale multilingual and -modal instruction-tuning data mixture highlight the potential of V-LCM: V-LCM matches state-of-the-art vision-language models on tasks covering image/video captioning and question answering, while significantly outperforming them across 61 rich- to low-resource languages out of all 62 tested languages.</p> + https://arxiv.org/abs/2603.01096 + Sun, 01 Mar 2026 13:22:44 +0000 - JavisDiT++: Unified Modeling and Optimization for Joint Audio-Video Generation - https://arxiv.org/abs/2602.19163 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.19163.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kai Liu, Yanhao Zheng, Kai Wang, Shengqiong Wu, Rongjunchen Zhang, Jiebo Luo, Dimitrios Hatzinakos, Ziwei Liu, Hao Fei, Tat-Seng Chua</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> AIGC has rapidly expanded from text-to-image generation toward high-quality multimodal synthesis across video and audio. Within this context, joint audio-video generation (JAVG) has emerged as a fundamental task that produces synchronized and semantically aligned sound and vision from textual descriptions. However, compared with advanced commercial models such as Veo3, existing open-source methods still suffer from limitations in generation quality, temporal synchrony, and alignment with human preferences. To bridge the gap, this paper presents JavisDiT++, a concise yet powerful framework for unified modeling and optimization of JAVG. First, we introduce a modality-specific mixture-of-experts (MS-MoE) design that enables cross-modal interaction efficacy while enhancing single-modal generation quality. Then, we propose a temporal-aligned RoPE (TA-RoPE) strategy to achieve explicit, frame-level synchronization between audio and video tokens. Besides, we develop an audio-video direct preference optimization (AV-DPO) method to align model outputs with human preference across quality, consistency, and synchrony dimensions. Built upon Wan2.1-1.3B-T2V, our model achieves state-of-the-art performance merely with around 1M public training entries, significantly outperforming prior approaches in both qualitative and quantitative evaluations. Comprehensive ablation studies have been conducted to validate the effectiveness of our proposed modules. All the code, model, and dataset are released at https://JavisVerse.github.io/JavisDiT2-page.</p> - https://arxiv.org/abs/2602.19163 - Sun, 22 Feb 2026 12:44:28 +0000 + Learn Hard Problems During RL with Reference Guided Fine-tuning + https://arxiv.org/abs/2603.01223 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.01223.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yangzhen Wu, Shanda Li, Zixin Wen, Xin Zhou, Ameet Talwalkar, Yiming Yang, Wenhao Huang, Tianle Cai</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Reinforcement learning (RL) for mathematical reasoning can suffer from reward sparsity: for challenging problems, LLM fails to sample any correct trajectories, preventing RL from receiving meaningful positive feedback. At the same time, there often exist human-written reference solutions along with the problem (e.g., problems from AoPS), but directly fine-tuning on these solutions offers no benefit because models often cannot imitate human proofs that lie outside their own reasoning distribution. We introduce Reference-Guided Fine-Tuning (ReGFT), a simple and effective method that utilizes human-written reference solutions to synthesize positive trajectories on hard problems and train on them before RL. For each problem, we provide the model with a partial reference solution and let it generate its own reasoning trace, ensuring the resulting trajectories remain in the model's reasoning space while still benefiting from reference guidance. Fine-tuning on these reference-guided trajectories increases the number of solvable problems and produces a checkpoint that receives more positive rewards during RL. Across three benchmarks (AIME24, AIME25, BeyondAIME), ReGFT consistently improves supervised accuracy, accelerates DAPO training, and raises the final performance plateau of RL. Our results show that ReGFT effectively overcomes reward sparsity and unlocks stronger RL-based mathematical reasoning.</p> + https://arxiv.org/abs/2603.01223 + Sun, 01 Mar 2026 18:41:28 +0000 - TOPReward: Token Probabilities as Hidden Zero-Shot Rewards for Robotics - https://arxiv.org/abs/2602.19313 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.19313.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shirui Chen, Cole Harrison, Ying-Chun Lee, Angela Jin Yang, Zhongzheng Ren, Lillian J. Ratliff, Jiafei Duan, Dieter Fox, Ranjay Krishna</p><p><b>Upvotes:</b> 23</p><p><b>Summary:</b> While Vision-Language-Action (VLA) models have seen rapid progress in pretraining, their advancement in Reinforcement Learning (RL) remains hampered by low sample efficiency and sparse rewards in real-world settings. Developing generalizable process reward models is essential for providing the fine-grained feedback necessary to bridge this gap, yet existing temporal value functions often fail to generalize beyond their training domains. We introduce TOPReward, a novel, probabilistically grounded temporal value function that leverages the latent world knowledge of pretrained video Vision-Language Models (VLMs) to estimate robotic task progress. Unlike prior methods that prompt VLMs to directly output progress values, which are prone to numerical misrepresentation, TOPReward extracts task progress directly from the VLM's internal token logits. In zero-shot evaluations across 130+ distinct real-world tasks and multiple robot platforms (e.g., Franka, YAM, SO-100/101), TOPReward achieves 0.947 mean Value-Order Correlation (VOC) on Qwen3-VL, dramatically outperforming the state-of-the-art GVL baseline which achieves near-zero correlation on the same open-source model. We further demonstrate that TOPReward serves as a versatile tool for downstream applications, including success detection and reward-aligned behavior cloning.</p> - https://arxiv.org/abs/2602.19313 - Sun, 22 Feb 2026 19:25:48 +0000 + AgilePruner: An Empirical Study of Attention and Diversity for Adaptive Visual Token Pruning in Large Vision-Language Models + https://arxiv.org/abs/2603.01236 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.01236.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Changwoo Baek, Jouwon Song, Sohyeon Kim, Kyeongbo Kong</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Large Vision-Language Models (LVLMs) have adopted visual token pruning strategies to mitigate substantial computational overhead incurred by extensive visual token sequences. While prior works primarily focus on either attention-based or diversity-based pruning methods, in-depth analysis of these approaches' characteristics and limitations remains largely unexplored. In this work, we conduct thorough empirical analysis using effective rank (erank) as a measure of feature diversity and attention score entropy to investigate visual token processing mechanisms and analyze the strengths and weaknesses of each approach. Our analysis reveals two insights: (1) Our erank-based quantitative analysis shows that many diversity-oriented pruning methods preserve substantially less feature diversity than intended; moreover, analysis using the CHAIR dataset reveals that the diversity they do retain is closely tied to increased hallucination frequency compared to attention-based pruning. (2) We further observe that attention-based approaches are more effective on simple images where visual evidence is concentrated, while diversity-based methods better handle complex images with distributed features. Building on these empirical insights, we show that incorporating image-aware adjustments into existing hybrid pruning strategies consistently improves their performance. We also provide a minimal instantiation of our empirical findings through a simple adaptive pruning mechanism, which achieves strong and reliable performance across standard benchmarks as well as hallucination-specific evaluations. Our project page available at https://cvsp-lab.github.io/AgilePruner.</p> + https://arxiv.org/abs/2603.01236 + Sun, 01 Mar 2026 19:14:39 +0000 - Anatomy of Agentic Memory: Taxonomy and Empirical Analysis of Evaluation and System Limitations - https://arxiv.org/abs/2602.19320 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.19320.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dongming Jiang, Yi Li, Songtao Wei, Jinxin Yang, Ayushi Kishore, Alysa Zhao, Dingyi Kang, Xu Hu, Feng Chen, Qiannan Li, Bingzhe Li</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Agentic memory systems enable large language model (LLM) agents to maintain state across long interactions, supporting long-horizon reasoning and personalization beyond fixed context windows. Despite rapid architectural development, the empirical foundations of these systems remain fragile: existing benchmarks are often underscaled, evaluation metrics are misaligned with semantic utility, performance varies significantly across backbone models, and system-level costs are frequently overlooked. This survey presents a structured analysis of agentic memory from both architectural and system perspectives. We first introduce a concise taxonomy of MAG systems based on four memory structures. Then, we analyze key pain points limiting current systems, including benchmark saturation effects, metric validity and judge sensitivity, backbone-dependent accuracy, and the latency and throughput overhead introduced by memory maintenance. By connecting the memory structure to empirical limitations, this survey clarifies why current agentic memory systems often underperform their theoretical promise and outlines directions for more reliable evaluation and scalable system design.</p> - https://arxiv.org/abs/2602.19320 - Sun, 22 Feb 2026 19:50:01 +0000 + Spectral Attention Steering for Prompt Highlighting + https://arxiv.org/abs/2603.01281 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.01281.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weixian Waylon Li, Yuchen Niu, Yongxin Yang, Keshuang Li, Tiejun Ma, Shay B. Cohen</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Attention steering is an important technique for controlling model focus, enabling capabilities such as prompt highlighting, where the model prioritises user-specified text. However, existing attention steering methods require explicit storage of the full attention matrix, making them incompatible with memory-efficient implementations like FlashAttention. We introduce Spectral Editing Key Amplification (SEKA), a training-free steering method that tackles this by directly editing key embeddings before attention computation. SEKA uses spectral decomposition to steer key embeddings towards latent directions that amplify attention scores for certain tokens. We extend this to Adaptive SEKA (AdaSEKA), a query-adaptive variant that uses a training-free routing mechanism to dynamically combine multiple expert subspaces based on the prompt's semantic intent. Our experiments show both methods significantly outperform strong baselines on standard steering benchmarks while adding much lower latency and memory overhead, in compatibility with optimised attention.</p> + https://arxiv.org/abs/2603.01281 + Sun, 01 Mar 2026 21:35:09 +0000 - Hepato-LLaVA: An Expert MLLM with Sparse Topo-Pack Attention for Hepatocellular Pathology Analysis on Whole Slide Images - https://arxiv.org/abs/2602.19424 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.19424.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuxuan Yang, Zhonghao Yan, Yi Zhang, Bo Yun, Muxi Diao, Guowei Zhao, Kongming Liang, Wenbin Li, Zhanyu Ma</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Hepatocellular Carcinoma diagnosis relies heavily on the interpretation of gigapixel Whole Slide Images. However, current computational approaches are constrained by fixed-resolution processing mechanisms and inefficient feature aggregation, which inevitably lead to either severe information loss or high feature redundancy. To address these challenges, we propose Hepato-LLaVA, a specialized Multi-modal Large Language Model designed for fine-grained hepatocellular pathology analysis. We introduce a novel Sparse Topo-Pack Attention mechanism that explicitly models 2D tissue topology. This mechanism effectively aggregates local diagnostic evidence into semantic summary tokens while preserving global context. Furthermore, to overcome the lack of multi-scale data, we present HepatoPathoVQA, a clinically grounded dataset comprising 33K hierarchically structured question-answer pairs validated by expert pathologists. Our experiments demonstrate that Hepato-LLaVA achieves state-of-the-art performance on HCC diagnosis and captioning tasks, significantly outperforming existing methods. Our code and implementation details are available at https://pris-cv.github.io/Hepto-LLaVA/.</p> - https://arxiv.org/abs/2602.19424 - Mon, 23 Feb 2026 01:43:32 +0000 + When Does RL Help Medical VLMs? Disentangling Vision, SFT, and RL Gains + https://arxiv.org/abs/2603.01301 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.01301.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ahmadreza Jeddi, Kimia Shaban, Negin Baghbanzadeh, Natasha Sharan, Abhishek Moturu, Elham Dolatabadi, Babak Taati</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Reinforcement learning (RL) is increasingly used to post-train medical Vision-Language Models (VLMs), yet it remains unclear whether RL improves medical visual reasoning or mainly sharpens behaviors already induced by supervised fine-tuning (SFT). We present a controlled study that disentangles these effects along three axes: vision, SFT, and RL. Using MedMNIST as a multi-modality testbed, we probe visual perception by benchmarking VLM vision towers against vision-only baselines, quantify reasoning support and sampling efficiency via Accuracy@1 versus Pass@K, and evaluate when RL closes the support gap and how gains transfer across modalities. We find that RL is most effective when the model already has non-trivial support (high Pass@K): it primarily sharpens the output distribution, improving Acc@1 and sampling efficiency, while SFT expands support and makes RL effective. Based on these findings, we propose a boundary-aware recipe and instantiate it by RL post-training an OctoMed-initialized model on a small, balanced subset of PMC multiple-choice VQA, achieving strong average performance across six medical VQA benchmarks.</p> + https://arxiv.org/abs/2603.01301 + Sun, 01 Mar 2026 22:16:19 +0000 - ISO-Bench: Can Coding Agents Optimize Real-World Inference Workloads? - https://arxiv.org/abs/2602.19594 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.19594.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ayush Nangia, Shikhar Mishra, Aman Gokrani, Paras Chopra</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> We introduce ISO-Bench, a benchmark for coding agents to test their capabilities on real-world inference optimization tasks. These tasks were taken from vLLM and SGLang, two of the most popular LLM serving frameworks. Each task provides an agent with a codebase and bottleneck description, whereby the agent must produce an optimization patch evaluated against expert human solutions. We curated 54 tasks from merged pull requests with measurable performance improvements. While existing benchmarks heavily use runtime-based metrics, such approaches can be gamed to pass tests without capturing the actual intent of the code changes. Therefore, we combine both hard (execution-based) and soft (LLM-based) metrics to show that both are necessary for complete evaluation. While evaluating both closed and open-source coding agents, we find no single agent dominates across codebases. Surprisingly, agents often identify correct bottlenecks but fail to execute working solutions. We also show that agents with identical underlying models differ substantially, suggesting scaffolding is as important as the model.</p> - https://arxiv.org/abs/2602.19594 - Mon, 23 Feb 2026 08:37:53 +0000 + SciDER: Scientific Data-centric End-to-end Researcher + https://arxiv.org/abs/2603.01421 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.01421.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ke Lin, Yilin Lu, Shreyas Bhat, Xuehang Guo, Junier Oliva, Qingyun Wang</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Automated scientific discovery with large language models is transforming the research lifecycle from ideation to experimentation, yet existing agents struggle to autonomously process raw data collected from scientific experiments. We introduce SciDER, a data-centric end-to-end system that automates the research lifecycle. Unlike traditional frameworks, our specialized agents collaboratively parse and analyze raw scientific data, generate hypotheses and experimental designs grounded in specific data characteristics, and write and execute corresponding code. Evaluation on three benchmarks shows SciDER excels in specialized data-driven scientific discovery and outperforms general-purpose agents and state-of-the-art models through its self-evolving memory and critic-led feedback loop. Distributed as a modular Python package, we also provide easy-to-use PyPI packages with a lightweight web interface to accelerate autonomous, data-driven research and aim to be accessible to all researchers and developers.</p> + https://arxiv.org/abs/2603.01421 + Mon, 02 Mar 2026 03:53:20 +0000 - Nacrith: Neural Lossless Compression via Ensemble Context Modeling and High-Precision CDF Coding - https://arxiv.org/abs/2602.19626 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.19626.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Roberto Tacconelli</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> We present Nacrith, a lossless compression system that combines a 135M-parameter transformer language model (SmolLM2-135M) with an ensemble of lightweight online predictors and a 32-bit arithmetic coder. Beyond the base LLM-plus-arithmetic-coding paradigm, Nacrith introduces several contributions: (1) a CDF precision upgrade from 2^16 to 2^24 that eliminates ~75% of quantization overhead caused by minimum-probability floors in large vocabularies; (2) a token-level N-gram model for fast local predictions; (3) an adaptive log-space bias head correcting per-document LLM errors via online gradient descent; (4) confidence-based LLM skip for accelerating highly predictable tokens; (5) a hybrid binary format (NC06) extending neural compression to arbitrary binary files--to our knowledge a first among LLM-based compressors; (6) a llama.cpp inference backend achieving ~7x faster single-token decode than PyTorch; (7) parallel multi-GPU compression across up to 8 workers; and (8) native KV cache sliding window reducing per-slide cost by ~37x. The system requires only ~500 MB of GGUF weights and ~1.2 GB VRAM per worker, running on consumer GPUs. On alice29.txt (Canterbury Corpus, 152 KB), Nacrith achieves 0.918 bits per byte (bpb)--outperforming gzip by 3.1x, bzip2 by 2.5x, CMIX v21 by 44%, and ts_zip by 20%, while compressing below the 0th-, 1st-, and 2nd-order byte-level Shannon entropy bounds. On enwik8 (100 MB), Nacrith achieves 0.9389 bpb (11.74%), surpassing ts_zip (~1.11 bpb) by 15% and FineZip (1.024 bpb) by 8% despite using a 60x smaller model with no fine-tuning. An out-of-distribution evaluation on a document published after the model's training cutoff confirms these gains are not memorization artifacts, achieving 0.723 bpb on unseen text.</p> - https://arxiv.org/abs/2602.19626 - Mon, 23 Feb 2026 09:14:05 +0000 + LaSER: Internalizing Explicit Reasoning into Latent Space for Dense Retrieval + https://arxiv.org/abs/2603.01425 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.01425.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiajie Jin, Yanzhao Zhang, Mingxin Li, Dingkun Long, Pengjun Xie, Yutao Zhu, Zhicheng Dou</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> LLMs have fundamentally transformed dense retrieval, upgrading backbones from discriminative encoders to generative architectures. However, a critical disconnect remains: while LLMs possess strong reasoning capabilities, current retrievers predominantly utilize them as static encoders, leaving their potential for complex reasoning unexplored. To address this, existing approaches typically adopt rewrite-then-retrieve pipelines to generate explicit CoT rationales before retrieval. However, this incurs prohibitive latency. In this paper, we propose LaSER, a novel self-distillation framework that internalizes explicit reasoning into the latent space of dense retrievers. Operating on a shared LLM backbone, LaSER introduces a dual-view training mechanism: an Explicit view that explicitly encodes ground-truth reasoning paths, and a Latent view that performs implicit latent thinking. To bridge the gap between these views, we design a multi-grained alignment strategy. Beyond standard output alignment, we introduce a trajectory alignment mechanism that synchronizes the intermediate latent states of the latent path with the semantic progression of the explicit reasoning segments. This allows the retriever to think silently and effectively without autoregressive text generation. Extensive experiments on both in-domain and out-of-domain reasoning-intensive benchmarks demonstrate that LaSER significantly outperforms state-of-the-art baselines. Furthermore, analyses across diverse backbones and model scales validate the robustness of our approach, confirming that our unified learning framework is essential for eliciting effective latent thinking. Our method successfully combines the reasoning depth of explicit CoT pipelines with the inference efficiency of standard dense retrievers.</p> + https://arxiv.org/abs/2603.01425 + Mon, 02 Mar 2026 04:11:18 +0000 - TAPE: Tool-Guided Adaptive Planning and Constrained Execution in Language Model Agents - https://arxiv.org/abs/2602.19633 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.19633.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jongwon Jeong, Jungtaek Kim, Kangwook Lee</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Language Model (LM) agents have demonstrated remarkable capabilities in solving tasks that require multiple interactions with the environment. However, they remain vulnerable in environments where a single error often leads to irrecoverable failure, particularly under strict feasibility constraints. We systematically analyze existing agent frameworks, identifying imperfect planning and stochastic execution as the primary causes. To address these challenges, we propose Tool-guided Adaptive Planning with constrained Execution (TAPE). TAPE enhances planning capability by aggregating multiple plans into a graph and employing an external solver to identify a feasible path. During execution, TAPE employs constrained decoding to reduce sampling noise, while adaptively re-planning whenever environmental feedback deviates from the intended state. Experiments across Sokoban, ALFWorld, MuSiQue, and GSM8K-Hard demonstrate that TAPE consistently outperforms existing frameworks, with particularly large gains on hard settings, improving success rates by 21.0 percentage points on hard settings on average, and by 20.0 percentage points for weaker base models on average. Code and data available at here.</p> - https://arxiv.org/abs/2602.19633 - Mon, 23 Feb 2026 09:19:56 +0000 + PhotoBench: Beyond Visual Matching Towards Personalized Intent-Driven Photo Retrieval + https://arxiv.org/abs/2603.01493 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.01493.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tianyi Xu, Rong Shan, Junjie Wu, Jiadeng Huang, Teng Wang, Jiachen Zhu, Wenteng Chen, Minxin Tu, Quantao Dou, Zhaoxiang Wang, Changwang Zhang, Weinan Zhang, Jun Wang, Jianghao Lin</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> Personal photo albums are not merely collections of static images but living, ecological archives defined by temporal continuity, social entanglement, and rich metadata, which makes the personalized photo retrieval non-trivial. However, existing retrieval benchmarks rely heavily on context-isolated web snapshots, failing to capture the multi-source reasoning required to resolve authentic, intent-driven user queries. To bridge this gap, we introduce PhotoBench, the first benchmark constructed from authentic, personal albums. It is designed to shift the paradigm from visual matching to personalized multi-source intent-driven reasoning. Based on a rigorous multi-source profiling framework, which integrates visual semantics, spatial-temporal metadata, social identity, and temporal events for each image, we synthesize complex intent-driven queries rooted in users' life trajectories. Extensive evaluation on PhotoBench exposes two critical limitations: the modality gap, where unified embedding models collapse on non-visual constraints, and the source fusion paradox, where agentic systems perform poor tool orchestration. These findings indicate that the next frontier in personal multimodal retrieval lies beyond unified embeddings, necessitating robust agentic reasoning systems capable of precise constraint satisfaction and multi-source fusion. Our PhotoBench is available.</p> + https://arxiv.org/abs/2603.01493 + Mon, 02 Mar 2026 06:02:40 +0000 - SkillOrchestra: Learning to Route Agents via Skill Transfer - https://arxiv.org/abs/2602.19672 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.19672.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiayu Wang, Yifei Ming, Zixuan Ke, Shafiq Joty, Aws Albarghouthi, Frederic Sala</p><p><b>Upvotes:</b> 55</p><p><b>Summary:</b> Compound AI systems promise capabilities beyond those of individual models, yet their success depends critically on effective orchestration. Existing routing approaches face two limitations: (1) input-level routers make coarse query-level decisions that ignore evolving task requirements; (2) RL-trained orchestrators are expensive to adapt and often suffer from routing collapse, repeatedly invoking one strong but costly option in multi-turn scenarios. We introduce SkillOrchestra, a framework for skill-aware orchestration. Instead of directly learning a routing policy end-to-end, SkillOrchestra learns fine-grained skills from execution experience and models agent-specific competence and cost under those skills. At deployment, the orchestrator infers the skill demands of the current interaction and selects agents that best satisfy them under an explicit performance-cost trade-off. Extensive experiments across ten benchmarks demonstrate that SkillOrchestra outperforms SoTA RL-based orchestrators by up to 22.5% with 700x and 300x learning cost reduction compared to Router-R1 and ToolOrchestra, respectively. These results show that explicit skill modeling enables scalable, interpretable, and sample-efficient orchestration, offering a principled alternative to data-intensive RL-based approaches. The code is available at: https://github.com/jiayuww/SkillOrchestra.</p> - https://arxiv.org/abs/2602.19672 - Mon, 23 Feb 2026 10:17:25 +0000 + RubricBench: Aligning Model-Generated Rubrics with Human Standards + https://arxiv.org/abs/2603.01562 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.01562.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qiyuan Zhang, Junyi Zhou, Yufei Wang, Fuyuan Lyu, Yidong Ming, Can Xu, Qingfeng Sun, Kai Zheng, Peng Kang, Xue Liu, Chen Ma</p><p><b>Upvotes:</b> 51</p><p><b>Summary:</b> As Large Language Model (LLM) alignment evolves from simple completions to complex, highly sophisticated generation, Reward Models are increasingly shifting toward rubric-guided evaluation to mitigate surface-level biases. However, the community lacks a unified benchmark to assess this evaluation paradigm, as existing benchmarks lack both the discriminative complexity and the ground-truth rubric annotations required for rigorous analysis. To bridge this gap, we introduce RubricBench, a curated benchmark with 1,147 pairwise comparisons specifically designed to assess the reliability of rubric-based evaluation. Our construction employs a multi-dimensional filtration pipeline to target hard samples featuring nuanced input complexity and misleading surface bias, augmenting each with expert-annotated, atomic rubrics derived strictly from instructions. Comprehensive experiments reveal a substantial capability gap between human-annotated and model-generated rubrics, indicating that even state-of-the-art models struggle to autonomously specify valid evaluation criteria, lagging considerably behind human-guided performance.</p> + https://arxiv.org/abs/2603.01562 + Mon, 02 Mar 2026 07:39:49 +0000 - DSDR: Dual-Scale Diversity Regularization for Exploration in LLM Reasoning - https://arxiv.org/abs/2602.19895 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.19895.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhongwei Wan, Yun Shen, Zhihao Dou, Donghao Zhou, Yu Zhang, Xin Wang, Hui Shen, Jing Xiong, Chaofan Tao, Zixuan Zhong, Peizhou Huang, Mi Zhang</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Reinforcement learning with verifiers (RLVR) is a central paradigm for improving large language model (LLM) reasoning, yet existing methods often suffer from limited exploration. Policies tend to collapse onto a few reasoning patterns and prematurely stop deep exploration, while conventional entropy regularization introduces only local stochasticity and fails to induce meaningful path-level diversity, leading to weak and unstable learning signals in group-based policy optimization. We propose DSDR, a Dual-Scale Diversity Regularization reinforcement learning framework that decomposes diversity in LLM reasoning into global and coupling components. Globally, DSDR promotes diversity among correct reasoning trajectories to explore distinct solution modes. Locally, it applies a length-invariant, token-level entropy regularization restricted to correct trajectories, preventing entropy collapse within each mode while preserving correctness. The two scales are coupled through a global-to-local allocation mechanism that emphasizes local regularization for more distinctive correct trajectories. We provide theoretical support showing that DSDR preserves optimal correctness under bounded regularization, sustains informative learning signals in group-based optimization, and yields a principled global-to-local coupling rule. Experiments on multiple reasoning benchmarks demonstrate consistent improvements in accuracy and pass@k, highlighting the importance of dual-scale diversity for deep exploration in RLVR. Code is available at https://github.com/SUSTechBruce/DSDR.</p> - https://arxiv.org/abs/2602.19895 - Mon, 23 Feb 2026 14:37:01 +0000 + Beyond Length Scaling: Synergizing Breadth and Depth for Generative Reward Models + https://arxiv.org/abs/2603.01571 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.01571.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qiyuan Zhang, Yufei Wang, Tianhe Wu, Can Xu, Qingfeng Sun, Kai Zheng, Xue Liu, Chen Ma</p><p><b>Upvotes:</b> 32</p><p><b>Summary:</b> Recent advancements in Generative Reward Models (GRMs) have demonstrated that scaling the length of Chain-of-Thought (CoT) reasoning considerably enhances the reliability of evaluation. However, current works predominantly rely on unstructured length scaling, ignoring the divergent efficacy of different reasoning mechanisms: Breadth-CoT (B-CoT, i.e., multi-dimensional principle coverage) and Depth-CoT (D-CoT, i.e., substantive judgment soundness). To address this, we introduce Mix-GRM, a framework that reconfigures raw rationales into structured B-CoT and D-CoT through a modular synthesis pipeline, subsequently employing Supervised Fine-Tuning (SFT) and Reinforcement Learning with Verifiable Rewards (RLVR) to internalize and optimize these mechanisms. Comprehensive experiments demonstrate that Mix-GRM establishes a new state-of-the-art across five benchmarks, surpassing leading open-source RMs by an average of 8.2\%. Our results reveal a clear divergence in reasoning: B-CoT benefits subjective preference tasks, whereas D-CoT excels in objective correctness tasks. Consequently, misaligning the reasoning mechanism with the task directly degrades performance. Furthermore, we demonstrate that RLVR acts as a switching amplifier, inducing an emergent polarization where the model spontaneously allocates its reasoning style to match task demands. The synthesized data and models are released at https://huggingface.co/collections/DonJoey/mix-grm{Hugging Face}, and the code is released at https://github.com/Don-Joey/Mix-GRM{Github}.</p> + https://arxiv.org/abs/2603.01571 + Mon, 02 Mar 2026 07:54:29 +0000 - Agents of Chaos - https://arxiv.org/abs/2602.20021 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.20021.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Natalie Shapira, Chris Wendler, Avery Yen, Gabriele Sarti, Koyena Pal, Olivia Floody, Adam Belfki, Alex Loftus, Aditya Ratan Jannali, Nikhil Prakash, Jasmine Cui, Giordano Rogers, Jannik Brinkmann, Can Rager, Amir Zur, Michael Ripa, Aruna Sankaranarayanan, David Atkinson, Rohit Gandikota, Jaden Fiotto-Kaufman, EunJeong Hwang, Hadas Orgad, P Sam Sahil, Negev Taglicht, Tomer Shabtay, Atai Ambus, Nitay Alon, Shiri Oron, Ayelet Gordon-Tapiero, Yotam Kaplan, Vered Shwartz, Tamar Rott Shaham, Christoph Riedl, Reuth Mirsky, Maarten Sap, David Manheim, Tomer Ullman, David Bau</p><p><b>Upvotes:</b> 27</p><p><b>Summary:</b> We report an exploratory red-teaming study of autonomous language-model-powered agents deployed in a live laboratory environment with persistent memory, email accounts, Discord access, file systems, and shell execution. Over a two-week period, twenty AI researchers interacted with the agents under benign and adversarial conditions. Focusing on failures emerging from the integration of language models with autonomy, tool use, and multi-party communication, we document eleven representative case studies. Observed behaviors include unauthorized compliance with non-owners, disclosure of sensitive information, execution of destructive system-level actions, denial-of-service conditions, uncontrolled resource consumption, identity spoofing vulnerabilities, cross-agent propagation of unsafe practices, and partial system takeover. In several cases, agents reported task completion while the underlying system state contradicted those reports. We also report on some of the failed attempts. Our findings establish the existence of security-, privacy-, and governance-relevant vulnerabilities in realistic deployment settings. These behaviors raise unresolved questions regarding accountability, delegated authority, and responsibility for downstream harms, and warrant urgent attention from legal scholars, policymakers, and researchers across disciplines. This report serves as an initial empirical contribution to that broader conversation.</p> - https://arxiv.org/abs/2602.20021 - Mon, 23 Feb 2026 16:28:48 +0000 + Surgical Post-Training: Cutting Errors, Keeping Knowledge + https://arxiv.org/abs/2603.01683 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.01683.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wenye Lin, Kai Han</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Enhancing the reasoning capabilities of Large Language Models (LLMs) via post-training is often constrained by the trade-off between efficiency and catastrophic forgetting. While prior research emphasizes the role of on-policy data in mitigating forgetting, we uncover--and validate both theoretically and empirically--an overlooked yet critical mechanism: the implicit regularization inherent in Direct Preference Optimization's (DPO) reward estimate. This motivates our Surgical Post-Training (SPoT), a new paradigm designed to optimize reasoning efficiently while preserving learned prior knowledge. SPoT consists of: (1) a data rectification pipeline that employs an Oracle to surgically correct erroneous steps via minimal edits, generating data proximal to the model's distribution; and (2) a reward-based binary cross-entropy objective. Unlike the relative ranking in DPO, this objective treats reasoning correctness as a binary classification problem, enforcing decoupled supervision signals. Empirically, with only 4k rectified math data pairs, SPoT improves Qwen3-8B's accuracy by 6.2% on average across in-domain and OOD tasks, requiring merely 28 minutes of training on 8x H800 GPUs. Code: https://github.com/Visual-AI/SPoT</p> + https://arxiv.org/abs/2603.01683 + Mon, 02 Mar 2026 10:12:56 +0000 - ManCAR: Manifold-Constrained Latent Reasoning with Adaptive Test-Time Computation for Sequential Recommendation - https://arxiv.org/abs/2602.20093 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.20093.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kun Yang, Yuxuan Zhu, Yazhe Chen, Siyao Zheng, Bangyang Hong, Kangle Wu, Yabo Ni, Anxiang Zeng, Cong Fu, Hui Li</p><p><b>Upvotes:</b> 28</p><p><b>Summary:</b> Sequential recommendation increasingly employs latent multi-step reasoning to enhance test-time computation. Despite empirical gains, existing approaches largely drive intermediate reasoning states via target-dominant objectives without imposing explicit feasibility constraints. This results in latent drift, where reasoning trajectories deviate into implausible regions. We argue that effective recommendation reasoning should instead be viewed as navigation on a collaborative manifold rather than free-form latent refinement. To this end, we propose ManCAR (Manifold-Constrained Adaptive Reasoning), a principled framework that grounds reasoning within the topology of a global interaction graph. ManCAR constructs a local intent prior from the collaborative neighborhood of a user's recent actions, represented as a distribution over the item simplex. During training, the model progressively aligns its latent predictive distribution with this prior, forcing the reasoning trajectory to remain within the valid manifold. At test time, reasoning proceeds adaptively until the predictive distribution stabilizes, avoiding over-refinement. We provide a variational interpretation of ManCAR to theoretically validate its drift-prevention and adaptive test-time stopping mechanisms. Experiments on seven benchmarks demonstrate that ManCAR consistently outperforms state-of-the-art baselines, achieving up to a 46.88% relative improvement w.r.t. NDCG@10. Our code is available at https://github.com/FuCongResearchSquad/ManCAR.</p> - https://arxiv.org/abs/2602.20093 - Mon, 23 Feb 2026 18:02:50 +0000 + Legal RAG Bench: an end-to-end benchmark for legal RAG + https://arxiv.org/abs/2603.01710 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.01710.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Abdur-Rahman Butler, Umar Butler</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> We introduce Legal RAG Bench, a benchmark and evaluation methodology for assessing the end-to-end performance of legal RAG systems. As a benchmark, Legal RAG Bench consists of 4,876 passages from the Victorian Criminal Charge Book alongside 100 complex, hand-crafted questions demanding expert knowledge of criminal law and procedure. Both long-form answers and supporting passages are provided. As an evaluation methodology, Legal RAG Bench leverages a full factorial design and novel hierarchical error decomposition framework, enabling apples-to-apples comparisons of the contributions of retrieval and reasoning models in RAG. We evaluate three state-of-the-art embedding models (Isaacus' Kanon 2 Embedder, Google's Gemini Embedding 001, and OpenAI's Text Embedding 3 Large) and two frontier LLMs (Gemini 3.1 Pro and GPT-5.2), finding that information retrieval is the primary driver of legal RAG performance, with LLMs exerting a more moderate effect on correctness and groundedness. Kanon 2 Embedder, in particular, had the largest positive impact on performance, improving average correctness by 17.5 points, groundedness by 4.5 points, and retrieval accuracy by 34 points. We observe that many errors attributed to hallucinations in legal RAG systems are in fact triggered by retrieval failures, concluding that retrieval sets the ceiling for the performance of many modern legal RAG systems. We document why and how we built Legal RAG Bench alongside the results of our evaluations. We also openly release our code and data to assist with reproduction of our findings.</p> + https://arxiv.org/abs/2603.01710 + Mon, 02 Mar 2026 10:34:28 +0000 - NanoKnow: How to Know What Your Language Model Knows - https://arxiv.org/abs/2602.20122 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.20122.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lingwei Gu, Nour Jedidi, Jimmy Lin</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> How do large language models (LLMs) know what they know? Answering this question has been difficult because pre-training data is often a "black box" -- unknown or inaccessible. The recent release of nanochat -- a family of small LLMs with fully open pre-training data -- addresses this as it provides a transparent view into where a model's parametric knowledge comes from. Towards the goal of understanding how knowledge is encoded by LLMs, we release NanoKnow, a benchmark dataset that partitions questions from Natural Questions and SQuAD into splits based on whether their answers are present in nanochat's pre-training corpus. Using these splits, we can now properly disentangle the sources of knowledge that LLMs rely on when producing an output. To demonstrate NanoKnow's utility, we conduct experiments using eight nanochat checkpoints. Our findings show: (1) closed-book accuracy is strongly influenced by answer frequency in the pre-training data, (2) providing external evidence can mitigate this frequency dependence, (3) even with external evidence, models are more accurate when answers were seen during pre-training, demonstrating that parametric and external knowledge are complementary, and (4) non-relevant information is harmful, with accuracy decreasing based on both the position and the number of non-relevant contexts. We release all NanoKnow artifacts at https://github.com/castorini/NanoKnow.</p> - https://arxiv.org/abs/2602.20122 - Mon, 23 Feb 2026 18:37:49 +0000 + OpenAutoNLU: Open Source AutoML Library for NLU + https://arxiv.org/abs/2603.01824 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.01824.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Grigory Arshinov, Aleksandr Boriskin, Sergey Senichev, Ayaz Zaripov, Daria Galimzianova, Daniil Karpov, Leonid Sanochkin</p><p><b>Upvotes:</b> 44</p><p><b>Summary:</b> OpenAutoNLU is an open-source automated machine learning library for natural language understanding (NLU) tasks, covering both text classification and named entity recognition (NER). Unlike existing solutions, we introduce data-aware training regime selection that requires no manual configuration from the user. The library also provides integrated data quality diagnostics, configurable out-of-distribution (OOD) detection, and large language model (LLM) features, all within a minimal lowcode API. The demo app is accessible here https://openautonlu.dev.</p> + https://arxiv.org/abs/2603.01824 + Mon, 02 Mar 2026 12:56:54 +0000 - A Very Big Video Reasoning Suite - https://arxiv.org/abs/2602.20159 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.20159.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Maijunxian Wang, Ruisi Wang, Juyi Lin, Ran Ji, Thaddäus Wiedemer, Qingying Gao, Dezhi Luo, Yaoyao Qian, Lianyu Huang, Zelong Hong, Jiahui Ge, Qianli Ma, Hang He, Yifan Zhou, Lingzi Guo, Lantao Mei, Jiachen Li, Hanwen Xing, Tianqi Zhao, Fengyuan Yu, Weihang Xiao, Yizheng Jiao, Jianheng Hou, Danyang Zhang, Pengcheng Xu, Boyang Zhong, Zehong Zhao, Gaoyun Fang, John Kitaoka, Yile Xu, Hua Xu, Kenton Blacutt, Tin Nguyen, Siyuan Song, Haoran Sun, Shaoyue Wen, Linyang He, Runming Wang, Yanzhi Wang, Mengyue Yang, Ziqiao Ma, Raphaël Millière, Freda Shi, Nuno Vasconcelos, Daniel Khashabi, Alan Yuille, Yilun Du, Ziming Liu, Bo Li, Dahua Lin, Ziwei Liu, Vikash Kumar, Yijiang Li, Lei Yang, Zhongang Cai, Hokin Deng</p><p><b>Upvotes:</b> 494</p><p><b>Summary:</b> Rapid progress in video models has largely focused on visual quality, leaving their reasoning capabilities underexplored. Video reasoning grounds intelligence in spatiotemporally consistent visual environments that go beyond what text can naturally capture, enabling intuitive reasoning over spatiotemporal structure such as continuity, interaction, and causality. However, systematically studying video reasoning and its scaling behavior is hindered by the lack of large-scale training data. To address this gap, we introduce the Very Big Video Reasoning (VBVR) Dataset, an unprecedentedly large-scale resource spanning 200 curated reasoning tasks following a principled taxonomy and over one million video clips, approximately three orders of magnitude larger than existing datasets. We further present VBVR-Bench, a verifiable evaluation framework that moves beyond model-based judging by incorporating rule-based, human-aligned scorers, enabling reproducible and interpretable diagnosis of video reasoning capabilities. Leveraging the VBVR suite, we conduct one of the first large-scale scaling studies of video reasoning and observe early signs of emergent generalization to unseen reasoning tasks. Together, VBVR lays a foundation for the next stage of research in generalizable video reasoning. The data, benchmark toolkit, and models are publicly available at https://video-reason.com/ .</p> - https://arxiv.org/abs/2602.20159 - Mon, 23 Feb 2026 18:59:41 +0000 + FireRed-OCR Technical Report + https://arxiv.org/abs/2603.01840 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.01840.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hao Wu, Haoran Lou, Xinyue Li, Zuodong Zhong, Zhaojun Sun, Phellon Chen, Xuanhe Zhou, Kai Zuo, Yibo Chen, Xu Tang, Yao Hu, Boxiang Zhou, Jian Wu, Yongji Wu, Wenxin Yu, Yingmiao Liu, Yuhao Huang, Manjie Xu, Gang Liu, Yidong Ma, Zhichao Sun, Changhao Qiao</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> We present FireRed-OCR, a systematic framework to specialize general VLMs into high-performance OCR models. Large Vision-Language Models (VLMs) have demonstrated impressive general capabilities but frequently suffer from ``structural hallucination'' when processing complex documents, limiting their utility in industrial OCR applications. In this paper, we introduce FireRed-OCR, a novel framework designed to transform general-purpose VLMs (based on Qwen3-VL) into pixel-precise structural document parsing experts. To address the scarcity of high-quality structured data, we construct a ``Geometry + Semantics'' Data Factory. Unlike traditional random sampling, our pipeline leverages geometric feature clustering and multi-dimensional tagging to synthesize and curate a highly balanced dataset, effectively handling long-tail layouts and rare document types. Furthermore, we propose a Three-Stage Progressive Training strategy that guides the model from pixel-level perception to logical structure generation. This curriculum includes: (1) Multi-task Pre-alignment to ground the model's understanding of document structure; (2) Specialized SFT for standardizing full-image Markdown output; and (3) Format-Constrained Group Relative Policy Optimization (GRPO), which utilizes reinforcement learning to enforce strict syntactic validity and structural integrity (e.g., table closure, formula syntax). Extensive evaluations on OmniDocBench v1.5 demonstrate that FireRed-OCR achieves state-of-the-art performance with an overall score of 92.94\%, significantly outperforming strong baselines such as DeepSeek-OCR 2 and OCRVerse across text, formula, table, and reading order metrics. We open-source our code and model weights to facilitate the ``General VLM to Specialized Structural Expert'' paradigm.</p> + https://arxiv.org/abs/2603.01840 + Mon, 02 Mar 2026 13:19:23 +0000 - tttLRM: Test-Time Training for Long Context and Autoregressive 3D Reconstruction - https://arxiv.org/abs/2602.20160 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.20160.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chen Wang, Hao Tan, Wang Yifan, Zhiqin Chen, Yuheng Liu, Kalyan Sunkavalli, Sai Bi, Lingjie Liu, Yiwei Hu</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> We propose tttLRM, a novel large 3D reconstruction model that leverages a Test-Time Training (TTT) layer to enable long-context, autoregressive 3D reconstruction with linear computational complexity, further scaling the model's capability. Our framework efficiently compresses multiple image observations into the fast weights of the TTT layer, forming an implicit 3D representation in the latent space that can be decoded into various explicit formats, such as Gaussian Splats (GS) for downstream applications. The online learning variant of our model supports progressive 3D reconstruction and refinement from streaming observations. We demonstrate that pretraining on novel view synthesis tasks effectively transfers to explicit 3D modeling, resulting in improved reconstruction quality and faster convergence. Extensive experiments show that our method achieves superior performance in feedforward 3D Gaussian reconstruction compared to state-of-the-art approaches on both objects and scenes.</p> - https://arxiv.org/abs/2602.20160 - Mon, 23 Feb 2026 18:59:45 +0000 + Agentic Code Reasoning + https://arxiv.org/abs/2603.01896 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.01896.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shubham Ugare, Satish Chandra</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Can LLM agents explore codebases and reason about code semantics without executing the code? We study this capability, which we call agentic code reasoning, and introduce semi-formal reasoning: a structured prompting methodology that requires agents to construct explicit premises, trace execution paths, and derive formal conclusions. Unlike unstructured chain-of-thought, semi-formal reasoning acts as a certificate: the agent cannot skip cases or make unsupported claims. We evaluate across three tasks (patch equivalence verification, fault localization, and code question answering) and show that semi-formal reasoning consistently improves accuracy on all of them. For patch equivalence, accuracy improves from 78% to 88% on curated examples and reaches 93% on real-world agent-generated patches, approaching the reliability needed for execution-free RL reward signals. For code question answering on RubberDuckBench Mohammad et al. (2026), semi-formal reasoning achieves 87% accuracy. For fault localization on Defects4J Just et al. (2014), semi-formal reasoning improves Top-5 accuracy by 5 percentage points over standard reasoning. These results demonstrate that structured agentic reasoning enables meaningful semantic code analysis without execution, opening practical applications in RL training pipelines, code review, and static program analysis.</p> + https://arxiv.org/abs/2603.01896 + Mon, 02 Mar 2026 14:17:06 +0000 - Mobile-O: Unified Multimodal Understanding and Generation on Mobile Device - https://arxiv.org/abs/2602.20161 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.20161.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Abdelrahman Shaker, Ahmed Heakl, Jaseel Muhammad, Ritesh Thawkar, Omkar Thawakar, Senmao Li, Hisham Cholakkal, Ian Reid, Eric P. Xing, Salman Khan, Fahad Shahbaz Khan</p><p><b>Upvotes:</b> 23</p><p><b>Summary:</b> Unified multimodal models can both understand and generate visual content within a single architecture. Existing models, however, remain data-hungry and too heavy for deployment on edge devices. We present Mobile-O, a compact vision-language-diffusion model that brings unified multimodal intelligence to a mobile device. Its core module, the Mobile Conditioning Projector (MCP), fuses vision-language features with a diffusion generator using depthwise-separable convolutions and layerwise alignment. This design enables efficient cross-modal conditioning with minimal computational cost. Trained on only a few million samples and post-trained in a novel quadruplet format (generation prompt, image, question, answer), Mobile-O jointly enhances both visual understanding and generation capabilities. Despite its efficiency, Mobile-O attains competitive or superior performance compared to other unified models, achieving 74% on GenEval and outperforming Show-O and JanusFlow by 5% and 11%, while running 6x and 11x faster, respectively. For visual understanding, Mobile-O surpasses them by 15.3% and 5.1% averaged across seven benchmarks. Running in only ~3s per 512x512 image on an iPhone, Mobile-O establishes the first practical framework for real-time unified multimodal understanding and generation on edge devices. We hope Mobile-O will ease future research in real-time unified multimodal intelligence running entirely on-device with no cloud dependency. Our code, models, datasets, and mobile application are publicly available at https://amshaker.github.io/Mobile-O/</p> - https://arxiv.org/abs/2602.20161 - Mon, 23 Feb 2026 18:59:58 +0000 + Efficient RLVR Training via Weighted Mutual Information Data Selection + https://arxiv.org/abs/2603.01907 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.01907.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xinyu Zhou, Boyu Zhu, Haotian Zhang, Huiming Wang, Zhijiang Guo</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Reinforcement learning (RL) plays a central role in improving the reasoning and alignment of large language models, yet its efficiency critically depends on how training data are selected. Existing online selection strategies predominantly rely on difficulty-based heuristics, favouring datapoints with intermediate success rates, implicitly equating difficulty with informativeness and neglecting epistemic uncertainty arising from limited evidence. We introduce InSight, an INformation-guided data SamplInG metHod for RL Training, grounded in a weighted mutual information objective. By modeling data outcomes with Bayesian latent success rates, we show that expected uncertainty reduction decomposes into complementary difficulty- and evidence-dependent components, revealing a fundamental limitation of difficulty-only selection. Leveraging this observation, InSight constructs a stable acquisition score based on the mean belief of datapoints' success rather than noisy sampled outcomes, and naturally extends to multi-rollout settings common in reinforcement learning with verifiable rewards (RLVR). Extensive experiments demonstrate that InSight consistently achieves state-of-the-art performance and improves training efficiency, including a +1.41 average gain on Planning & Mathmatics benchmarks, +1.01 improvement on general reasoning, and up to ~2.2x acceleration, with negligible additional computational overhead.</p> + https://arxiv.org/abs/2603.01907 + Mon, 02 Mar 2026 14:25:07 +0000 - What Makes a Good Query? Measuring the Impact of Human-Confusing Linguistic Features on LLM Performance - https://arxiv.org/abs/2602.20300 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.20300.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> William Watson, Nicole Cho, Sumitra Ganesh, Manuela Veloso</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Large Language Model (LLM) hallucinations are usually treated as defects of the model or its decoding strategy. Drawing on classical linguistics, we argue that a query's form can also shape a listener's (and model's) response. We operationalize this insight by constructing a 22-dimension query feature vector covering clause complexity, lexical rarity, and anaphora, negation, answerability, and intention grounding, all known to affect human comprehension. Using 369,837 real-world queries, we ask: Are there certain types of queries that make hallucination more likely? A large-scale analysis reveals a consistent "risk landscape": certain features such as deep clause nesting and underspecification align with higher hallucination propensity. In contrast, clear intention grounding and answerability align with lower hallucination rates. Others, including domain specificity, show mixed, dataset- and model-dependent effects. Thus, these findings establish an empirically observable query-feature representation correlated with hallucination risk, paving the way for guided query rewriting and future intervention studies.</p> - https://arxiv.org/abs/2602.20300 - Mon, 23 Feb 2026 19:30:08 +0000 + CoVe: Training Interactive Tool-Use Agents via Constraint-Guided Verification + https://arxiv.org/abs/2603.01940 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.01940.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jinpeng Chen, Cheng Gong, Hanbo Li, Ziru Liu, Zichen Tian, Xinyu Fu, Shi Wu, Chenyang Zhang, Wu Zhang, Suiyun Zhang, Dandan Tu, Rui Liu</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> Developing multi-turn interactive tool-use agents is challenging because real-world user needs are often complex and ambiguous, yet agents must execute deterministic actions to satisfy them. To address this gap, we introduce CoVe (Constraint-Verification), a post-training data synthesis framework designed for training interactive tool-use agents while ensuring both data complexity and correctness. CoVe begins by defining explicit task constraints, which serve a dual role: they guide the generation of complex trajectories and act as deterministic verifiers for assessing trajectory quality. This enables the creation of high-quality training trajectories for supervised fine-tuning (SFT) and the derivation of accurate reward signals for reinforcement learning (RL). Our evaluation on the challenging τ^2-bench benchmark demonstrates the effectiveness of the framework. Notably, our compact CoVe-4B model achieves success rates of 43.0\% and 59.4\% in the Airline and Retail domains, respectively; its overall performance significantly outperforms strong baselines of similar scale and remains competitive with models up to 17times its size. These results indicate that CoVe provides an effective and efficient pathway for synthesizing training data for state-of-the-art interactive tool-use agents. To support future research, we open-source our code, trained model, and the full set of 12K high-quality trajectories used for training.</p> + https://arxiv.org/abs/2603.01940 + Mon, 02 Mar 2026 14:56:35 +0000 - QuantVLA: Scale-Calibrated Post-Training Quantization for Vision-Language-Action Models - https://arxiv.org/abs/2602.20309 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.20309.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jingxuan Zhang, Yunta Hsieh, Zhongwei Wang, Haokun Lin, Xin Wang, Ziqi Wang, Yingtie Lei, Mi Zhang</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Vision-language-action (VLA) models unify perception, language, and control for embodied agents but face significant challenges in practical deployment due to rapidly increasing compute and memory demands, especially as models scale to longer horizons and larger backbones. To address these bottlenecks, we introduce QuantVLA, a training-free post-training quantization (PTQ) framework that, to our knowledge, is the first PTQ approach for VLA systems and the first to successfully quantize a diffusion transformer (DiT) action head. QuantVLA incorporates three scale-calibrated components: (1) a selective quantization layout that integerizes all linear layers in both the language backbone and the DiT while keeping attention projections in floating point to preserve the original operator schedule; (2) attention temperature matching, a lightweight per-head scaling mechanism that stabilizes attention logits and is folded into the dequantization scales at inference; and (3) output head balancing, a per-layer residual interface calibration that mitigates post-projection energy drift. The framework requires no additional training, uses only a small unlabeled calibration buffer, and supports integer kernels for low-bit weights and activations while leaving the architecture unchanged. Across representative VLA models on LIBERO, QuantVLA exceeds the task success rates of full-precision baselines, achieves about 70% relative memory savings on the quantized components, and delivers a 1.22x speedup in end-to-end inference latency, providing a practical pathway toward scalable low-bit embodied intelligence under strict compute, memory, and power constraints.</p> - https://arxiv.org/abs/2602.20309 - Mon, 23 Feb 2026 19:55:54 +0000 + CharacterFlywheel: Scaling Iterative Improvement of Engaging and Steerable LLMs in Production + https://arxiv.org/abs/2603.01973 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.01973.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yixin Nie, Lin Guan, Zhongyao Ma, Anchit Gupta, Yipin Zhou, Xiao Li, Zhengping Zhou, Raymond Zeng, Gelin Zhou, Shigan Chu, Ajay Thampi, Wancen Mu, Nathan Shuster, Ketong Wang, Lin Chen, Jason Brewer, Derek Hao Hu, Alexander McCauley, Jason Weston, Sem Park, Na Zhang, Kevin Tang</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> This report presents CharacterFlywheel, an iterative flywheel process for improving large language models (LLMs) in production social chat applications across Instagram, WhatsApp, and Messenger. Starting from LLaMA 3.1, we refined models across 15 generations using data from both internal and external real-user traffic. Through continuous deployments from July 2024 to April 2025, we conducted controlled 7-day A/B tests showing consistent engagement improvements: 7 of 8 newly deployed models demonstrated positive lift over the baseline, with the strongest performers achieving up to 8.8% improvement in engagement breadth and 19.4% in engagement depth. We also observed substantial gains in steerability, with instruction following increasing from 59.2% to 84.8% and instruction violations decreasing from 26.6% to 5.8%. We detail the CharacterFlywheel process which integrates data curation, reward modeling to estimate and interpolate the landscape of engagement metrics, supervised fine-tuning (SFT), reinforcement learning (RL), and both offline and online evaluation to ensure reliable progress at each optimization step. We also discuss our methods for overfitting prevention and navigating production dynamics at scale. These contributions advance the scientific rigor and understanding of LLMs in social applications serving millions of users.</p> + https://arxiv.org/abs/2603.01973 + Mon, 02 Mar 2026 15:27:31 +0000 - No One Size Fits All: QueryBandits for Hallucination Mitigation - https://arxiv.org/abs/2602.20332 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.20332.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Nicole Cho, William Watson, Alec Koppel, Sumitra Ganesh, Manuela Veloso</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Advanced reasoning capabilities in Large Language Models (LLMs) have led to more frequent hallucinations; yet most mitigation work focuses on open-source models for post-hoc detection and parameter editing. The dearth of studies focusing on hallucinations in closed-source models is especially concerning, as they constitute the vast majority of models in institutional deployments. We introduce QueryBandits, a model-agnostic contextual bandit framework that adaptively learns online to select the optimal query-rewrite strategy by leveraging an empirically validated and calibrated reward function. Across 16 QA scenarios, our top QueryBandit (Thompson Sampling) achieves an 87.5% win rate over a No-Rewrite baseline and outperforms zero-shot static policies (e.g., Paraphrase or Expand) by 42.6% and 60.3%, respectively. Moreover, all contextual bandits outperform vanilla bandits across all datasets, with higher feature variance coinciding with greater variance in arm selection. This substantiates our finding that there is no single rewrite policy optimal for all queries. We also discover that certain static policies incur higher cumulative regret than No-Rewrite, indicating that an inflexible query-rewriting policy can worsen hallucinations. Thus, learning an online policy over semantic features with QueryBandits can shift model behavior purely through forward-pass mechanisms, enabling its use with closed-source models and bypassing the need for retraining or gradient-based adaptation.</p> - https://arxiv.org/abs/2602.20332 - Mon, 23 Feb 2026 20:28:48 +0000 + MMR-Life: Piecing Together Real-life Scenes for Multimodal Multi-image Reasoning + https://arxiv.org/abs/2603.02024 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.02024.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiachun Li, Shaoping Huang, Zhuoran Jin, Chenlong Zhang, Pengfei Cao, Yubo Chen, Kang Liu, Jun Zhao</p><p><b>Upvotes:</b> 42</p><p><b>Summary:</b> Recent progress in the reasoning capabilities of multimodal large language models (MLLMs) has empowered them to address more complex tasks such as scientific analysis and mathematical reasoning. Despite their promise, MLLMs' reasoning abilities across different scenarios in real life remain largely unexplored and lack standardized benchmarks for evaluation. To address this gap, we introduce MMR-Life, a comprehensive benchmark designed to evaluate the diverse multimodal multi-image reasoning capabilities of MLLMs across real-life scenarios. MMR-Life consists of 2,646 multiple-choice questions based on 19,108 images primarily sourced from real-world contexts, comprehensively covering seven reasoning types: abductive, analogical, causal, deductive, inductive, spatial, and temporal. Unlike existing reasoning benchmarks, MMR-Life does not rely on domain-specific expertise but instead requires models to integrate information across multiple images and apply diverse reasoning abilities. The evaluation of 37 advanced models highlights the substantial challenge posed by MMR-Life. Even top models like GPT-5 achieve only 58% accuracy and display considerable variance in performance across reasoning types. Moreover, we analyze the reasoning paradigms of existing MLLMs, exploring how factors such as thinking length, reasoning method, and reasoning type affect their performance. In summary, MMR-Life establishes a comprehensive foundation for evaluating, analyzing, and improving the next generation of multimodal reasoning systems.</p> + https://arxiv.org/abs/2603.02024 + Mon, 02 Mar 2026 16:06:23 +0000 - MedCLIPSeg: Probabilistic Vision-Language Adaptation for Data-Efficient and Generalizable Medical Image Segmentation - https://arxiv.org/abs/2602.20423 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.20423.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Taha Koleilat, Hojat Asgariandehkordi, Omid Nejati Manzari, Berardino Barile, Yiming Xiao, Hassan Rivaz</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Medical image segmentation remains challenging due to limited annotations for training, ambiguous anatomical features, and domain shifts. While vision-language models such as CLIP offer strong cross-modal representations, their potential for dense, text-guided medical image segmentation remains underexplored. We present MedCLIPSeg, a novel framework that adapts CLIP for robust, data-efficient, and uncertainty-aware medical image segmentation. Our approach leverages patch-level CLIP embeddings through probabilistic cross-modal attention, enabling bidirectional interaction between image and text tokens and explicit modeling of predictive uncertainty. Together with a soft patch-level contrastive loss that encourages more nuanced semantic learning across diverse textual prompts, MedCLIPSeg effectively improves data efficiency and domain generalizability. Extensive experiments across 16 datasets spanning five imaging modalities and six organs demonstrate that MedCLIPSeg outperforms prior methods in accuracy, efficiency, and robustness, while providing interpretable uncertainty maps that highlight local reliability of segmentation results. This work demonstrates the potential of probabilistic vision-language modeling for text-driven medical image segmentation.</p> - https://arxiv.org/abs/2602.20423 - Mon, 23 Feb 2026 23:46:05 +0000 + WorldStereo: Bridging Camera-Guided Video Generation and Scene Reconstruction via 3D Geometric Memories + https://arxiv.org/abs/2603.02049 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.02049.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yisu Zhang, Chenjie Cao, Tengfei Wang, Xuhui Zuo, Junta Wu, Jianke Zhu, Chunchao Guo</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Recent advances in foundational Video Diffusion Models (VDMs) have yielded significant progress. Yet, despite the remarkable visual quality of generated videos, reconstructing consistent 3D scenes from these outputs remains challenging, due to limited camera controllability and inconsistent generated content when viewed from distinct camera trajectories. In this paper, we propose WorldStereo, a novel framework that bridges camera-guided video generation and 3D reconstruction via two dedicated geometric memory modules. Formally, the global-geometric memory enables precise camera control while injecting coarse structural priors through incrementally updated point clouds. Moreover, the spatial-stereo memory constrains the model's attention receptive fields with 3D correspondence to focus on fine-grained details from the memory bank. These components enable WorldStereo to generate multi-view-consistent videos under precise camera control, facilitating high-quality 3D reconstruction. Furthermore, the flexible control branch-based WorldStereo shows impressive efficiency, benefiting from the distribution matching distilled VDM backbone without joint training. Extensive experiments across both camera-guided video generation and 3D reconstruction benchmarks demonstrate the effectiveness of our approach. Notably, we show that WorldStereo acts as a powerful world model, tackling diverse scene generation tasks (whether starting from perspective or panoramic images) with high-fidelity 3D results. Models will be released.</p> + https://arxiv.org/abs/2603.02049 + Mon, 02 Mar 2026 16:36:56 +0000 - Implicit Intelligence -- Evaluating Agents on What Users Don't Say - https://arxiv.org/abs/2602.20424 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.20424.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ved Sirdeshmukh, Marc Wetter</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Real-world requests to AI agents are fundamentally underspecified. Natural human communication relies on shared context and unstated constraints that speakers expect listeners to infer. Current agentic benchmarks test explicit instruction-following but fail to evaluate whether agents can reason about implicit requirements spanning accessibility needs, privacy boundaries, catastrophic risks, and contextual constraints. We present Implicit Intelligence, an evaluation framework testing whether AI agents can move beyond prompt-following to become genuine goal-fulfillers, paired with Agent-as-a-World (AaW), a harness where interactive worlds are defined in human-readable YAML files and simulated by language models. Our scenarios feature apparent simplicity in user requests, hidden complexity in correct solutions, and discoverability of constraints through environmental exploration. Evaluating 16 frontier and open-weight models across 205 scenarios, we find that even the best-performing model achieves only 48.3% scenario pass rate, revealing substantial room for improvement in bridging the gap between literal instruction-following and human-like contextual reasoning.</p> - https://arxiv.org/abs/2602.20424 - Mon, 23 Feb 2026 23:46:55 +0000 + Recursive Think-Answer Process for LLMs and VLMs + https://arxiv.org/abs/2603.02099 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.02099.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Byung-Kwan Lee, Youngchae Chee, Yong Man Ro</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Think-Answer reasoners such as DeepSeek-R1 have made notable progress by leveraging interpretable internal reasoning. However, despite the frequent presence of self-reflective cues like "Oops!", they remain vulnerable to output errors during single-pass inference. To address this limitation, we propose an efficient Recursive Think-Answer Process (R-TAP) that enables models to engage in iterative reasoning cycles and generate more accurate answers, going beyond conventional single-pass approaches. Central to this approach is a confidence generator that evaluates the certainty of model responses and guides subsequent improvements. By incorporating two complementary rewards-Recursively Confidence Increase Reward and Final Answer Confidence Reward-we show that R-TAP-enhanced models consistently outperform conventional single-pass methods for both large language models (LLMs) and vision-language models (VLMs). Moreover, by analyzing the frequency of "Oops"-like expressions in model responses, we find that R-TAP-applied models exhibit significantly fewer self-reflective patterns, resulting in more stable and faster inference-time reasoning. We hope R-TAP pave the way evolving into efficient and elaborated methods to refine the reasoning processes of future AI.</p> + https://arxiv.org/abs/2603.02099 + Mon, 02 Mar 2026 17:20:10 +0000 - Generative AI and Machine Learning Collaboration for Container Dwell Time Prediction via Data Standardization - https://arxiv.org/abs/2602.20540 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.20540.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Minseop Kim, Takhyeong Kim, Taekhyun Park, Hanbyeol Park, Hyerim Bae</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Import container dwell time (ICDT) prediction is a key task for improving productivity in container terminals, as accurate predictions enable the reduction of container re-handling operations by yard cranes. Achieving this objective requires accurately predicting the dwell time of individual containers. However, the primary determinants of dwell time-owner information and cargo information-are recorded as unstructured text, which limits their effective use in machine learning models. This study addresses this limitation by proposing a collaborative framework that integrates generative artificial intelligence (Gen AI) with machine learning. The proposed framework employs Gen AI to standardize unstructured information into standard international codes, with dynamic re-prediction triggered by electronic data interchange state updates, enabling the machine learning model to predict ICDT accurately. Extensive experiments conducted on real container terminal data demonstrate that the proposed methodology achieves a 13.88% improvement in mean absolute error compared to conventional models that do not utilize standardized information. Furthermore, applying the improved predictions to container stacking strategies achieves up to 14.68% reduction in the number of relocations, thereby empirically validating the potential of Gen AI to enhance productivity in container terminal operations. Overall, this study provides both technical and methodological insights into the adoption of Gen AI in port logistics and its effectiveness.</p> - https://arxiv.org/abs/2602.20540 - Tue, 24 Feb 2026 04:38:31 +0000 + OmniLottie: Generating Vector Animations via Parameterized Lottie Tokens + https://arxiv.org/abs/2603.02138 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.02138.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yiying Yang, Wei Cheng, Sijin Chen, Honghao Fu, Xianfang Zeng, Yujun Cai, Gang Yu, Xingjun Ma</p><p><b>Upvotes:</b> 134</p><p><b>Summary:</b> OmniLottie is a versatile framework that generates high quality vector animations from multi-modal instructions. For flexible motion and visual content control, we focus on Lottie, a light weight JSON formatting for both shapes and animation behaviors representation. However, the raw Lottie JSON files contain extensive invariant structural metadata and formatting tokens, posing significant challenges for learning vector animation generation. Therefore, we introduce a well designed Lottie tokenizer that transforms JSON files into structured sequences of commands and parameters representing shapes, animation functions and control parameters. Such tokenizer enables us to build OmniLottie upon pretrained vision language models to follow multi-modal interleaved instructions and generate high quality vector animations. To further advance research in vector animation generation, we curate MMLottie-2M, a large scale dataset of professionally designed vector animations paired with textual and visual annotations. With extensive experiments, we validate that OmniLottie can produce vivid and semantically aligned vector animations that adhere closely to multi modal human instructions.</p> + https://arxiv.org/abs/2603.02138 + Mon, 02 Mar 2026 17:59:05 +0000 - Communication-Inspired Tokenization for Structured Image Representations - https://arxiv.org/abs/2602.20731 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.20731.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Aram Davtyan, Yusuf Sahin, Yasaman Haghighi, Sebastian Stapf, Pablo Acuaviva, Alexandre Alahi, Paolo Favaro</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Discrete image tokenizers have emerged as a key component of modern vision and multimodal systems, providing a sequential interface for transformer-based architectures. However, most existing approaches remain primarily optimized for reconstruction and compression, often yielding tokens that capture local texture rather than object-level semantic structure. Inspired by the incremental and compositional nature of human communication, we introduce COMmunication inspired Tokenization (COMiT), a framework for learning structured discrete visual token sequences. COMiT constructs a latent message within a fixed token budget by iteratively observing localized image crops and recurrently updating its discrete representation. At each step, the model integrates new visual information while refining and reorganizing the existing token sequence. After several encoding iterations, the final message conditions a flow-matching decoder that reconstructs the full image. Both encoding and decoding are implemented within a single transformer model and trained end-to-end using a combination of flow-matching reconstruction and semantic representation alignment losses. Our experiments demonstrate that while semantic alignment provides grounding, attentive sequential tokenization is critical for inducing interpretable, object-centric token structure and substantially improving compositional generalization and relational reasoning over prior methods.</p> - https://arxiv.org/abs/2602.20731 - Tue, 24 Feb 2026 09:53:50 +0000 + SageBwd: A Trainable Low-bit Attention + https://arxiv.org/abs/2603.02170 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.02170.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jintao Zhang, Marco Chen, Haoxu Wang, Kai Jiang, Ion Stoica, Joseph E. Gonzalez, Jianfei Chen, Jun Zhu</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Low-bit attention, such as SageAttention, has emerged as an effective approach for accelerating model inference, but its applicability to training remains poorly understood. In prior work, we introduced SageBwd, a trainable INT8 attention that quantizes six of seven attention matrix multiplications while preserving fine-tuning performance. However, SageBwd exhibited a persistent performance gap to full-precision attention (FPA) during pre-training. In this work, we investigate why this gap occurs and demonstrate that SageBwd matches full-precision attention during pretraining. Through experiments and theoretical analysis, we reach a few important insights and conclusions: (i) QK-norm is necessary for stable training at large tokens per step, (ii) quantization errors primarily arise from the backward-pass score gradient dS, (iii) reducing tokens per step enables SageBwd to match FPA performance in pre-training, and (iv) K-smoothing remains essential for training stability, while Q-smoothing provides limited benefit during pre-training.</p> + https://arxiv.org/abs/2603.02170 + Mon, 02 Mar 2026 18:39:49 +0000 - PyVision-RL: Forging Open Agentic Vision Models via RL - https://arxiv.org/abs/2602.20739 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.20739.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shitian Zhao, Shaoheng Lin, Ming Li, Haoquan Zhang, Wenshuo Peng, Kaipeng Zhang, Chen Wei</p><p><b>Upvotes:</b> 29</p><p><b>Summary:</b> Reinforcement learning for agentic multimodal models often suffers from interaction collapse, where models learn to reduce tool usage and multi-turn reasoning, limiting the benefits of agentic behavior. We introduce PyVision-RL, a reinforcement learning framework for open-weight multimodal models that stabilizes training and sustains interaction. Our approach combines an oversampling-filtering-ranking rollout strategy with an accumulative tool reward to prevent collapse and encourage multi-turn tool use. Using a unified training pipeline, we develop PyVision-Image and PyVision-Video for image and video understanding. For video reasoning, PyVision-Video employs on-demand context construction, selectively sampling task-relevant frames during reasoning to significantly reduce visual token usage. Experiments show strong performance and improved efficiency, demonstrating that sustained interaction and on-demand visual processing are critical for scalable multimodal agents.</p> - https://arxiv.org/abs/2602.20739 - Tue, 24 Feb 2026 10:08:33 +0000 + Kiwi-Edit: Versatile Video Editing via Instruction and Reference Guidance + https://arxiv.org/abs/2603.02175 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.02175.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yiqi Lin, Guoqiang Liang, Ziyun Zeng, Zechen Bai, Yanzhe Chen, Mike Zheng Shou</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> Instruction-based video editing has witnessed rapid progress, yet current methods often struggle with precise visual control, as natural language is inherently limited in describing complex visual nuances. Although reference-guided editing offers a robust solution, its potential is currently bottlenecked by the scarcity of high-quality paired training data. To bridge this gap, we introduce a scalable data generation pipeline that transforms existing video editing pairs into high-fidelity training quadruplets, leveraging image generative models to create synthesized reference scaffolds. Using this pipeline, we construct RefVIE, a large-scale dataset tailored for instruction-reference-following tasks, and establish RefVIE-Bench for comprehensive evaluation. Furthermore, we propose a unified editing architecture, Kiwi-Edit, that synergizes learnable queries and latent visual features for reference semantic guidance. Our model achieves significant gains in instruction following and reference fidelity via a progressive multi-stage training curriculum. Extensive experiments demonstrate that our data and architecture establish a new state-of-the-art in controllable video editing. All datasets, models, and code is released at https://github.com/showlab/Kiwi-Edit.</p> + https://arxiv.org/abs/2603.02175 + Mon, 02 Mar 2026 18:46:28 +0000 - SIMSPINE: A Biomechanics-Aware Simulation Framework for 3D Spine Motion Annotation and Benchmarking - https://arxiv.org/abs/2602.20792 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.20792.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Muhammad Saif Ullah Khan, Didier Stricker</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Modeling spinal motion is fundamental to understanding human biomechanics, yet remains underexplored in computer vision due to the spine's complex multi-joint kinematics and the lack of large-scale 3D annotations. We present a biomechanics-aware keypoint simulation framework that augments existing human pose datasets with anatomically consistent 3D spinal keypoints derived from musculoskeletal modeling. Using this framework, we create the first open dataset, named SIMSPINE, which provides sparse vertebra-level 3D spinal annotations for natural full-body motions in indoor multi-camera capture without external restraints. With 2.14 million frames, this enables data-driven learning of vertebral kinematics from subtle posture variations and bridges the gap between musculoskeletal simulation and computer vision. In addition, we release pretrained baselines covering fine-tuned 2D detectors, monocular 3D pose lifting models, and multi-view reconstruction pipelines, establishing a unified benchmark for biomechanically valid spine motion estimation. Specifically, our 2D spine baselines improve the state-of-the-art from 0.63 to 0.80 AUC in controlled environments, and from 0.91 to 0.93 AP for in-the-wild spine tracking. Together, the simulation framework and SIMSPINE dataset advance research in vision-based biomechanics, motion analysis, and digital human modeling by enabling reproducible, anatomically grounded 3D spine estimation under natural conditions.</p> - https://arxiv.org/abs/2602.20792 - Tue, 24 Feb 2026 11:31:20 +0000 + Tool Verification for Test-Time Reinforcement Learning + https://arxiv.org/abs/2603.02203 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.02203.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ruotong Liao, Nikolai Röhrich, Xiaohan Wang, Yuhui Zhang, Yasaman Samadzadeh, Volker Tresp, Serena Yeung-Levy</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Test-time reinforcement learning (TTRL) has emerged as a promising paradigm for self-evolving large reasoning models (LRMs), enabling online adaptation on unlabeled test inputs via self-induced rewards through majority voting. However, a spurious yet high-frequency unverified consensus can become a biased and reinforced reward signal, leading to incorrect mode collapse. We address this failure mode with T^3RL (Tool-Verification for Test-Time Reinforcement Learning), which introduces test-time tool verification into reward estimation. Concretely, a verifier uses an external tool as evidence (e.g., from code execution) to upweight verified rollouts in a verification-aware voting, producing more reliable pseudo-labels for training. Across various math difficulties (MATH-500, AMC, and AIME 2024) and diverse backbone types, T^3RL significantly improves over TTRL, with larger gains on harder problems. More broadly, T^3RL can be viewed as verified online data synthesis, highlighting test-time tool verification as a key mechanism for stabilizing self-evolution.</p> + https://arxiv.org/abs/2603.02203 + Mon, 02 Mar 2026 18:57:52 +0000 - Dropping Anchor and Spherical Harmonics for Sparse-view Gaussian Splatting - https://arxiv.org/abs/2602.20933 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.20933.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shuangkang Fang, I-Chao Shen, Xuanyang Zhang, Zesheng Wang, Yufeng Wang, Wenrui Ding, Gang Yu, Takeo Igarashi</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Recent 3D Gaussian Splatting (3DGS) Dropout methods address overfitting under sparse-view conditions by randomly nullifying Gaussian opacities. However, we identify a neighbor compensation effect in these approaches: dropped Gaussians are often compensated by their neighbors, weakening the intended regularization. Moreover, these methods overlook the contribution of high-degree spherical harmonic coefficients (SH) to overfitting. To address these issues, we propose DropAnSH-GS, a novel anchor-based Dropout strategy. Rather than dropping Gaussians independently, our method randomly selects certain Gaussians as anchors and simultaneously removes their spatial neighbors. This effectively disrupts local redundancies near anchors and encourages the model to learn more robust, globally informed representations. Furthermore, we extend the Dropout to color attributes by randomly dropping higher-degree SH to concentrate appearance information in lower-degree SH. This strategy further mitigates overfitting and enables flexible post-training model compression via SH truncation. Experimental results demonstrate that DropAnSH-GS substantially outperforms existing Dropout methods with negligible computational overhead, and can be readily integrated into various 3DGS variants to enhance their performances. Project Website: https://sk-fun.fun/DropAnSH-GS</p> - https://arxiv.org/abs/2602.20933 - Tue, 24 Feb 2026 14:11:56 +0000 + Reasoning Core: A Scalable Procedural Data Generation Suite for Symbolic Pre-training and Post-Training + https://arxiv.org/abs/2603.02208 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.02208.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Valentin Lacombe, Valentin Quesnel, Damien Sileo</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Training on verifiable symbolic data is a promising way to expand the reasoning frontier of language models beyond what standard pre-training corpora provide. Yet existing procedural generators often rely on fixed puzzles or templates and do not deliver the distributional breadth needed at scale. We introduce Reasoning Core, a scalable suite that procedurally generates verifiable symbolic reasoning data across core formal domains: PDDL planning over randomized domains, first-order logic with equality, context-free grammar parsing and generation, causal reasoning over random Bayesian networks, and systems of equations. Each task is paired with an external solver for rigorous verification and admits continuous difficulty control for curriculum design. Examples can optionally include solver-derived reasoning traces, enabling supervised training from the earliest pre-training stages, and the same interface provides verifiable reward functions for reinforcement learning. Our experiments show that mixing Reasoning Core data into pre-training improves downstream reasoning while preserving, or slightly improving, language modeling quality. Zero-shot evaluations confirm these tasks challenge frontier models such as GPT-5. The code and data are publicly available under the MIT license.</p> + https://arxiv.org/abs/2603.02208 + Mon, 02 Mar 2026 18:59:29 +0000 - The Art of Efficient Reasoning: Data, Reward, and Optimization - https://arxiv.org/abs/2602.20945 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.20945.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Taiqiang Wu, Zenan Zu, Bo Zhou, Ngai Wong</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Large Language Models (LLMs) consistently benefit from scaled Chain-of-Thought (CoT) reasoning, but also suffer from heavy computational overhead. To address this issue, efficient reasoning aims to incentivize short yet accurate thinking trajectories, typically through reward shaping with Reinforcement Learning (RL). In this paper, we systematically investigate the mechanics of efficient reasoning for LLMs. For comprehensive evaluation, we advocate for more fine-grained metrics, including length distribution conditioned on correctness and performance across a wide spectrum of token budgets ranging from 2k to 32k. First, we reveal that the training process follows a two-stage paradigm: length adaptation and reasoning refinement. After that, we conduct extensive experiments (about 0.2 million GPU hours) in a unified protocol, deconstructing training prompts and rollouts, reward shaping, and optimization strategies. In particular, a key finding is to train on relatively easier prompts, ensuring the density of positive reward signals and thus avoiding the length collapse. Meanwhile, the learned length bias can be generalized across domains. We distill all findings into valuable insights and practical guidelines, and further validate them across the Qwen3 series, ranging from 0.6B to 30B, demonstrating the robustness and generalization.</p> - https://arxiv.org/abs/2602.20945 - Tue, 24 Feb 2026 14:28:16 +0000 + HiFi-Inpaint: Towards High-Fidelity Reference-Based Inpainting for Generating Detail-Preserving Human-Product Images + https://arxiv.org/abs/2603.02210 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.02210.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yichen Liu, Donghao Zhou, Jie Wang, Xin Gao, Guisheng Liu, Jiatong Li, Quanwei Zhang, Qiang Lyu, Lanqing Guo, Shilei Wen, Weiqiang Wang, Pheng-Ann Heng</p><p><b>Upvotes:</b> 26</p><p><b>Summary:</b> Human-product images, which showcase the integration of humans and products, play a vital role in advertising, e-commerce, and digital marketing. The essential challenge of generating such images lies in ensuring the high-fidelity preservation of product details. Among existing paradigms, reference-based inpainting offers a targeted solution by leveraging product reference images to guide the inpainting process. However, limitations remain in three key aspects: the lack of diverse large-scale training data, the struggle of current models to focus on product detail preservation, and the inability of coarse supervision for achieving precise guidance. To address these issues, we propose HiFi-Inpaint, a novel high-fidelity reference-based inpainting framework tailored for generating human-product images. HiFi-Inpaint introduces Shared Enhancement Attention (SEA) to refine fine-grained product features and Detail-Aware Loss (DAL) to enforce precise pixel-level supervision using high-frequency maps. Additionally, we construct a new dataset, HP-Image-40K, with samples curated from self-synthesis data and processed with automatic filtering. Experimental results show that HiFi-Inpaint achieves state-of-the-art performance, delivering detail-preserving human-product images.</p> + https://arxiv.org/abs/2603.02210 + Mon, 02 Mar 2026 18:59:36 +0000 - See and Fix the Flaws: Enabling VLMs and Diffusion Models to Comprehend Visual Artifacts via Agentic Data Synthesis - https://arxiv.org/abs/2602.20951 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.20951.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jaehyun Park, Minyoung Ahn, Minkyu Kim, Jonghyun Lee, Jae-Gil Lee, Dongmin Park</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Despite recent advances in diffusion models, AI generated images still often contain visual artifacts that compromise realism. Although more thorough pre-training and bigger models might reduce artifacts, there is no assurance that they can be completely eliminated, which makes artifact mitigation a highly crucial area of study. Previous artifact-aware methodologies depend on human-labeled artifact datasets, which are costly and difficult to scale, underscoring the need for an automated approach to reliably acquire artifact-annotated datasets. In this paper, we propose ArtiAgent, which efficiently creates pairs of real and artifact-injected images. It comprises three agents: a perception agent that recognizes and grounds entities and subentities from real images, a synthesis agent that introduces artifacts via artifact injection tools through novel patch-wise embedding manipulation within a diffusion transformer, and a curation agent that filters the synthesized artifacts and generates both local and global explanations for each instance. Using ArtiAgent, we synthesize 100K images with rich artifact annotations and demonstrate both efficacy and versatility across diverse applications. Code is available at link.</p> - https://arxiv.org/abs/2602.20951 - Tue, 24 Feb 2026 14:34:13 +0000 + PRISM: Pushing the Frontier of Deep Think via Process Reward Model-Guided Inference + https://arxiv.org/abs/2603.02479 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.02479.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Rituraj Sharma, Weiyuan Chen, Noah Provenzano, Tu Vu</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> DEEPTHINK methods improve reasoning by generating, refining, and aggregating populations of candidate solutions, which enables strong performance on complex mathematical and scientific tasks. However, existing frameworks often lack reliable correctness signals during inference, which creates a population-enhancement bottleneck where deeper deliberation amplifies errors, suppresses correct minority solutions, and yields weak returns to additional compute. In this paper, we introduce a functional decomposition of DEEPTHINK systems and propose PRISM, a Process Reward Model (PRM)-guided inference algorithm that uses step-level verification to guide both population refinement and solution aggregation. During refinement, PRISM treats candidate solutions as particles in a PRM-defined energy landscape and reshapes the population through score-guided resampling and stochastic refinement, which concentrates probability mass on higher-quality reasoning while preserving diversity. Across mathematics and science benchmarks, PRISM is competitive with or outperforms existing DEEPTHINK methods, reaching 90.0%, 75.4%, and 71.4% with gpt-oss-20b on AIME25, HMMT25, and GPQA Diamond, respectively, while matching or exceeding gpt-oss-120b. Additionally, our analysis shows that PRISM produces consistent net-directional correction during refinement, remains reliable when the initial population contains few correct candidates, and often lies on the compute-accuracy Pareto frontier.</p> + https://arxiv.org/abs/2603.02479 + Tue, 03 Mar 2026 00:03:42 +0000 - From Perception to Action: An Interactive Benchmark for Vision Reasoning - https://arxiv.org/abs/2602.21015 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.21015.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuhao Wu, Maojia Song, Yihuai Lan, Lei Wang, Zhiqiang Hu, Yao Xiao, Heng Zhou, Weihua Zheng, Dylan Raharja, Soujanya Poria, Roy Ka-Wei Lee</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> Understanding the physical structure is essential for real-world applications such as embodied agents, interactive design, and long-horizon manipulation. Yet, prevailing Vision-Language Model (VLM) evaluations still center on structure-agnostic, single-turn setups (e.g., VQA), which fail to assess agents' ability to reason about how geometry, contact, and support relations jointly constrain what actions are possible in a dynamic environment. To address this gap, we introduce the Causal Hierarchy of Actions and Interactions (CHAIN) benchmark, an interactive 3D, physics-driven testbed designed to evaluate whether models can understand, plan, and execute structured action sequences grounded in physical constraints. CHAIN shifts evaluation from passive perception to active problem solving, spanning tasks such as interlocking mechanical puzzles and 3D stacking and packing. We conduct a comprehensive study of state-of-the-art VLMs and diffusion-based models under unified interactive settings. Our results show that top-performing models still struggle to internalize physical structure and causal constraints, often failing to produce reliable long-horizon plans and cannot robustly translate perceived structure into effective actions. The project is available at https://social-ai-studio.github.io/CHAIN/.</p> - https://arxiv.org/abs/2602.21015 - Tue, 24 Feb 2026 15:33:02 +0000 + MUSE: A Run-Centric Platform for Multimodal Unified Safety Evaluation of Large Language Models + https://arxiv.org/abs/2603.02482 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.02482.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhongxi Wang, Yueqian Lin, Jingyang Zhang, Hai Helen Li, Yiran Chen</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Safety evaluation and red-teaming of large language models remain predominantly text-centric, and existing frameworks lack the infrastructure to systematically test whether alignment generalizes to audio, image, and video inputs. We present MUSE (Multimodal Unified Safety Evaluation), an open-source, run-centric platform that integrates automatic cross-modal payload generation, three multi-turn attack algorithms (Crescendo, PAIR, Violent Durian), provider-agnostic model routing, and an LLM judge with a five-level safety taxonomy into a single browser-based system. A dual-metric framework distinguishes hard Attack Success Rate (Compliance only) from soft ASR (including Partial Compliance), capturing partial information leakage that binary metrics miss. To probe whether alignment generalizes across modality boundaries, we introduce Inter-Turn Modality Switching (ITMS), which augments multi-turn attacks with per-turn modality rotation. Experiments across six multimodal LLMs from four providers show that multi-turn strategies can achieve up to 90-100% ASR against models with near-perfect single-turn refusal. ITMS does not uniformly raise final ASR on already-saturated baselines, but accelerates convergence by destabilizing early-turn defenses, and ablation reveals that the direction of modality effects is model-family-specific rather than universal, underscoring the need for provider-aware cross-modal safety testing.</p> + https://arxiv.org/abs/2603.02482 + Tue, 03 Mar 2026 00:10:23 +0000 - OmniOCR: Generalist OCR for Ethnic Minority Languages - https://arxiv.org/abs/2602.21042 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.21042.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bonan Liu, Zeyu Zhang, Bingbing Meng, Han Wang, Hanshuo Zhang, Chengping Wang, Daji Ergu, Ying Cai</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Optical character recognition (OCR) has advanced rapidly with deep learning and multimodal models, yet most methods focus on well-resourced scripts such as Latin and Chinese. Ethnic minority languages remain underexplored due to complex writing systems, scarce annotations, and diverse historical and modern forms, making generalization in low-resource or zero-shot settings challenging. To address these challenges, we present OmniOCR, a universal framework for ethnic minority scripts. OmniOCR introduces Dynamic Low-Rank Adaptation (Dynamic LoRA) to allocate model capacity across layers and scripts, enabling effective adaptation while preserving knowledge.A sparsity regularization prunes redundant updates, ensuring compact and efficient adaptation without extra inference cost. Evaluations on TibetanMNIST, Shui, ancient Yi, and Dongba show that OmniOCR outperforms zero-shot foundation models and standard post training, achieving state-of-the-art accuracy with superior parameter efficiency, and compared with the state-of-the-art baseline models, it improves accuracy by 39%-66% on these four datasets. Code: https://github.com/AIGeeksGroup/OmniOCR.</p> - https://arxiv.org/abs/2602.21042 - Tue, 24 Feb 2026 16:02:49 +0000 + MemSifter: Offloading LLM Memory Retrieval via Outcome-Driven Proxy Reasoning + https://arxiv.org/abs/2603.03379 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.03379.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiejun Tan, Zhicheng Dou, Liancheng Zhang, Yuyang Hu, Yiruo Cheng, Ji-Rong Wen</p><p><b>Upvotes:</b> 26</p><p><b>Summary:</b> As Large Language Models (LLMs) are increasingly used for long-duration tasks, maintaining effective long-term memory has become a critical challenge. Current methods often face a trade-off between cost and accuracy. Simple storage methods often fail to retrieve relevant information, while complex indexing methods (such as memory graphs) require heavy computation and can cause information loss. Furthermore, relying on the working LLM to process all memories is computationally expensive and slow. To address these limitations, we propose MemSifter, a novel framework that offloads the memory retrieval process to a small-scale proxy model. Instead of increasing the burden on the primary working LLM, MemSifter uses a smaller model to reason about the task before retrieving the necessary information. This approach requires no heavy computation during the indexing phase and adds minimal overhead during inference. To optimize the proxy model, we introduce a memory-specific Reinforcement Learning (RL) training paradigm. We design a task-outcome-oriented reward based on the working LLM's actual performance in completing the task. The reward measures the actual contribution of retrieved memories by mutiple interactions with the working LLM, and discriminates retrieved rankings by stepped decreasing contributions. Additionally, we employ training techniques such as Curriculum Learning and Model Merging to improve performance. We evaluated MemSifter on eight LLM memory benchmarks, including Deep Research tasks. The results demonstrate that our method meets or exceeds the performance of existing state-of-the-art approaches in both retrieval accuracy and final task completion. MemSifter offers an efficient and scalable solution for long-term LLM memory. We have open-sourced the model weights, code, and training data to support further research.</p> + https://arxiv.org/abs/2603.03379 + Tue, 03 Mar 2026 02:57:38 +0000 - OCR-Agent: Agentic OCR with Capability and Memory Reflection - https://arxiv.org/abs/2602.21053 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.21053.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shimin Wen, Zeyu Zhang, Xingdou Bian, Hongjie Zhu, Lulu He, Layi Shama, Daji Ergu, Ying Cai</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Large Vision-Language Models (VLMs) have demonstrated significant potential on complex visual understanding tasks through iterative optimization methods.However, these models generally lack effective self-correction mechanisms, making it difficult for them to independently rectify cognitive biases. Consequently, during multi-turn revisions, they often fall into repetitive and ineffective attempts, failing to achieve stable improvements in answer quality.To address this issue, we propose a novel iterative self-correction framework that endows models with two key capabilities: Capability Reflection and Memory Reflection. This framework guides the model to first diagnose errors and generate a correction plan via Capability Reflection, then leverage Memory Reflection to review past attempts to avoid repetition and explore new solutions, and finally, optimize the answer through rigorous re-reasoning. Experiments on the challenging OCRBench v2 benchmark show that OCR-Agent outperforms the current open-source SOTA model InternVL3-8B by +2.0 on English and +1.2 on Chinese subsets, while achieving state-of-the-art results in Visual Understanding (79.9) and Reasoning (66.5) - surpassing even larger fine-tuned models. Our method demonstrates that structured, self-aware reflection can significantly enhance VLMs' reasoning robustness without additional training. Code: https://github.com/AIGeeksGroup/OCR-Agent.</p> - https://arxiv.org/abs/2602.21053 - Tue, 24 Feb 2026 16:10:27 +0000 + Track4World: Feedforward World-centric Dense 3D Tracking of All Pixels + https://arxiv.org/abs/2603.02573 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.02573.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiahao Lu, Jiayi Xu, Wenbo Hu, Ruijie Zhu, Chengfeng Zhao, Sai-Kit Yeung, Ying Shan, Yuan Liu</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Estimating the 3D trajectory of every pixel from a monocular video is crucial and promising for a comprehensive understanding of the 3D dynamics of videos. Recent monocular 3D tracking works demonstrate impressive performance, but are limited to either tracking sparse points on the first frame or a slow optimization-based framework for dense tracking. In this paper, we propose a feedforward model, called Track4World, enabling an efficient holistic 3D tracking of every pixel in the world-centric coordinate system. Built on the global 3D scene representation encoded by a VGGT-style ViT, Track4World applies a novel 3D correlation scheme to simultaneously estimate the pixel-wise 2D and 3D dense flow between arbitrary frame pairs. The estimated scene flow, along with the reconstructed 3D geometry, enables subsequent efficient 3D tracking of every pixel of this video. Extensive experiments on multiple benchmarks demonstrate that our approach consistently outperforms existing methods in 2D/3D flow estimation and 3D tracking, highlighting its robustness and scalability for real-world 4D reconstruction tasks.</p> + https://arxiv.org/abs/2603.02573 + Tue, 03 Mar 2026 03:45:43 +0000 - The Diffusion Duality, Chapter II: Ψ-Samplers and Efficient Curriculum - https://arxiv.org/abs/2602.21185 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.21185.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Justin Deschenaux, Caglar Gulcehre, Subham Sekhar Sahoo</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Uniform-state discrete diffusion models excel at few-step generation and guidance due to their ability to self-correct, making them preferred over autoregressive or Masked diffusion models in these settings. However, their sampling quality plateaus with ancestral samplers as the number of steps increases. We introduce a family of Predictor-Corrector (PC) samplers for discrete diffusion that generalize prior methods and apply to arbitrary noise processes. When paired with uniform-state diffusion, our samplers outperform ancestral sampling on both language and image modeling, achieving lower generative perplexity at matched unigram entropy on OpenWebText and better FID/IS scores on CIFAR10. Crucially, unlike conventional samplers, our PC methods continue to improve with more sampling steps. Taken together, these findings call into question the assumption that Masked diffusion is the inevitable future of diffusion-based language modeling. Beyond sampling, we develop a memory-efficient curriculum for the Gaussian relaxation training phase, reducing training time by 25% and memory by 33% compared to Duo while maintaining comparable perplexity on OpenWebText and LM1B and strong downstream performance. We release code, checkpoints, and a video-tutorial on: https://s-sahoo.com/duo-ch2</p> - https://arxiv.org/abs/2602.21185 - Tue, 24 Feb 2026 18:35:22 +0000 + How Controllable Are Large Language Models? A Unified Evaluation across Behavioral Granularities + https://arxiv.org/abs/2603.02578 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.02578.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ziwen Xu, Kewei Xu, Haoming Xu, Haiwen Hong, Longtao Huang, Hui Xue, Ningyu Zhang, Yongliang Shen, Guozhou Zheng, Huajun Chen, Shumin Deng</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> Large Language Models (LLMs) are increasingly deployed in socially sensitive domains, yet their unpredictable behaviors, ranging from misaligned intent to inconsistent personality, pose significant risks. We introduce SteerEval, a hierarchical benchmark for evaluating LLM controllability across three domains: language features, sentiment, and personality. Each domain is structured into three specification levels: L1 (what to express), L2 (how to express), and L3 (how to instantiate), connecting high-level behavioral intent to concrete textual output. Using SteerEval, we systematically evaluate contemporary steering methods, revealing that control often degrades at finer-grained levels. Our benchmark offers a principled and interpretable framework for safe and controllable LLM behavior, serving as a foundation for future research.</p> + https://arxiv.org/abs/2603.02578 + Tue, 03 Mar 2026 03:50:13 +0000 - On Data Engineering for Scaling LLM Terminal Capabilities - https://arxiv.org/abs/2602.21193 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.21193.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Renjie Pi, Grace Lam, Mohammad Shoeybi, Pooya Jannaty, Bryan Catanzaro, Wei Ping</p><p><b>Upvotes:</b> 89</p><p><b>Summary:</b> Despite rapid recent progress in the terminal capabilities of large language models, the training data strategies behind state-of-the-art terminal agents remain largely undisclosed. We address this gap through a systematic study of data engineering practices for terminal agents, making two key contributions: (1) Terminal-Task-Gen, a lightweight synthetic task generation pipeline that supports seed-based and skill-based task construction, and (2) a comprehensive analysis of data and training strategies, including filtering, curriculum learning, long context training, and scaling behavior. Our pipeline yields Terminal-Corpus, a large-scale open-source dataset for terminal tasks. Using this dataset, we train Nemotron-Terminal, a family of models initialized from Qwen3(8B, 14B, 32B) that achieve substantial gains on Terminal-Bench 2.0: Nemotron-Terminal-8B improves from 2.5% to 13.0% Nemotron-Terminal-14B improves from 4.0% to 20.2%, and Nemotron-Terminal-32B improves from 3.4% to 27.4%, matching the performance of significantly larger models. To accelerate research in this domain, we open-source our model checkpoints and most of our synthetic datasets at https://huggingface.co/collections/nvidia/nemotron-terminal.</p> - https://arxiv.org/abs/2602.21193 - Tue, 24 Feb 2026 18:51:04 +0000 + Heterogeneous Agent Collaborative Reinforcement Learning + https://arxiv.org/abs/2603.02604 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.02604.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhixia Zhang, Zixuan Huang, Xin Xia, Deqing Wang, Fuzhen Zhuang, Shuai Ma, Ning Ding, Yaodong Yang, Jianxin Li, Yikun Ban</p><p><b>Upvotes:</b> 146</p><p><b>Summary:</b> We introduce Heterogeneous Agent Collaborative Reinforcement Learning (HACRL), a new learning paradigm that addresses the inefficiencies of isolated on-policy optimization. HACRL enables collaborative optimization with independent execution: heterogeneous agents share verified rollouts during training to mutually improve, while operating independently at inference time. Unlike LLM-based multi-agent reinforcement learning (MARL), HACRL does not require coordinated deployment, and unlike on-/off-policy distillation, it enables bidirectional mutual learning among heterogeneous agents rather than one-directional teacher-to-student transfer. Building on this paradigm, we propose HACPO, a collaborative RL algorithm that enables principled rollout sharing to maximize sample utilization and cross-agent knowledge transfer. To mitigate capability discrepancies and policy distribution shifts, HACPO introduces four tailored mechanisms with theoretical guarantees on unbiased advantage estimation and optimization correctness. Extensive experiments across diverse heterogeneous model combinations and reasoning benchmarks show that HACPO consistently improves all participating agents, outperforming GSPO by an average of 3.3\% while using only half the rollout cost.</p> + https://arxiv.org/abs/2603.02604 + Tue, 03 Mar 2026 05:09:49 +0000 - Untied Ulysses: Memory-Efficient Context Parallelism via Headwise Chunking - https://arxiv.org/abs/2602.21196 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.21196.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ravi Ghadia, Maksim Abraham, Sergei Vorobyov, Max Ryabinin</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Efficiently processing long sequences with Transformer models usually requires splitting the computations across accelerators via context parallelism. The dominant approaches in this family of methods, such as Ring Attention or DeepSpeed Ulysses, enable scaling over the context dimension but do not focus on memory efficiency, which limits the sequence lengths they can support. More advanced techniques, such as Fully Pipelined Distributed Transformer or activation offloading, can further extend the possible context length at the cost of training throughput. In this paper, we present UPipe, a simple yet effective context parallelism technique that performs fine-grained chunking at the attention head level. This technique significantly reduces the activation memory usage of self-attention, breaking the activation memory barrier and unlocking much longer context lengths. Our approach reduces intermediate tensor memory usage in the attention layer by as much as 87.5% for 32B Transformers, while matching previous context parallelism techniques in terms of training speed. UPipe can support the context length of 5M tokens when training Llama3-8B on a single 8timesH100 node, improving upon prior methods by over 25%.</p> - https://arxiv.org/abs/2602.21196 - Tue, 24 Feb 2026 18:54:39 +0000 + DREAM: Where Visual Understanding Meets Text-to-Image Generation + https://arxiv.org/abs/2603.02667 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.02667.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chao Li, Tianhong Li, Sai Vidyaranya Nuthalapati, Hong-You Chen, Satya Narayan Shukla, Yonghuan Yang, Jun Xiao, Xiangjun Fan, Aashu Singh, Dina Katabi, Shlok Kumar Mishra</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Unifying visual representation learning and text-to-image (T2I) generation within a single model remains a central challenge in multimodal learning. We introduce DREAM, a unified framework that jointly optimizes discriminative and generative objectives, while learning strong visual representations. DREAM is built on two key techniques: During training, Masking Warmup, a progressive masking schedule, begins with minimal masking to establish the contrastive alignment necessary for representation learning, then gradually transitions to full masking for stable generative training. At inference, DREAM employs Semantically Aligned Decoding to align partially masked image candidates with the target text and select the best one for further decoding, improving text-image fidelity (+6.3%) without external rerankers. Trained solely on CC12M, DREAM achieves 72.7% ImageNet linear-probing accuracy (+1.1% over CLIP) and an FID of 4.25 (+6.2% over FLUID), with consistent gains in few-shot classification, semantic segmentation, and depth estimation. These results demonstrate that discriminative and generative objectives can be synergistic, allowing unified multimodal models that excel at both visual understanding and generation.</p> + https://arxiv.org/abs/2603.02667 + Tue, 03 Mar 2026 06:54:19 +0000 - Learning from Trials and Errors: Reflective Test-Time Planning for Embodied LLMs - https://arxiv.org/abs/2602.21198 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.21198.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yining Hong, Huang Huang, Manling Li, Li Fei-Fei, Jiajun Wu, Yejin Choi</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Embodied LLMs endow robots with high-level task reasoning, but they cannot reflect on what went wrong or why, turning deployment into a sequence of independent trials where mistakes repeat rather than accumulate into experience. Drawing upon human reflective practitioners, we introduce Reflective Test-Time Planning, which integrates two modes of reflection: reflection-in-action, where the agent uses test-time scaling to generate and score multiple candidate actions using internal reflections before execution; and reflection-on-action, which uses test-time training to update both its internal reflection model and its action policy based on external reflections after execution. We also include retrospective reflection, allowing the agent to re-evaluate earlier decisions and perform model updates with hindsight for proper long-horizon credit assignment. Experiments on our newly-designed Long-Horizon Household benchmark and MuJoCo Cupboard Fitting benchmark show significant gains over baseline models, with ablative studies validating the complementary roles of reflection-in-action and reflection-on-action. Qualitative analyses, including real-robot trials, highlight behavioral correction through reflection.</p> - https://arxiv.org/abs/2602.21198 - Tue, 24 Feb 2026 18:55:18 +0000 + Next Embedding Prediction Makes World Models Stronger + https://arxiv.org/abs/2603.02765 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.02765.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> George Bredis, Nikita Balagansky, Daniil Gavrilov, Ruslan Rakhimov</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Capturing temporal dependencies is critical for model-based reinforcement learning (MBRL) in partially observable, high-dimensional domains. We introduce NE-Dreamer, a decoder-free MBRL agent that leverages a temporal transformer to predict next-step encoder embeddings from latent state sequences, directly optimizing temporal predictive alignment in representation space. This approach enables NE-Dreamer to learn coherent, predictive state representations without reconstruction losses or auxiliary supervision. On the DeepMind Control Suite, NE-Dreamer matches or exceeds the performance of DreamerV3 and leading decoder-free agents. On a challenging subset of DMLab tasks involving memory and spatial reasoning, NE-Dreamer achieves substantial gains. These results establish next-embedding prediction with temporal transformers as an effective, scalable framework for MBRL in complex, partially observable environments.</p> + https://arxiv.org/abs/2603.02765 + Tue, 03 Mar 2026 09:04:28 +0000 - Aletheia tackles FirstProof autonomously - https://arxiv.org/abs/2602.21201 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.21201.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tony Feng, Junehyuk Jung, Sang-hyun Kim, Carlo Pagano, Sergei Gukov, Chiang-Chiang Tsai, David Woodruff, Adel Javanmard, Aryan Mokhtari, Dawsen Hwang, Yuri Chervonyi, Jonathan N. Lee, Garrett Bingham, Trieu H. Trinh, Vahab Mirrokni, Quoc V. Le, Thang Luong</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> We report the performance of Aletheia (Feng et al., 2026b), a mathematics research agent powered by Gemini 3 Deep Think, on the inaugural FirstProof challenge. Within the allowed timeframe of the challenge, Aletheia autonomously solved 6 problems (2, 5, 7, 8, 9, 10) out of 10 according to majority expert assessments; we note that experts were not unanimous on Problem 8 (only). For full transparency, we explain our interpretation of FirstProof and disclose details about our experiments as well as our evaluation. Raw prompts and outputs are available at https://github.com/google-deepmind/superhuman/tree/main/aletheia.</p> - https://arxiv.org/abs/2602.21201 - Tue, 24 Feb 2026 18:56:10 +0000 + NOVA: Sparse Control, Dense Synthesis for Pair-Free Video Editing + https://arxiv.org/abs/2603.02802 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.02802.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tianlin Pan, Jiayi Dai, Chenpu Yuan, Zhengyao Lv, Binxin Yang, Hubery Yin, Chen Li, Jing Lyu, Caifeng Shan, Chenyang Si</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Recent video editing models have achieved impressive results, but most still require large-scale paired datasets. Collecting such naturally aligned pairs at scale remains highly challenging and constitutes a critical bottleneck, especially for local video editing data. Existing workarounds transfer image editing to video through global motion control for pair-free video editing, but such designs struggle with background and temporal consistency. In this paper, we propose NOVA: Sparse Control \& Dense Synthesis, a new framework for unpaired video editing. Specifically, the sparse branch provides semantic guidance through user-edited keyframes distributed across the video, and the dense branch continuously incorporates motion and texture information from the original video to maintain high fidelity and coherence. Moreover, we introduce a degradation-simulation training strategy that enables the model to learn motion reconstruction and temporal consistency by training on artificially degraded videos, thus eliminating the need for paired data. Our extensive experiments demonstrate that NOVA outperforms existing approaches in edit fidelity, motion preservation, and temporal coherence.</p> + https://arxiv.org/abs/2603.02802 + Tue, 03 Mar 2026 09:41:06 +0000 - Multi-Vector Index Compression in Any Modality - https://arxiv.org/abs/2602.21202 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.21202.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hanxiang Qin, Alexander Martin, Rohan Jha, Chunsheng Zuo, Reno Kriz, Benjamin Van Durme</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> We study efficient multi-vector retrieval for late interaction in any modality. Late interaction has emerged as a dominant paradigm for information retrieval in text, images, visual documents, and videos, but its computation and storage costs grow linearly with document length, making it costly for image-, video-, and audio-rich corpora. To address this limitation, we explore query-agnostic methods for compressing multi-vector document representations under a constant vector budget. We introduce four approaches for index compression: sequence resizing, memory tokens, hierarchical pooling, and a novel attention-guided clustering (AGC). AGC uses an attention-guided mechanism to identify the most semantically salient regions of a document as cluster centroids and to weight token aggregation. Evaluating these methods on retrieval tasks spanning text (BEIR), visual-document (ViDoRe), and video (MSR-VTT, MultiVENT 2.0), we show that attention-guided clustering consistently outperforms other parameterized compression methods (sequence resizing and memory tokens), provides greater flexibility in index size than non-parametric hierarchical clustering, and achieves competitive or improved performance compared to a full, uncompressed index. The source code is available at: github.com/hanxiangqin/omni-col-press.</p> - https://arxiv.org/abs/2602.21202 - Tue, 24 Feb 2026 18:57:33 +0000 + Kling-MotionControl Technical Report + https://arxiv.org/abs/2603.03160 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.03160.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kling Team, Jialu Chen, Yikang Ding, Zhixue Fang, Kun Gai, Kang He, Xu He, Jingyun Hua, Mingming Lao, Xiaohan Li, Hui Liu, Jiwen Liu, Xiaoqiang Liu, Fan Shi, Xiaoyu Shi, Peiqin Sun, Songlin Tang, Pengfei Wan, Tiancheng Wen, Zhiyong Wu, Haoxian Zhang, Runze Zhao, Yuanxing Zhang, Yan Zhou</p><p><b>Upvotes:</b> 25</p><p><b>Summary:</b> Character animation aims to generate lifelike videos by transferring motion dynamics from a driving video to a reference image. Recent strides in generative models have paved the way for high-fidelity character animation. In this work, we present Kling-MotionControl, a unified DiT-based framework engineered specifically for robust, precise, and expressive holistic character animation. Leveraging a divide-and-conquer strategy within a cohesive system, the model orchestrates heterogeneous motion representations tailored to the distinct characteristics of body, face, and hands, effectively reconciling large-scale structural stability with fine-grained articulatory expressiveness. To ensure robust cross-identity generalization, we incorporate adaptive identity-agnostic learning, facilitating natural motion retargeting for diverse characters ranging from realistic humans to stylized cartoons. Simultaneously, we guarantee faithful appearance preservation through meticulous identity injection and fusion designs, further supported by a subject library mechanism that leverages comprehensive reference contexts. To ensure practical utility, we implement an advanced acceleration framework utilizing multi-stage distillation, boosting inference speed by over 10x. Kling-MotionControl distinguishes itself through intelligent semantic motion understanding and precise text responsiveness, allowing for flexible control beyond visual inputs. Human preference evaluations demonstrate that Kling-MotionControl delivers superior performance compared to leading commercial and open-source solutions, achieving exceptional fidelity in holistic motion control, open domain generalization, and visual quality and coherence. These results establish Kling-MotionControl as a robust solution for high-quality, controllable, and lifelike character animation.</p> + https://arxiv.org/abs/2603.03160 + Tue, 03 Mar 2026 17:02:45 +0000 - Test-Time Training with KV Binding Is Secretly Linear Attention - https://arxiv.org/abs/2602.21204 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.21204.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junchen Liu, Sven Elflein, Or Litany, Zan Gojcic, Ruilong Li</p><p><b>Upvotes:</b> 28</p><p><b>Summary:</b> Test-time training (TTT) with KV binding as sequence modeling layer is commonly interpreted as a form of online meta-learning that memorizes a key-value mapping at test time. However, our analysis reveals multiple phenomena that contradict this memorization-based interpretation. Motivated by these findings, we revisit the formulation of TTT and show that a broad class of TTT architectures can be expressed as a form of learned linear attention operator. Beyond explaining previously puzzling model behaviors, this perspective yields multiple practical benefits: it enables principled architectural simplifications, admits fully parallel formulations that preserve performance while improving efficiency, and provides a systematic reduction of diverse TTT variants to a standard linear attention form. Overall, our results reframe TTT not as test-time memorization, but as learned linear attention with enhanced representational capacity.</p> - https://arxiv.org/abs/2602.21204 - Tue, 24 Feb 2026 18:59:30 +0000 + BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing? + https://arxiv.org/abs/2603.03194 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.03194.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Guoxin Chen, Fanzhe Meng, Jiale Zhao, Minghao Li, Daixuan Cheng, Huatong Song, Jie Chen, Yuzhi Lin, Hui Chen, Xin Zhao, Ruihua Song, Chang Liu, Cheng Chen, Kai Jia, Ji-Rong Wen</p><p><b>Upvotes:</b> 50</p><p><b>Summary:</b> Current benchmarks for code agents primarily assess narrow, repository-specific fixes, overlooking critical real-world challenges such as cross-repository reasoning, domain-specialized problem solving, dependency-driven migration, and full-repository generation. To address this gap, we introduce BeyondSWE, a comprehensive benchmark that broadens existing evaluations along two axes - resolution scope and knowledge scope - using 500 real-world instances across four distinct settings. Experimental results reveal a significant capability gap: even frontier models plateau below 45% success, and no single model performs consistently across task types. To systematically investigate the role of external knowledge, we develop SearchSWE, a framework that integrates deep search with coding abilities. Our experiments show that search augmentation yields inconsistent gains and can in some cases degrade performance, highlighting the difficulty of emulating developer-like workflows that interleave search and reasoning during coding tasks. This work offers both a realistic, challenging evaluation benchmark and a flexible framework to advance research toward more capable code agents.</p> + https://arxiv.org/abs/2603.03194 + Tue, 03 Mar 2026 17:52:01 +0000 - Overconfident Errors Need Stronger Correction: Asymmetric Confidence Penalties for Reinforcement Learning - https://arxiv.org/abs/2602.21420 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.21420.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuanda Xu, Hejian Sang, Zhengze Zhou, Ran He, Zhipeng Wang</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Reinforcement Learning with Verifiable Rewards (RLVR) has become the leading paradigm for enhancing reasoning in Large Language Models (LLMs). However, standard RLVR algorithms suffer from a well-documented pathology: while they improve Pass@1 accuracy through sharpened sampling, they simultaneously narrow the model's reasoning boundary and reduce generation diversity. We identify a root cause that existing methods overlook: the uniform penalization of errors. Current approaches -- whether data-filtering methods that select prompts by difficulty, or advantage normalization schemes -- treat all incorrect rollouts within a group identically. We show that this uniformity allows overconfident errors (incorrect reasoning paths that the RL process has spuriously reinforced) to persist and monopolize probability mass, ultimately suppressing valid exploratory trajectories. To address this, we propose the Asymmetric Confidence-aware Error Penalty (ACE). ACE introduces a per-rollout confidence shift metric, c_i = log(pi_theta(y_i|x) / pi_ref(y_i|x)), to dynamically modulate negative advantages. Theoretically, we demonstrate that ACE's gradient can be decomposed into the gradient of a selective regularizer restricted to overconfident errors, plus a well-characterized residual that partially moderates the regularizer's strength. We conduct extensive experiments fine-tuning Qwen2.5-Math-7B, Qwen3-8B-Base, and Llama-3.1-8B-Instruct on the DAPO-Math-17K dataset using GRPO and DAPO within the VERL framework. Evaluated on MATH-500 and AIME 2025, ACE composes seamlessly with existing methods and consistently improves the full Pass@k spectrum across all three model families and benchmarks.</p> - https://arxiv.org/abs/2602.21420 - Tue, 24 Feb 2026 22:46:43 +0000 + Chain of World: World Model Thinking in Latent Motion + https://arxiv.org/abs/2603.03195 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.03195.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fuxiang Yang, Donglin Di, Lulu Tang, Xuancheng Zhang, Lei Fan, Hao Li, Chen Wei, Tonghua Su, Baorui Ma</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Vision-Language-Action (VLA) models are a promising path toward embodied intelligence, yet they often overlook the predictive and temporal-causal structure underlying visual dynamics. World-model VLAs address this by predicting future frames, but waste capacity reconstructing redundant backgrounds. Latent-action VLAs encode frame-to-frame transitions compactly, but lack temporally continuous dynamic modeling and world knowledge. To overcome these limitations, we introduce CoWVLA (Chain-of-World VLA), a new "Chain of World" paradigm that unifies world-model temporal reasoning with a disentangled latent motion representation. First, a pretrained video VAE serves as a latent motion extractor, explicitly factorizing video segments into structure and motion latents. Then, during pre-training, the VLA learns from an instruction and an initial frame to infer a continuous latent motion chain and predict the segment's terminal frame. Finally, during co-fine-tuning, this latent dynamic is aligned with discrete action prediction by jointly modeling sparse keyframes and action sequences in a unified autoregressive decoder. This design preserves the world-model benefits of temporal reasoning and world knowledge while retaining the compactness and interpretability of latent actions, enabling efficient visuomotor learning. Extensive experiments on robotic simulation benchmarks show that CoWVLA outperforms existing world-model and latent-action approaches and achieves moderate computational efficiency, highlighting its potential as a more effective VLA pretraining paradigm. The project website can be found at https://fx-hit.github.io/cowvla-io.</p> + https://arxiv.org/abs/2603.03195 + Tue, 03 Mar 2026 17:52:06 +0000 - Revisiting Text Ranking in Deep Research - https://arxiv.org/abs/2602.21456 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.21456.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chuan Meng, Litu Ou, Sean MacAvaney, Jeff Dalton</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Deep research has emerged as an important task that aims to address hard queries through extensive open-web exploration. To tackle it, most prior work equips large language model (LLM)-based agents with opaque web search APIs, enabling agents to iteratively issue search queries, retrieve external evidence, and reason over it. Despite search's essential role in deep research, black-box web search APIs hinder systematic analysis of search components, leaving the behaviour of established text ranking methods in deep research largely unclear. To fill this gap, we reproduce a selection of key findings and best practices for IR text ranking methods in the deep research setting. In particular, we examine their effectiveness from three perspectives: (i) retrieval units (documents vs. passages), (ii) pipeline configurations (different retrievers, re-rankers, and re-ranking depths), and (iii) query characteristics (the mismatch between agent-issued queries and the training queries of text rankers). We perform experiments on BrowseComp-Plus, a deep research dataset with a fixed corpus, evaluating 2 open-source agents, 5 retrievers, and 3 re-rankers across diverse setups. We find that agent-issued queries typically follow web-search-style syntax (e.g., quoted exact matches), favouring lexical, learned sparse, and multi-vector retrievers; passage-level units are more efficient under limited context windows, and avoid the difficulties of document length normalisation in lexical retrieval; re-ranking is highly effective; translating agent-issued queries into natural-language questions significantly bridges the query mismatch.</p> - https://arxiv.org/abs/2602.21456 - Wed, 25 Feb 2026 00:18:07 +0000 + Specificity-aware reinforcement learning for fine-grained open-world classification + https://arxiv.org/abs/2603.03197 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.03197.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Samuele Angheben, Davide Berasi, Alessandro Conti, Elisa Ricci, Yiming Wang</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Classifying fine-grained visual concepts under open-world settings, i.e., without a predefined label set, demands models to be both accurate and specific. Recent reasoning Large Multimodal Models (LMMs) exhibit strong visual understanding capability but tend to produce overly generic predictions when performing fine-grained image classification. Our preliminary analysis reveals that models do possess the intrinsic fine-grained domain knowledge. However, promoting more specific predictions (specificity) without compromising correct ones (correctness) remains a non-trivial and understudied challenge. In this work, we investigate how to steer reasoning LMMs toward predictions that are both correct and specific. We propose a novel specificity-aware reinforcement learning framework, SpeciaRL, to fine-tune reasoning LMMs on fine-grained image classification under the open-world setting. SpeciaRL introduces a dynamic, verifier-based reward signal anchored to the best predictions within online rollouts, promoting specificity while respecting the model's capabilities to prevent incorrect predictions. Our out-of-domain experiments show that SpeciaRL delivers the best trade-off between correctness and specificity across extensive fine-grained benchmarks, surpassing existing methods and advancing open-world fine-grained image classification. Code and model are publicly available at https://github.com/s-angheben/SpeciaRL.</p> + https://arxiv.org/abs/2603.03197 + Tue, 03 Mar 2026 17:52:39 +0000 - VecGlypher: Unified Vector Glyph Generation with Language Models - https://arxiv.org/abs/2602.21461 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.21461.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiaoke Huang, Bhavul Gauri, Kam Woh Ng, Tony Ng, Mengmeng Xu, Zhiheng Liu, Weiming Ren, Zhaochong An, Zijian Zhou, Haonan Qiu, Yuyin Zhou, Sen He, Ziheng Wang, Tao Xiang, Xiao Han</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Vector glyphs are the atomic units of digital typography, yet most learning-based pipelines still depend on carefully curated exemplar sheets and raster-to-vector postprocessing, which limits accessibility and editability. We introduce VecGlypher, a single multimodal language model that generates high-fidelity vector glyphs directly from text descriptions or image exemplars. Given a style prompt, optional reference glyph images, and a target character, VecGlypher autoregressively emits SVG path tokens, avoiding raster intermediates and producing editable, watertight outlines in one pass. A typography-aware data and training recipe makes this possible: (i) a large-scale continuation stage on 39K noisy Envato fonts to master SVG syntax and long-horizon geometry, followed by (ii) post-training on 2.5K expert-annotated Google Fonts with descriptive tags and exemplars to align language and imagery with geometry; preprocessing normalizes coordinate frames, canonicalizes paths, de-duplicates families, and quantizes coordinates for stable long-sequence decoding. On cross-family OOD evaluation, VecGlypher substantially outperforms both general-purpose LLMs and specialized vector-font baselines for text-only generation, while image-referenced generation reaches a state-of-the-art performance, with marked gains over DeepVecFont-v2 and DualVector. Ablations show that model scale and the two-stage recipe are critical and that absolute-coordinate serialization yields the best geometry. VecGlypher lowers the barrier to font creation by letting users design with words or exemplars, and provides a scalable foundation for future multimodal design tools.</p> - https://arxiv.org/abs/2602.21461 - Wed, 25 Feb 2026 00:27:23 +0000 + Code2Math: Can Your Code Agent Effectively Evolve Math Problems Through Exploration? + https://arxiv.org/abs/2603.03202 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.03202.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dadi Guo, Yuejin Xie, Qingyu Liu, Jiayu Liu, Zhiyuan Fan, Qihan Ren, Shuai Shao, Tianyi Zhou, Dongrui Liu, Yi R. Fung</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> As large language models (LLMs) advance their mathematical capabilities toward the IMO level, the scarcity of challenging, high-quality problems for training and evaluation has become a significant bottleneck. Simultaneously, recent code agents have demonstrated sophisticated skills in agentic coding and reasoning, suggesting that code execution can serve as a scalable environment for mathematical experimentation. In this paper, we investigate the potential of code agents to autonomously evolve existing math problems into more complex variations. We introduce a multi-agent framework designed to perform problem evolution while validating the solvability and increased difficulty of the generated problems. Our experiments demonstrate that, given sufficient test-time exploration, code agents can synthesize new, solvable problems that are structurally distinct from and more challenging than the originals. This work provides empirical evidence that code-driven agents can serve as a viable mechanism for synthesizing high-difficulty mathematical reasoning problems within scalable computational environments. Our data is available at https://github.com/TarferSoul/Code2Math.</p> + https://arxiv.org/abs/2603.03202 + Tue, 03 Mar 2026 17:55:10 +0000 - The Design Space of Tri-Modal Masked Diffusion Models - https://arxiv.org/abs/2602.21472 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.21472.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Louis Bethune, Victor Turrisi, Bruno Kacper Mlodozeniec, Pau Rodriguez Lopez, Lokesh Boominathan, Nikhil Bhendawade, Amitis Shidani, Joris Pelemans, Theo X. Olausson, Devon Hjelm, Paul Dixon, Joao Monteiro, Pierre Ablin, Vishnu Banna, Arno Blaas, Nick Henderson, Kari Noriy, Dan Busbridge, Josh Susskind, Marco Cuturi, Irina Belousova, Luca Zappella, Russ Webb, Jason Ramapuram</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Discrete diffusion models have emerged as strong alternatives to autoregressive language models, with recent work initializing and fine-tuning a base unimodal model for bimodal generation. Diverging from previous approaches, we introduce the first tri-modal masked diffusion model pretrained from scratch on text, image-text, and audio-text data. We systematically analyze multimodal scaling laws, modality mixing ratios, noise schedules, and batch-size effects, and we provide optimized inference sampling defaults. Our batch-size analysis yields a novel stochastic differential equation (SDE)-based reparameterization that eliminates the need for tuning the optimal batch size as reported in recent work. This reparameterization decouples the physical batch size, often chosen based on compute constraints (GPU saturation, FLOP efficiency, wall-clock time), from the logical batch size, chosen to balance gradient variance during stochastic optimization. Finally, we pretrain a preliminary 3B-parameter tri-modal model on 6.4T tokens, demonstrating the capabilities of a unified design and achieving strong results in text generation, text-to-image tasks, and text-to-speech tasks. Our work represents the largest-scale systematic open study of multimodal discrete diffusion models conducted to date, providing insights into scaling behaviors across multiple modalities.</p> - https://arxiv.org/abs/2602.21472 - Wed, 25 Feb 2026 01:02:11 +0000 + Learning When to Act or Refuse: Guarding Agentic Reasoning Models for Safe Multi-Step Tool Use + https://arxiv.org/abs/2603.03205 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.03205.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Aradhye Agarwal, Gurdit Siyan, Yash Pandya, Joykirat Singh, Akshay Nambi, Ahmed Awadallah</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Agentic language models operate in a fundamentally different safety regime than chat models: they must plan, call tools, and execute long-horizon actions where a single misstep, such as accessing files or entering credentials, can cause irreversible harm. Existing alignment methods, largely optimized for static generation and task completion, break down in these settings due to sequential decision-making, adversarial tool feedback, and overconfident intermediate reasoning. We introduce MOSAIC, a post-training framework that aligns agents for safe multi-step tool use by making safety decisions explicit and learnable. MOSAIC structures inference as a plan, check, then act or refuse loop, with explicit safety reasoning and refusal as first-class actions. To train without trajectory-level labels, we use preference-based reinforcement learning with pairwise trajectory comparisons, which captures safety distinctions often missed by scalar rewards. We evaluate MOSAIC zero-shot across three model families, Qwen2.5-7B, Qwen3-4B-Thinking, and Phi-4, and across out-of-distribution benchmarks spanning harmful tasks, prompt injection, benign tool use, and cross-domain privacy leakage. MOSAIC reduces harmful behavior by up to 50%, increases harmful-task refusal by over 20% on injection attacks, cuts privacy leakage, and preserves or improves benign task performance, demonstrating robust generalization across models, domains, and agentic settings.</p> + https://arxiv.org/abs/2603.03205 + Tue, 03 Mar 2026 17:59:35 +0000 - ARLArena: A Unified Framework for Stable Agentic Reinforcement Learning - https://arxiv.org/abs/2602.21534 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.21534.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiaoxuan Wang, Han Zhang, Haixin Wang, Yidan Shi, Ruoyan Li, Kaiqiao Han, Chenyi Tong, Haoran Deng, Renliang Sun, Alexander Taylor, Yanqiao Zhu, Jason Cong, Yizhou Sun, Wei Wang</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> Agentic reinforcement learning (ARL) has rapidly gained attention as a promising paradigm for training agents to solve complex, multi-step interactive tasks. Despite encouraging early results, ARL remains highly unstable, often leading to training collapse. This instability limits scalability to larger environments and longer interaction horizons, and constrains systematic exploration of algorithmic design choices. In this paper, we first propose ARLArena, a stable training recipe and systematic analysis framework that examines training stability in a controlled and reproducible setting. ARLArena first constructs a clean and standardized testbed. Then, we decompose policy gradient into four core design dimensions and assess the performance and stability of each dimension. Through this fine-grained analysis, we distill a unified perspective on ARL and propose SAMPO, a stable agentic policy optimization method designed to mitigate the dominant sources of instability in ARL. Empirically, SAMPO achieves consistently stable training and strong performance across diverse agentic tasks. Overall, this study provides a unifying policy gradient perspective for ARL and offers practical guidance for building stable and reproducible LLM-based agent training pipelines.</p> - https://arxiv.org/abs/2602.21534 - Wed, 25 Feb 2026 03:43:34 +0000 + UniG2U-Bench: Do Unified Models Advance Multimodal Understanding? + https://arxiv.org/abs/2603.03241 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.03241.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zimo Wen, Boxiu Li, Wanbo Zhang, Junxiang Lei, Xiaoyu Chen, Yijia Fan, Qi Zhang, Yujiang Wang, Lili Qiu, Bo Li, Ziwei Liu, Caihua Shan, Yifan Yang, Yifei Shen</p><p><b>Upvotes:</b> 79</p><p><b>Summary:</b> Unified multimodal models have recently demonstrated strong generative capabilities, yet whether and when generation improves understanding remains unclear. Existing benchmarks lack a systematic exploration of the specific tasks where generation facilitates understanding. To this end, we introduce UniG2U-Bench, a comprehensive benchmark categorizing generation-to-understanding (G2U) evaluation into 7 regimes and 30 subtasks, requiring varying degrees of implicit or explicit visual transformations. Extensive evaluation of over 30 models reveals three core findings: 1) Unified models generally underperform their base Vision-Language Models (VLMs), and Generate-then-Answer (GtA) inference typically degrades performance relative to direct inference. 2) Consistent enhancements emerge in spatial intelligence, visual illusions, or multi-round reasoning subtasks, where enhanced spatial and shape perception, as well as multi-step intermediate image states, prove beneficial. 3) Tasks with similar reasoning structures and models sharing architectures exhibit correlated behaviors, suggesting that generation-understanding coupling induces class-consistent inductive biases over tasks, pretraining data, and model architectures. These findings highlight the necessity for more diverse training data and novel paradigms to fully unlock the potential of unified multimodal modeling.</p> + https://arxiv.org/abs/2603.03241 + Tue, 03 Mar 2026 18:36:16 +0000 - DualPath: Breaking the Storage Bandwidth Bottleneck in Agentic LLM Inference - https://arxiv.org/abs/2602.21548 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.21548.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yongtong Wu, Shaoyuan Chen, Yinmin Zhong, Rilin Huang, Yixuan Tan, Wentao Zhang, Liyue Zhang, Shangyan Zhou, Yuxuan Liu, Shunfeng Zhou, Mingxing Zhang, Xin Jin, Panpan Huang</p><p><b>Upvotes:</b> 29</p><p><b>Summary:</b> The performance of multi-turn, agentic LLM inference is increasingly dominated by KV-Cache storage I/O rather than computation. In prevalent disaggregated architectures, loading the massive KV-Cache from external storage creates a fundamental imbalance: storage NICs on prefill engines become bandwidth-saturated, while those on decoding engines remain idle. This asymmetry severely constrains overall system throughput. We present DualPath, an inference system that breaks this bottleneck by introducing dual-path KV-Cache loading. Beyond the traditional storage-to-prefill path, DualPath enables a novel storage-to-decode path, in which the KV-Cache is loaded into decoding engines and then efficiently transferred to prefill engines via RDMA over the compute network. DualPath combines this optimized data path -- which inherently avoids network congestion and avoids interference with latency-critical model execution communications -- with a global scheduler that dynamically balances load across prefill and decode engines. Our evaluation on three models with production agentic workloads demonstrates that DualPath improves offline inference throughput by up to 1.87times on our in-house inference system. It can also improve online serving throughput by an average factor of 1.96times without violating SLO.</p> - https://arxiv.org/abs/2602.21548 - Wed, 25 Feb 2026 04:10:58 +0000 + Beyond Language Modeling: An Exploration of Multimodal Pretraining + https://arxiv.org/abs/2603.03276 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.03276.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shengbang Tong, David Fan, John Nguyen, Ellis Brown, Gaoyue Zhou, Shengyi Qian, Boyang Zheng, Théophane Vallaeys, Junlin Han, Rob Fergus, Naila Murray, Marjan Ghazvininejad, Mike Lewis, Nicolas Ballas, Amir Bar, Michael Rabbat, Jakob Verbeek, Luke Zettlemoyer, Koustuv Sinha, Yann LeCun, Saining Xie</p><p><b>Upvotes:</b> 73</p><p><b>Summary:</b> The visual world offers a critical axis for advancing foundation models beyond language. Despite growing interest in this direction, the design space for native multimodal models remains opaque. We provide empirical clarity through controlled, from-scratch pretraining experiments, isolating the factors that govern multimodal pretraining without interference from language pretraining. We adopt the Transfusion framework, using next-token prediction for language and diffusion for vision, to train on diverse data including text, video, image-text pairs, and even action-conditioned video. Our experiments yield four key insights: (i) Representation Autoencoder (RAE) provides an optimal unified visual representation by excelling at both visual understanding and generation; (ii) visual and language data are complementary and yield synergy for downstream capabilities; (iii) unified multimodal pretraining leads naturally to world modeling, with capabilities emerging from general training; and (iv) Mixture-of-Experts (MoE) enables efficient and effective multimodal scaling while naturally inducing modality specialization. Through IsoFLOP analysis, we compute scaling laws for both modalities and uncover a scaling asymmetry: vision is significantly more data-hungry than language. We demonstrate that the MoE architecture harmonizes this scaling asymmetry by providing the high model capacity required by language while accommodating the data-intensive nature of vision, paving the way for truly unified multimodal models.</p> + https://arxiv.org/abs/2603.03276 + Tue, 03 Mar 2026 18:58:00 +0000 - Accelerating Diffusion via Hybrid Data-Pipeline Parallelism Based on Conditional Guidance Scheduling - https://arxiv.org/abs/2602.21760 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.21760.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Euisoo Jung, Byunghyun Kim, Hyunjin Kim, Seonghye Cho, Jae-Gil Lee</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Diffusion models have achieved remarkable progress in high-fidelity image, video, and audio generation, yet inference remains computationally expensive. Nevertheless, current diffusion acceleration methods based on distributed parallelism suffer from noticeable generation artifacts and fail to achieve substantial acceleration proportional to the number of GPUs. Therefore, we propose a hybrid parallelism framework that combines a novel data parallel strategy, condition-based partitioning, with an optimal pipeline scheduling method, adaptive parallelism switching, to reduce generation latency and achieve high generation quality in conditional diffusion models. The key ideas are to (i) leverage the conditional and unconditional denoising paths as a new data-partitioning perspective and (ii) adaptively enable optimal pipeline parallelism according to the denoising discrepancy between these two paths. Our framework achieves 2.31times and 2.07times latency reductions on SDXL and SD3, respectively, using two NVIDIA RTX~3090 GPUs, while preserving image quality. This result confirms the generality of our approach across U-Net-based diffusion models and DiT-based flow-matching architectures. Our approach also outperforms existing methods in acceleration under high-resolution synthesis settings. Code is available at https://github.com/kaist-dmlab/Hybridiff.</p> - https://arxiv.org/abs/2602.21760 - Wed, 25 Feb 2026 10:23:07 +0000 + CFG-Ctrl: Control-Based Classifier-Free Diffusion Guidance + https://arxiv.org/abs/2603.03281 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.03281.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hanyang Wang, Yiyang Liu, Jiawei Chi, Fangfu Liu, Ran Xue, Yueqi Duan</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Classifier-Free Guidance (CFG) has emerged as a central approach for enhancing semantic alignment in flow-based diffusion models. In this paper, we explore a unified framework called CFG-Ctrl, which reinterprets CFG as a control applied to the first-order continuous-time generative flow, using the conditional-unconditional discrepancy as an error signal to adjust the velocity field. From this perspective, we summarize vanilla CFG as a proportional controller (P-control) with fixed gain, and typical follow-up variants develop extended control-law designs derived from it. However, existing methods mainly rely on linear control, inherently leading to instability, overshooting, and degraded semantic fidelity especially on large guidance scales. To address this, we introduce Sliding Mode Control CFG (SMC-CFG), which enforces the generative flow toward a rapidly convergent sliding manifold. Specifically, we define an exponential sliding mode surface over the semantic prediction error and introduce a switching control term to establish nonlinear feedback-guided correction. Moreover, we provide a Lyapunov stability analysis to theoretically support finite-time convergence. Experiments across text-to-image generation models including Stable Diffusion 3.5, Flux, and Qwen-Image demonstrate that SMC-CFG outperforms standard CFG in semantic alignment and enhances robustness across a wide range of guidance scales. Project Page: https://hanyang-21.github.io/CFG-Ctrl</p> + https://arxiv.org/abs/2603.03281 + Tue, 03 Mar 2026 18:59:48 +0000 - From Statics to Dynamics: Physics-Aware Image Editing with Latent Transition Priors - https://arxiv.org/abs/2602.21778 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.21778.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Liangbing Zhao, Le Zhuo, Sayak Paul, Hongsheng Li, Mohamed Elhoseiny</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Instruction-based image editing has achieved remarkable success in semantic alignment, yet state-of-the-art models frequently fail to render physically plausible results when editing involves complex causal dynamics, such as refraction or material deformation. We attribute this limitation to the dominant paradigm that treats editing as a discrete mapping between image pairs, which provides only boundary conditions and leaves transition dynamics underspecified. To address this, we reformulate physics-aware editing as predictive physical state transitions and introduce PhysicTran38K, a large-scale video-based dataset comprising 38K transition trajectories across five physical domains, constructed via a two-stage filtering and constraint-aware annotation pipeline. Building on this supervision, we propose PhysicEdit, an end-to-end framework equipped with a textual-visual dual-thinking mechanism. It combines a frozen Qwen2.5-VL for physically grounded reasoning with learnable transition queries that provide timestep-adaptive visual guidance to a diffusion backbone. Experiments show that PhysicEdit improves over Qwen-Image-Edit by 5.9% in physical realism and 10.1% in knowledge-grounded editing, setting a new state-of-the-art for open-source methods, while remaining competitive with leading proprietary models.</p> - https://arxiv.org/abs/2602.21778 - Wed, 25 Feb 2026 10:54:46 +0000 + Utonia: Toward One Encoder for All Point Clouds + https://arxiv.org/abs/2603.03283 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.03283.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yujia Zhang, Xiaoyang Wu, Yunhan Yang, Xianzhe Fan, Han Li, Yuechen Zhang, Zehao Huang, Naiyan Wang, Hengshuang Zhao</p><p><b>Upvotes:</b> 148</p><p><b>Summary:</b> We dream of a future where point clouds from all domains can come together to shape a single model that benefits them all. Toward this goal, we present Utonia, a first step toward training a single self-supervised point transformer encoder across diverse domains, spanning remote sensing, outdoor LiDAR, indoor RGB-D sequences, object-centric CAD models, and point clouds lifted from RGB-only videos. Despite their distinct sensing geometries, densities, and priors, Utonia learns a consistent representation space that transfers across domains. This unification improves perception capability while revealing intriguing emergent behaviors that arise only when domains are trained jointly. Beyond perception, we observe that Utonia representations can also benefit embodied and multimodal reasoning: conditioning vision-language-action policies on Utonia features improves robotic manipulation, and integrating them into vision-language models yields gains on spatial reasoning. We hope Utonia can serve as a step toward foundation models for sparse 3D data, and support downstream applications in AR/VR, robotics, and autonomous driving.</p> + https://arxiv.org/abs/2603.03283 + Tue, 03 Mar 2026 18:59:58 +0000 - SkyReels-V4: Multi-modal Video-Audio Generation, Inpainting and Editing model - https://arxiv.org/abs/2602.21818 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.21818.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Guibin Chen, Dixuan Lin, Jiangping Yang, Youqiang Zhang, Zhengcong Fei, Debang Li, Sheng Chen, Chaofeng Ao, Nuo Pang, Yiming Wang, Yikun Dou, Zheng Chen, Mingyuan Fan, Tuanhui Li, Mingshan Chang, Hao Zhang, Xiaopeng Sun, Jingtao Xu, Yuqiang Xie, Jiahua Wang, Zhiheng Xu, Weiming Xiong, Yuzhe Jin, Baoxuan Gu, Binjie Mao, Yunjie Yu, Jujie He, Yuhao Feng, Shiwen Tu, Chaojie Wang, Rui Yan, Wei Shen, Jingchen Wu, Peng Zhao, Xuanyue Zhong, Zhuangzhuang Liu, Kaifei Wang, Fuxiang Zhang, Weikai Xu, Wenyan Liu, Binglu Zhang, Yu Shen, Tianhui Xiong, Bin Peng, Liang Zeng, Xuchen Song, Haoxiang Guo, Peiyu Wang, Yahui Zhou</p><p><b>Upvotes:</b> 48</p><p><b>Summary:</b> SkyReels V4 is a unified multi modal video foundation model for joint video audio generation, inpainting, and editing. The model adopts a dual stream Multimodal Diffusion Transformer (MMDiT) architecture, where one branch synthesizes video and the other generates temporally aligned audio, while sharing a powerful text encoder based on the Multimodal Large Language Models (MMLM). SkyReels V4 accepts rich multi modal instructions, including text, images, video clips, masks, and audio references. By combining the MMLMs multi modal instruction following capability with in context learning in the video branch MMDiT, the model can inject fine grained visual guidance under complex conditioning, while the audio branch MMDiT simultaneously leverages audio references to guide sound generation. On the video side, we adopt a channel concatenation formulation that unifies a wide range of inpainting style tasks, such as image to video, video extension, and video editing under a single interface, and naturally extends to vision referenced inpainting and editing via multi modal prompts. SkyReels V4 supports up to 1080p resolution, 32 FPS, and 15 second duration, enabling high fidelity, multi shot, cinema level video generation with synchronized audio. To make such high resolution, long-duration generation computationally feasible, we introduce an efficiency strategy: Joint generation of low resolution full sequences and high-resolution keyframes, followed by dedicated super-resolution and frame interpolation models. To our knowledge, SkyReels V4 is the first video foundation model that simultaneously supports multi-modal input, joint video audio generation, and a unified treatment of generation, inpainting, and editing, while maintaining strong efficiency and quality at cinematic resolutions and durations.</p> - https://arxiv.org/abs/2602.21818 - Wed, 25 Feb 2026 11:47:00 +0000 + Proact-VL: A Proactive VideoLLM for Real-Time AI Companions + https://arxiv.org/abs/2603.03447 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.03447.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weicai Yan, Yuhong Dai, Qi Ran, Haodong Li, Wang Lin, Hao Liao, Xing Xie, Tao Jin, Jianxun Lian</p><p><b>Upvotes:</b> 25</p><p><b>Summary:</b> Proactive and real-time interactive experiences are essential for human-like AI companions, yet face three key challenges: (1) achieving low-latency inference under continuous streaming inputs, (2) autonomously deciding when to respond, and (3) controlling both quality and quantity of generated content to meet real-time constraints. In this work, we instantiate AI companions through two gaming scenarios, commentator and guide, selected for their suitability for automatic evaluation. We introduce the Live Gaming Benchmark, a large-scale dataset with three representative scenarios: solo commentary, co-commentary, and user guidance, and present Proact-VL, a general framework that shapes multimodal language models into proactive, real-time interactive agents capable of human-like environment perception and interaction. Extensive experiments show Proact-VL achieves superior response latency and quality while maintaining strong video understanding capabilities, demonstrating its practicality for real-time interactive applications.</p> + https://arxiv.org/abs/2603.03447 + Tue, 03 Mar 2026 19:02:46 +0000 - UniVBench: Towards Unified Evaluation for Video Foundation Models - https://arxiv.org/abs/2602.21835 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.21835.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jianhui Wei, Xiaotian Zhang, Yichen Li, Yuan Wang, Yan Zhang, Ziyi Chen, Zhihang Tang, Wei Xu, Zuozhu Liu</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Video foundation models aim to integrate video understanding, generation, editing, and instruction following within a single framework, making them a central direction for next-generation multimodal systems. However, existing evaluation benchmarks remain fragmented and limited in scope, as they each target a single task, rely on task-specific metrics, and typically use short or simple video clips. As a result, they do not capture the unified capabilities that these models are designed to deliver. To address this gap, we introduce UniVBench, a benchmark purpose-built for evaluating video foundation models across four core abilities: video understanding, video generation, video editing, and a newly proposed task, video reconstruction, which assesses how faithfully a model can reproduce video content it has encountered. Our benchmark substantially expands the complexity of evaluation by incorporating 200 high-quality, diverse and multi-shot videos, each paired with detailed captions, multi-format editing instructions, and reference images. All videos are human-created and carefully validated, offering richer cinematic information than prior benchmarks. In addition, we develop a unified agentic evaluation system (UniV-Eval) that standardizes prompting, instruction parsing, and scoring across all tasks, enabling fair, scalable, and reproducible comparisons of unified video models. By grounding evaluation in instruction-based multi-shot video tasks, UniVBench provides the first framework for measuring the integrated capabilities that video foundation models aim to achieve. Extensive human annotations ensure our evaluation aligns with human judgment, enabling rigorous assessment and accelerating progress toward robust video intelligence.</p> - https://arxiv.org/abs/2602.21835 - Wed, 25 Feb 2026 12:08:53 +0000 + InfinityStory: Unlimited Video Generation with World Consistency and Character-Aware Shot Transitions + https://arxiv.org/abs/2603.03646 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.03646.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mohamed Elmoghany, Liangbing Zhao, Xiaoqian Shen, Subhojyoti Mukherjee, Yang Zhou, Gang Wu, Viet Dac Lai, Seunghyun Yoon, Ryan Rossi, Abdullah Rashwan, Puneet Mathur, Varun Manjunatha, Daksh Dangi, Chien Nguyen, Nedim Lipka, Trung Bui, Krishna Kumar Singh, Ruiyi Zhang, Xiaolei Huang, Jaemin Cho, Yu Wang, Namyong Park, Zhengzhong Tu, Hongjie Chen, Hoda Eldardiry, Nesreen Ahmed, Thien Nguyen, Dinesh Manocha, Mohamed Elhoseiny, Franck Dernoncourt</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Generating long-form storytelling videos with consistent visual narratives remains a significant challenge in video synthesis. We present a novel framework, dataset, and a model that address three critical limitations: background consistency across shots, seamless multi-subject shot-to-shot transitions, and scalability to hour-long narratives. Our approach introduces a background-consistent generation pipeline that maintains visual coherence across scenes while preserving character identity and spatial relationships. We further propose a transition-aware video synthesis module that generates smooth shot transitions for complex scenarios involving multiple subjects entering or exiting frames, going beyond the single-subject limitations of prior work. To support this, we contribute with a synthetic dataset of 10,000 multi-subject transition sequences covering underrepresented dynamic scene compositions. On VBench, InfinityStory achieves the highest Background Consistency (88.94), highest Subject Consistency (82.11), and the best overall average rank (2.80), showing improved stability, smoother transitions, and better temporal coherence.</p> + https://arxiv.org/abs/2603.03646 + Wed, 04 Mar 2026 02:10:32 +0000 - World Guidance: World Modeling in Condition Space for Action Generation - https://arxiv.org/abs/2602.22010 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.22010.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yue Su, Sijin Chen, Haixin Shi, Mingyu Liu, Zhengshen Zhang, Ningyuan Huang, Weiheng Zhong, Zhengbang Zhu, Yuxiao Liu, Xihui Liu</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Leveraging future observation modeling to facilitate action generation presents a promising avenue for enhancing the capabilities of Vision-Language-Action (VLA) models. However, existing approaches struggle to strike a balance between maintaining efficient, predictable future representations and preserving sufficient fine-grained information to guide precise action generation. To address this limitation, we propose WoG (World Guidance), a framework that maps future observations into compact conditions by injecting them into the action inference pipeline. The VLA is then trained to simultaneously predict these compressed conditions alongside future actions, thereby achieving effective world modeling within the condition space for action inference. We demonstrate that modeling and predicting this condition space not only facilitates fine-grained action generation but also exhibits superior generalization capabilities. Moreover, it learns effectively from substantial human manipulation videos. Extensive experiments across both simulation and real-world environments validate that our method significantly outperforms existing methods based on future prediction. Project page is available at: https://selen-suyue.github.io/WoGNet/</p> - https://arxiv.org/abs/2602.22010 - Wed, 25 Feb 2026 15:27:09 +0000 + MOOSE-Star: Unlocking Tractable Training for Scientific Discovery by Breaking the Complexity Barrier + https://arxiv.org/abs/2603.03756 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.03756.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zonglin Yang, Lidong Bing</p><p><b>Upvotes:</b> 82</p><p><b>Summary:</b> While large language models (LLMs) show promise in scientific discovery, existing research focuses on inference or feedback-driven training, leaving the direct modeling of the generative reasoning process, P(hypothesis|background) (P(h|b)), unexplored. We demonstrate that directly training P(h|b) is mathematically intractable due to the combinatorial complexity (O(N^k)) inherent in retrieving and composing inspirations from a vast knowledge base. To break this barrier, we introduce MOOSE-Star, a unified framework enabling tractable training and scalable inference. In the best case, MOOSE-Star reduces complexity from exponential to logarithmic (O(log N)) by (1) training on decomposed subtasks derived from the probabilistic equation of discovery, (2) employing motivation-guided hierarchical search to enable logarithmic retrieval and prune irrelevant subspaces, and (3) utilizing bounded composition for robustness against retrieval noise. To facilitate this, we release TOMATO-Star, a dataset of 108,717 decomposed papers (38,400 GPU hours) for training. Furthermore, we show that while brute-force sampling hits a ''complexity wall,'' MOOSE-Star exhibits continuous test-time scaling.</p> + https://arxiv.org/abs/2603.03756 + Wed, 04 Mar 2026 06:11:18 +0000 - GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL - https://arxiv.org/abs/2602.22190 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.22190.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Rui Yang, Qianhui Wu, Zhaoyang Wang, Hanyang Chen, Ke Yang, Hao Cheng, Huaxiu Yao, Baoling Peng, Huan Zhang, Jianfeng Gao, Tong Zhang</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Open-source native GUI agents still lag behind closed-source systems on long-horizon navigation tasks. This gap stems from two limitations: a shortage of high-quality, action-aligned reasoning data, and the direct adoption of generic post-training pipelines that overlook the unique challenges of GUI agents. We identify two fundamental issues in these pipelines: (i) standard SFT with CoT reasoning often hurts grounding, and (ii) step-wise RLVR-tyle training faces partial verifiability, where multiple actions can be correct but only a single demonstrated action is used for verification. This makes offline step-wise metrics weak predictors of online task success. In this work, we present GUI-Libra, a tailored training recipe that addresses these challenges. First, to mitigate the scarcity of action-aligned reasoning data, we introduce a data construction and filtering pipeline and release a curated 81K GUI reasoning dataset. Second, to reconcile reasoning with grounding, we propose action-aware SFT that mixes reasoning-then-action and direct-action data and reweights tokens to emphasize action and grounding. Third, to stabilize RL under partial verifiability, we identify the overlooked importance of KL regularization in RLVR and show that a KL trust region is critical for improving offline-to-online predictability; we further introduce success-adaptive scaling to downweight unreliable negative gradients. Across diverse web and mobile benchmarks, GUI-Libra consistently improves both step-wise accuracy and end-to-end task completion. Our results suggest that carefully designed post-training and data curation can unlock significantly stronger task-solving capabilities without costly online data collection. We release our dataset, code, and models to facilitate further research on data-efficient post-training for reasoning-capable GUI agents.</p> - https://arxiv.org/abs/2602.22190 - Wed, 25 Feb 2026 18:34:57 +0000 + T2S-Bench & Structure-of-Thought: Benchmarking and Prompting Comprehensive Text-to-Structure Reasoning + https://arxiv.org/abs/2603.03790 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.03790.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qinsi Wang, Hancheng Ye, Jinhee Kim, Jinghan Ke, Yifei Wang, Martin Kuo, Zishan Shao, Dongting Li, Yueqian Lin, Ting Jiang, Chiyue Wei, Qi Qian, Wei Wen, Helen Li, Yiran Chen</p><p><b>Upvotes:</b> 109</p><p><b>Summary:</b> Think about how human handles complex reading tasks: marking key points, inferring their relationships, and structuring information to guide understanding and responses. Likewise, can a large language model benefit from text structure to enhance text-processing performance? To explore it, in this work, we first introduce Structure of Thought (SoT), a prompting technique that explicitly guides models to construct intermediate text structures, consistently boosting performance across eight tasks and three model families. Building upon this insight, we present T2S-Bench, the first benchmark designed to evaluate and improve text-to-structure capabilities of models. T2S-Bench includes 1.8K samples across 6 scientific domains and 32 structural types, rigorously constructed to ensure accuracy, fairness, and quality. Evaluation on 45 mainstream models reveals substantial improvement potential: the average accuracy on the multi-hop reasoning task is only 52.1%, and even the most advanced model achieves 58.1% node accuracy in end-to-end extraction. Furthermore, on Qwen2.5-7B-Instruct, SoT alone yields an average +5.7% improvement across eight diverse text-processing tasks, and fine-tuning on T2S-Bench further increases this gain to +8.6%. These results highlight the value of explicit text structuring and the complementary contributions of SoT and T2S-Bench. Dataset and eval code have been released at https://t2s-bench.github.io/T2S-Bench-Page/.</p> + https://arxiv.org/abs/2603.03790 + Wed, 04 Mar 2026 07:05:09 +0000 - Solaris: Building a Multiplayer Video World Model in Minecraft - https://arxiv.org/abs/2602.22208 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.22208.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Georgy Savva, Oscar Michel, Daohan Lu, Suppakit Waiwitlikhit, Timothy Meehan, Dhairya Mishra, Srivats Poddar, Jack Lu, Saining Xie</p><p><b>Upvotes:</b> 25</p><p><b>Summary:</b> Existing action-conditioned video generation models (video world models) are limited to single-agent perspectives, failing to capture the multi-agent interactions of real-world environments. We introduce Solaris, a multiplayer video world model that simulates consistent multi-view observations. To enable this, we develop a multiplayer data system designed for robust, continuous, and automated data collection on video games such as Minecraft. Unlike prior platforms built for single-player settings, our system supports coordinated multi-agent interaction and synchronized videos + actions capture. Using this system, we collect 12.64 million multiplayer frames and propose an evaluation framework for multiplayer movement, memory, grounding, building, and view consistency. We train Solaris using a staged pipeline that progressively transitions from single-player to multiplayer modeling, combining bidirectional, causal, and Self Forcing training. In the final stage, we introduce Checkpointed Self Forcing, a memory-efficient Self Forcing variant that enables a longer-horizon teacher. Results show our architecture and training design outperform existing baselines. Through open-sourcing our system and models, we hope to lay the groundwork for a new generation of multi-agent world models.</p> - https://arxiv.org/abs/2602.22208 - Wed, 25 Feb 2026 18:59:01 +0000 + Phi-4-reasoning-vision-15B Technical Report + https://arxiv.org/abs/2603.03975 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.03975.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jyoti Aneja, Michael Harrison, Neel Joshi, Tyler LaBonte, John Langford, Eduardo Salinas</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> We present Phi-4-reasoning-vision-15B, a compact open-weight multimodal reasoning model, and share the motivations, design choices, experiments, and learnings that informed its development. Our goal is to contribute practical insight to the research community on building smaller, efficient multimodal reasoning models and to share the result of these learnings as an open-weight model that is good at common vision and language tasks and excels at scientific and mathematical reasoning and understanding user interfaces. Our contributions include demonstrating that careful architecture choices and rigorous data curation enable smaller, open-weight multimodal models to achieve competitive performance with significantly less training and inference-time compute and tokens. The most substantial improvements come from systematic filtering, error correction, and synthetic augmentation -- reinforcing that data quality remains the primary lever for model performance. Systematic ablations show that high-resolution, dynamic-resolution encoders yield consistent improvements, as accurate perception is a prerequisite for high-quality reasoning. Finally, a hybrid mix of reasoning and non-reasoning data with explicit mode tokens allows a single model to deliver fast direct answers for simpler tasks and chain-of-thought reasoning for complex problems.</p> + https://arxiv.org/abs/2603.03975 + Wed, 04 Mar 2026 12:16:53 +0000 - veScale-FSDP: Flexible and High-Performance FSDP at Scale - https://arxiv.org/abs/2602.22437 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.22437.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zezhou Wang, Youjie Li, Zhiqi Lin, Jiacheng Yang, Cong Xie, Guanyu Feng, Zheng Zhong, Ziyue Huang, Hongyu Zhu, Zhi Zhang, Yanghua Peng, Xin Liu</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Fully Sharded Data Parallel (FSDP), also known as ZeRO, is widely used for training large-scale models, featuring its flexibility and minimal intrusion on model code. However, current FSDP systems struggle with structure-aware training methods (e.g., block-wise quantized training) and with non-element-wise optimizers (e.g., Shampoo and Muon) used in cutting-edge models (e.g., Gemini, Kimi K2). FSDP's fixed element- or row-wise sharding formats conflict with the block-structured computations. In addition, today's implementations fall short in communication and memory efficiency, limiting scaling to tens of thousands of GPUs. We introduce veScale-FSDP, a redesigned FSDP system that couples a flexible sharding format, RaggedShard, with a structure-aware planning algorithm to deliver both flexibility and performance at scale. veScale-FSDP natively supports efficient data placement required by FSDP, empowering block-wise quantization and non-element-wise optimizers. As a result, veScale-FSDP achieves 5~66% higher throughput and 16~30% lower memory usage than existing FSDP systems, while scaling efficiently to tens of thousands of GPUs.</p> - https://arxiv.org/abs/2602.22437 - Wed, 25 Feb 2026 21:55:43 +0000 + RIVER: A Real-Time Interaction Benchmark for Video LLMs + https://arxiv.org/abs/2603.03985 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.03985.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yansong Shi, Qingsong Zhao, Tianxiang Jiang, Xiangyu Zeng, Yi Wang, Limin Wang</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> The rapid advancement of multimodal large language models has demonstrated impressive capabilities, yet nearly all operate in an offline paradigm, hindering real-time interactivity. Addressing this gap, we introduce the Real-tIme Video intERaction Bench (RIVER Bench), designed for evaluating online video comprehension. RIVER Bench introduces a novel framework comprising Retrospective Memory, Live-Perception, and Proactive Anticipation tasks, closely mimicking interactive dialogues rather than responding to entire videos at once. We conducted detailed annotations using videos from diverse sources and varying lengths, and precisely defined the real-time interactive format. Evaluations across various model categories reveal that while offline models perform well in single question-answering tasks, they struggle with real-time processing. Addressing the limitations of existing models in online video interaction, especially their deficiencies in long-term memory and future perception, we proposed a general improvement method that enables models to interact with users more flexibly in real time. We believe this work will significantly advance the development of real-time interactive video understanding models and inspire future research in this emerging field. Datasets and code are publicly available at https://github.com/OpenGVLab/RIVER.</p> + https://arxiv.org/abs/2603.03985 + Wed, 04 Mar 2026 12:29:34 +0000 - Causal Motion Diffusion Models for Autoregressive Motion Generation - https://arxiv.org/abs/2602.22594 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.22594.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qing Yu, Akihisa Watanabe, Kent Fujiwara</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Recent advances in motion diffusion models have substantially improved the realism of human motion synthesis. However, existing approaches either rely on full-sequence diffusion models with bidirectional generation, which limits temporal causality and real-time applicability, or autoregressive models that suffer from instability and cumulative errors. In this work, we present Causal Motion Diffusion Models (CMDM), a unified framework for autoregressive motion generation based on a causal diffusion transformer that operates in a semantically aligned latent space. CMDM builds upon a Motion-Language-Aligned Causal VAE (MAC-VAE), which encodes motion sequences into temporally causal latent representations. On top of this latent representation, an autoregressive diffusion transformer is trained using causal diffusion forcing to perform temporally ordered denoising across motion frames. To achieve fast inference, we introduce a frame-wise sampling schedule with causal uncertainty, where each subsequent frame is predicted from partially denoised previous frames. The resulting framework supports high-quality text-to-motion generation, streaming synthesis, and long-horizon motion generation at interactive rates. Experiments on HumanML3D and SnapMoGen demonstrate that CMDM outperforms existing diffusion and autoregressive models in both semantic fidelity and temporal smoothness, while substantially reducing inference latency.</p> - https://arxiv.org/abs/2602.22594 - Thu, 26 Feb 2026 03:58:25 +0000 + Memex(RL): Scaling Long-Horizon LLM Agents via Indexed Experience Memory + https://arxiv.org/abs/2603.04257 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.04257.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhenting Wang, Huancheng Chen, Jiayun Wang, Wei Wei</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Large language model (LLM) agents are fundamentally bottlenecked by finite context windows on long-horizon tasks. As trajectories grow, retaining tool outputs and intermediate reasoning in-context quickly becomes infeasible: the working context becomes prohibitively long, eventually exceeds the context budget, and makes distant evidence harder to use even when it is still present. Existing solutions typically shorten context through truncation or running summaries, but these methods are fundamentally lossy because they compress or discard past evidence itself. We introduce Memex, an indexed experience memory mechanism that instead compresses context without discarding evidence. Memex maintains a compact working context consisting of concise structured summaries and stable indices, while storing full-fidelity underlying interactions in an external experience database under those indices. The agent can then decide when to dereference an index and recover the exact past evidence needed for the current subgoal. We optimize both write and read behaviors with our reinforcement learning framework MemexRL, using reward shaping tailored to indexed memory usage under a context budget, so the agent learns what to summarize, what to archive, how to index it, and when to retrieve it. This yields a substantially less lossy form of long-horizon memory than summary-only approaches. We further provide a theoretical analysis showing the potential of the Memex loop to preserve decision quality with bounded dereferencing while keeping effective in-context computation bounded as history grows. Empirically, on challenging long-horizon tasks, Memex agent trained with MemexRL improves task success while using a significantly smaller working context.</p> + https://arxiv.org/abs/2603.04257 + Wed, 04 Mar 2026 16:45:06 +0000 - MobilityBench: A Benchmark for Evaluating Route-Planning Agents in Real-World Mobility Scenarios - https://arxiv.org/abs/2602.22638 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.22638.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhiheng Song, Jingshuai Zhang, Chuan Qin, Chao Wang, Chao Chen, Longfei Xu, Kaikui Liu, Xiangxiang Chu, Hengshu Zhu</p><p><b>Upvotes:</b> 99</p><p><b>Summary:</b> Route-planning agents powered by large language models (LLMs) have emerged as a promising paradigm for supporting everyday human mobility through natural language interaction and tool-mediated decision making. However, systematic evaluation in real-world mobility settings is hindered by diverse routing demands, non-deterministic mapping services, and limited reproducibility. In this study, we introduce MobilityBench, a scalable benchmark for evaluating LLM-based route-planning agents in real-world mobility scenarios. MobilityBench is constructed from large-scale, anonymized real user queries collected from Amap and covers a broad spectrum of route-planning intents across multiple cities worldwide. To enable reproducible, end-to-end evaluation, we design a deterministic API-replay sandbox that eliminates environmental variance from live services. We further propose a multi-dimensional evaluation protocol centered on outcome validity, complemented by assessments of instruction understanding, planning, tool use, and efficiency. Using MobilityBench, we evaluate multiple LLM-based route-planning agents across diverse real-world mobility scenarios and provide an in-depth analysis of their behaviors and performance. Our findings reveal that current models perform competently on Basic information retrieval and Route Planning tasks, yet struggle considerably with Preference-Constrained Route Planning, underscoring significant room for improvement in personalized mobility applications. We publicly release the benchmark data, evaluation toolkit, and documentation at https://github.com/AMAP-ML/MobilityBench .</p> - https://arxiv.org/abs/2602.22638 - Thu, 26 Feb 2026 05:39:38 +0000 + CubeComposer: Spatio-Temporal Autoregressive 4K 360° Video Generation from Perspective Video + https://arxiv.org/abs/2603.04291 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.04291.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lingen Li, Guangzhi Wang, Xiaoyu Li, Zhaoyang Zhang, Qi Dou, Jinwei Gu, Tianfan Xue, Ying Shan</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Generating high-quality 360° panoramic videos from perspective input is one of the crucial applications for virtual reality (VR), whereby high-resolution videos are especially important for immersive experience. Existing methods are constrained by computational limitations of vanilla diffusion models, only supporting leq 1K resolution native generation and relying on suboptimal post super-resolution to increase resolution. We introduce CubeComposer, a novel spatio-temporal autoregressive diffusion model that natively generates 4K-resolution 360° videos. By decomposing videos into cubemap representations with six faces, CubeComposer autoregressively synthesizes content in a well-planned spatio-temporal order, reducing memory demands while enabling high-resolution output. Specifically, to address challenges in multi-dimensional autoregression, we propose: (1) a spatio-temporal autoregressive strategy that orchestrates 360° video generation across cube faces and time windows for coherent synthesis; (2) a cube face context management mechanism, equipped with a sparse context attention design to improve efficiency; and (3) continuity-aware techniques, including cube-aware positional encoding, padding, and blending to eliminate boundary seams. Extensive experiments on benchmark datasets demonstrate that CubeComposer outperforms state-of-the-art methods in native resolution and visual quality, supporting practical VR application scenarios. Project page: https://lg-li.github.io/project/cubecomposer</p> + https://arxiv.org/abs/2603.04291 + Wed, 04 Mar 2026 17:06:56 +0000 - Search More, Think Less: Rethinking Long-Horizon Agentic Search for Efficiency and Generalization - https://arxiv.org/abs/2602.22675 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.22675.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qianben Chen, Tianrui Qin, King Zhu, Qiexiang Wang, Chengjun Yu, Shu Xu, Jiaqi Wu, Jiayu Zhang, Xinpeng Liu, Xin Gui, Jingyi Cao, Piaohong Wang, Dingfeng Shi, He Zhu, Tiannan Wang, Yuqing Wang, Maojia Song, Tianyu Zheng, Ge Zhang, Jian Yang, Jiaheng Liu, Minghao Liu, Yuchen Eleanor Jiang, Wangchunshu Zhou</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> Recent deep research agents primarily improve performance by scaling reasoning depth, but this leads to high inference cost and latency in search-intensive scenarios. Moreover, generalization across heterogeneous research settings remains challenging. In this work, we propose Search More, Think Less (SMTL), a framework for long-horizon agentic search that targets both efficiency and generalization. SMTL replaces sequential reasoning with parallel evidence acquisition, enabling efficient context management under constrained context budgets. To support generalization across task types, we further introduce a unified data synthesis pipeline that constructs search tasks spanning both deterministic question answering and open-ended research scenarios with task appropriate evaluation metrics. We train an end-to-end agent using supervised fine-tuning and reinforcement learning, achieving strong and often state of the art performance across benchmarks including BrowseComp (48.6\%), GAIA (75.7\%), Xbench (82.0\%), and DeepResearch Bench (45.9\%). Compared to Mirothinker-v1.0, SMTL with maximum 100 interaction steps reduces the average number of reasoning steps on BrowseComp by 70.7\%, while improving accuracy.</p> - https://arxiv.org/abs/2602.22675 - Thu, 26 Feb 2026 06:46:41 +0000 + V_1: Unifying Generation and Self-Verification for Parallel Reasoners + https://arxiv.org/abs/2603.04304 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.04304.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Harman Singh, Xiuyu Li, Kusha Sareen, Monishwaran Maheswaran, Sijun Tan, Xiaoxia Wu, Junxiong Wang, Alpay Ariyak, Qingyang Wu, Samir Khaki, Rishabh Tiwari, Long Lian, Yucheng Lu, Boyi Li, Alane Suhr, Ben Athiwaratkun, Kurt Keutzer</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Test-time scaling for complex reasoning tasks shows that leveraging inference-time compute, by methods such as independently sampling and aggregating multiple solutions, results in significantly better task outcomes. However, a critical bottleneck is verification: sampling is only effective if correct solutions can be reliably identified among candidates. While existing approaches typically evaluate candidates independently via scalar scoring, we demonstrate that models are substantially stronger at pairwise self-verification. Leveraging this insight, we introduce V_1, a framework that unifies generation and verification through efficient pairwise ranking. V_1 comprises two components: V_1-Infer, an uncertainty-guided algorithm using a tournament-based ranking that dynamically allocates self-verification compute to candidate pairs whose relative correctness is most uncertain; and V_1-PairRL, an RL framework that jointly trains a single model as both generator and pairwise self-verifier, ensuring the verifier adapts to the generator's evolving distribution. On code generation (LiveCodeBench, CodeContests, SWE-Bench) and math reasoning (AIME, HMMT) benchmarks, V_1-Infer improves Pass@1 by up to 10% over pointwise verification and outperforms recent test-time scaling methods while being significantly more efficient. Furthermore, V_1-PairRL achieves 7--9% test-time scaling gains over standard RL and pointwise joint training, and improves base Pass@1 by up to 8.7% over standard RL in a code-generation setting.</p> + https://arxiv.org/abs/2603.04304 + Wed, 04 Mar 2026 17:22:16 +0000 - Imagination Helps Visual Reasoning, But Not Yet in Latent Space - https://arxiv.org/abs/2602.22766 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.22766.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> You Li, Chi Chen, Yanghao Li, Fanhu Zeng, Kaiyu Huang, Jinan Xu, Maosong Sun</p><p><b>Upvotes:</b> 36</p><p><b>Summary:</b> Latent visual reasoning aims to mimic human's imagination process by meditating through hidden states of Multimodal Large Language Models. While recognized as a promising paradigm for visual reasoning, the underlying mechanisms driving its effectiveness remain unclear. Motivated to demystify the true source of its efficacy, we investigate the validity of latent reasoning using Causal Mediation Analysis. We model the process as a causal chain: the input as the treatment, the latent tokens as the mediator, and the final answer as the outcome. Our findings uncover two critical disconnections: (a) Input-Latent Disconnect: dramatic perturbations on the input result in negligible changes to the latent tokens, suggesting that latent tokens do not effectively attend to the input sequence. (b) Latent-Answer Disconnect: perturbations on the latent tokens yield minimal impact on the final answer, indicating the limited causal effect latent tokens imposing on the outcome. Furthermore, extensive probing analysis reveals that latent tokens encode limited visual information and exhibit high similarity. Consequently, we challenge the necessity of latent reasoning and propose a straightforward alternative named CapImagine, which teaches the model to explicitly imagine using text. Experiments on vision-centric benchmarks show that CapImagine significantly outperforms complex latent-space baselines, highlighting the superior potential of visual reasoning through explicit imagination.</p> - https://arxiv.org/abs/2602.22766 - Thu, 26 Feb 2026 08:56:23 +0000 + ArtHOI: Articulated Human-Object Interaction Synthesis by 4D Reconstruction from Video Priors + https://arxiv.org/abs/2603.04338 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.04338.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zihao Huang, Tianqi Liu, Zhaoxi Chen, Shaocong Xu, Saining Zhang, Lixing Xiao, Zhiguo Cao, Wei Li, Hao Zhao, Ziwei Liu</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> Synthesizing physically plausible articulated human-object interactions (HOI) without 3D/4D supervision remains a fundamental challenge. While recent zero-shot approaches leverage video diffusion models to synthesize human-object interactions, they are largely confined to rigid-object manipulation and lack explicit 4D geometric reasoning. To bridge this gap, we formulate articulated HOI synthesis as a 4D reconstruction problem from monocular video priors: given only a video generated by a diffusion model, we reconstruct a full 4D articulated scene without any 3D supervision. This reconstruction-based approach treats the generated 2D video as supervision for an inverse rendering problem, recovering geometrically consistent and physically plausible 4D scenes that naturally respect contact, articulation, and temporal coherence. We introduce ArtHOI, the first zero-shot framework for articulated human-object interaction synthesis via 4D reconstruction from video priors. Our key designs are: 1) Flow-based part segmentation: leveraging optical flow as a geometric cue to disentangle dynamic from static regions in monocular video; 2) Decoupled reconstruction pipeline: joint optimization of human motion and object articulation is unstable under monocular ambiguity, so we first recover object articulation, then synthesize human motion conditioned on the reconstructed object states. ArtHOI bridges video-based generation and geometry-aware reconstruction, producing interactions that are both semantically aligned and physically grounded. Across diverse articulated scenes (e.g., opening fridges, cabinets, microwaves), ArtHOI significantly outperforms prior methods in contact accuracy, penetration reduction, and articulation fidelity, extending zero-shot interaction synthesis beyond rigid manipulation through reconstruction-informed synthesis.</p> + https://arxiv.org/abs/2603.04338 + Wed, 04 Mar 2026 17:58:04 +0000 - From Blind Spots to Gains: Diagnostic-Driven Iterative Training for Large Multimodal Models - https://arxiv.org/abs/2602.22859 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.22859.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hongrui Jia, Chaoya Jiang, Shikun Zhang, Wei Ye</p><p><b>Upvotes:</b> 147</p><p><b>Summary:</b> As Large Multimodal Models (LMMs) scale up and reinforcement learning (RL) methods mature, LMMs have made notable progress in complex reasoning and decision making. Yet training still relies on static data and fixed recipes, making it difficult to diagnose capability blind spots or provide dynamic, targeted reinforcement. Motivated by findings that test driven error exposure and feedback based correction outperform repetitive practice, we propose Diagnostic-driven Progressive Evolution (DPE), a spiral loop where diagnosis steers data generation and reinforcement, and each iteration re-diagnoses the updated model to drive the next round of targeted improvement. DPE has two key components. First, multiple agents annotate and quality control massive unlabeled multimodal data, using tools such as web search and image editing to produce diverse, realistic samples. Second, DPE attributes failures to specific weaknesses, dynamically adjusts the data mixture, and guides agents to generate weakness focused data for targeted reinforcement. Experiments on Qwen3-VL-8B-Instruct and Qwen2.5-VL-7B-Instruct show stable, continual gains across eleven benchmarks, indicating DPE as a scalable paradigm for continual LMM training under open task distributions. Our code, models, and data are publicly available at https://github.com/hongruijia/DPE.</p> - https://arxiv.org/abs/2602.22859 - Thu, 26 Feb 2026 10:53:57 +0000 + Helios: Real Real-Time Long Video Generation Model + https://arxiv.org/abs/2603.04379 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.04379.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shenghai Yuan, Yuanyang Yin, Zongjian Li, Xinwei Huang, Xiao Yang, Li Yuan</p><p><b>Upvotes:</b> 136</p><p><b>Summary:</b> We introduce Helios, the first 14B video generation model that runs at 19.5 FPS on a single NVIDIA H100 GPU and supports minute-scale generation while matching the quality of a strong baseline. We make breakthroughs along three key dimensions: (1) robustness to long-video drifting without commonly used anti-drifting heuristics such as self-forcing, error-banks, or keyframe sampling; (2) real-time generation without standard acceleration techniques such as KV-cache, sparse/linear attention, or quantization; and (3) training without parallelism or sharding frameworks, enabling image-diffusion-scale batch sizes while fitting up to four 14B models within 80 GB of GPU memory. Specifically, Helios is a 14B autoregressive diffusion model with a unified input representation that natively supports T2V, I2V, and V2V tasks. To mitigate drifting in long-video generation, we characterize typical failure modes and propose simple yet effective training strategies that explicitly simulate drifting during training, while eliminating repetitive motion at its source. For efficiency, we heavily compress the historical and noisy context and reduce the number of sampling steps, yielding computational costs comparable to -- or lower than -- those of 1.3B video generative models. Moreover, we introduce infrastructure-level optimizations that accelerate both inference and training while reducing memory consumption. Extensive experiments demonstrate that Helios consistently outperforms prior methods on both short- and long-video generation. We plan to release the code, base model, and distilled model to support further development by the community.</p> + https://arxiv.org/abs/2603.04379 + Wed, 04 Mar 2026 18:45:21 +0000 - OmniGAIA: Towards Native Omni-Modal AI Agents - https://arxiv.org/abs/2602.22897 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.22897.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiaoxi Li, Wenxiang Jiao, Jiarui Jin, Shijian Wang, Guanting Dong, Jiajie Jin, Hao Wang, Yinuo Wang, Ji-Rong Wen, Yuan Lu, Zhicheng Dou</p><p><b>Upvotes:</b> 49</p><p><b>Summary:</b> Human intelligence naturally intertwines omni-modal perception -- spanning vision, audio, and language -- with complex reasoning and tool usage to interact with the world. However, current multi-modal LLMs are primarily confined to bi-modal interactions (e.g., vision-language), lacking the unified cognitive capabilities required for general AI assistants. To bridge this gap, we introduce OmniGAIA, a comprehensive benchmark designed to evaluate omni-modal agents on tasks necessitating deep reasoning and multi-turn tool execution across video, audio, and image modalities. Constructed via a novel omni-modal event graph approach, OmniGAIA synthesizes complex, multi-hop queries derived from real-world data that require cross-modal reasoning and external tool integration. Furthermore, we propose OmniAtlas, a native omni-modal foundation agent under tool-integrated reasoning paradigm with active omni-modal perception. Trained on trajectories synthesized via a hindsight-guided tree exploration strategy and OmniDPO for fine-grained error correction, OmniAtlas effectively enhances the tool-use capabilities of existing open-source models. This work marks a step towards next-generation native omni-modal AI assistants for real-world scenarios.</p> - https://arxiv.org/abs/2602.22897 - Thu, 26 Feb 2026 11:35:04 +0000 + Interactive Benchmarks + https://arxiv.org/abs/2603.04737 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.04737.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Baoqing Yue, Zihan Zhu, Yifan Zhang, Jichen Feng, Hufei Yang, Mengdi Wang</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Standard benchmarks have become increasingly unreliable due to saturation, subjectivity, and poor generalization. We argue that evaluating model's ability to acquire information actively is important to assess model's intelligence. We propose Interactive Benchmarks, a unified evaluation paradigm that assesses model's reasoning ability in an interactive process under budget constraints. We instantiate this framework across two settings: Interactive Proofs, where models interact with a judge to deduce objective truths or answers in logic and mathematics; and Interactive Games, where models reason strategically to maximize long-horizon utilities. Our results show that interactive benchmarks provide a robust and faithful assessment of model intelligence, revealing that there is still substantial room to improve in interactive scenarios. Project page: https://github.com/interactivebench/interactivebench</p> + https://arxiv.org/abs/2603.04737 + Thu, 05 Mar 2026 02:18:26 +0000 - General Agent Evaluation - https://arxiv.org/abs/2602.22953 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.22953.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Elron Bandel, Asaf Yehudai, Lilach Eden, Yehoshua Sagron, Yotam Perlitz, Elad Venezian, Natalia Razinkov, Natan Ergas, Shlomit Shachor Ifergan, Segev Shlomov, Michal Jacovi, Leshem Choshen, Liat Ein-Dor, Yoav Katz, Michal Shmueli-Scheuer</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> The promise of general-purpose agents - systems that perform tasks in unfamiliar environments without domain-specific engineering - remains largely unrealized. Existing agents are predominantly specialized, and while emerging implementations like OpenAI SDK Agent and Claude Code hint at broader capabilities, no systematic evaluation of their general performance has been pursued. Current agentic benchmarks assume domain-specific integration, encoding task information in ways that preclude fair evaluation of general agents. This paper frames general-agent evaluation as a first-class research objective. We propose conceptual principles for such evaluation, a Unified Protocol enabling agent-benchmark integration, and Exgentic - a practical framework for general agent evaluation. We benchmark five prominent agent implementations across six environments as the first Open General Agent Leaderboard. Our experiments show that general agents generalize across diverse environments, achieving performance comparable to domain-specific agents without any environment-specific tuning. We release our evaluation protocol, framework, and leaderboard to establish a foundation for systematic research on general-purpose agents.</p> - https://arxiv.org/abs/2602.22953 - Thu, 26 Feb 2026 12:48:02 +0000 + DARE: Aligning LLM Agents with the R Statistical Ecosystem via Distribution-Aware Retrieval + https://arxiv.org/abs/2603.04743 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.04743.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Maojun Sun, Yue Wu, Yifei Xie, Ruijian Han, Binyan Jiang, Defeng Sun, Yancheng Yuan, Jian Huang</p><p><b>Upvotes:</b> 44</p><p><b>Summary:</b> Large Language Model (LLM) agents can automate data-science workflows, but many rigorous statistical methods implemented in R remain underused because LLMs struggle with statistical knowledge and tool retrieval. Existing retrieval-augmented approaches focus on function-level semantics and ignore data distribution, producing suboptimal matches. We propose DARE (Distribution-Aware Retrieval Embedding), a lightweight, plug-and-play retrieval model that incorporates data distribution information into function representations for R package retrieval. Our main contributions are: (i) RPKB, a curated R Package Knowledge Base derived from 8,191 high-quality CRAN packages; (ii) DARE, an embedding model that fuses distributional features with function metadata to improve retrieval relevance; and (iii) RCodingAgent, an R-oriented LLM agent for reliable R code generation and a suite of statistical analysis tasks for systematically evaluating LLM agents in realistic analytical scenarios. Empirically, DARE achieves an NDCG at 10 of 93.47%, outperforming state-of-the-art open-source embedding models by up to 17% on package retrieval while using substantially fewer parameters. Integrating DARE into RCodingAgent yields significant gains on downstream analysis tasks. This work helps narrow the gap between LLM automation and the mature R statistical ecosystem.</p> + https://arxiv.org/abs/2603.04743 + Thu, 05 Mar 2026 02:29:54 +0000 - Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization - https://arxiv.org/abs/2602.23008 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.23008.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zeyuan Liu, Jeonghye Kim, Xufang Luo, Dongsheng Li, Yuqing Yang</p><p><b>Upvotes:</b> 30</p><p><b>Summary:</b> Exploration remains the key bottleneck for large language model agents trained with reinforcement learning. While prior methods exploit pretrained knowledge, they fail in environments requiring the discovery of novel states. We propose Exploratory Memory-Augmented On- and Off-Policy Optimization (EMPO^2), a hybrid RL framework that leverages memory for exploration and combines on- and off-policy updates to make LLMs perform well with memory while also ensuring robustness without it. On ScienceWorld and WebShop, EMPO^2 achieves 128.6% and 11.3% improvements over GRPO, respectively. Moreover, in out-of-distribution tests, EMPO^2 demonstrates superior adaptability to new tasks, requiring only a few trials with memory and no parameter updates. These results highlight EMPO^2 as a promising framework for building more exploratory and generalizable LLM-based agents.</p> - https://arxiv.org/abs/2602.23008 - Thu, 26 Feb 2026 13:50:57 +0000 + Timer-S1: A Billion-Scale Time Series Foundation Model with Serial Scaling + https://arxiv.org/abs/2603.04791 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.04791.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yong Liu, Xingjian Su, Shiyu Wang, Haoran Zhang, Haixuan Liu, Yuxuan Wang, Zhou Ye, Yang Xiang, Jianmin Wang, Mingsheng Long</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> We introduce Timer-S1, a strong Mixture-of-Experts (MoE) time series foundation model with 8.3B total parameters, 0.75B activated parameters for each token, and a context length of 11.5K. To overcome the scalability bottleneck in existing pre-trained time series foundation models, we perform Serial Scaling in three dimensions: model architecture, dataset, and training pipeline. Timer-S1 integrates sparse TimeMoE blocks and generic TimeSTP blocks for Serial-Token Prediction (STP), a generic training objective that adheres to the serial nature of forecasting. The proposed paradigm introduces serial computations to improve long-term predictions while avoiding costly rolling-style inference and pronounced error accumulation in the standard next-token prediction. Pursuing a high-quality and unbiased training dataset, we curate TimeBench, a corpus with one trillion time points, and apply meticulous data augmentation to mitigate predictive bias. We further pioneer a post-training stage, including continued pre-training and long-context extension, to enhance short-term and long-context performance. Evaluated on the large-scale GIFT-Eval leaderboard, Timer-S1 achieves state-of-the-art forecasting performance, attaining the best MASE and CRPS scores as a pre-trained model. Timer-S1 will be released to facilitate further research.</p> + https://arxiv.org/abs/2603.04791 + Thu, 05 Mar 2026 04:13:57 +0000 - GeoWorld: Geometric World Models - https://arxiv.org/abs/2602.23058 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.23058.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zeyu Zhang, Danning Li, Ian Reid, Richard Hartley</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Energy-based predictive world models provide a powerful approach for multi-step visual planning by reasoning over latent energy landscapes rather than generating pixels. However, existing approaches face two major challenges: (i) their latent representations are typically learned in Euclidean space, neglecting the underlying geometric and hierarchical structure among states, and (ii) they struggle with long-horizon prediction, which leads to rapid degradation across extended rollouts. To address these challenges, we introduce GeoWorld, a geometric world model that preserves geometric structure and hierarchical relations through a Hyperbolic JEPA, which maps latent representations from Euclidean space onto hyperbolic manifolds. We further introduce Geometric Reinforcement Learning for energy-based optimization, enabling stable multi-step planning in hyperbolic latent space. Extensive experiments on CrossTask and COIN demonstrate around 3% SR improvement in 3-step planning and 2% SR improvement in 4-step planning compared to the state-of-the-art V-JEPA 2. Project website: https://steve-zeyu-zhang.github.io/GeoWorld.</p> - https://arxiv.org/abs/2602.23058 - Thu, 26 Feb 2026 14:42:53 +0000 + MASQuant: Modality-Aware Smoothing Quantization for Multimodal Large Language Models + https://arxiv.org/abs/2603.04800 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.04800.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lulu Hu, Wenhu Xiao, Xin Chen, Xinhua Xu, Bowen Xu, Kun Li, Yongliang Tao</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Post-training quantization (PTQ) with computational invariance for Large Language Models~(LLMs) have demonstrated remarkable advances, however, their application to Multimodal Large Language Models~(MLLMs) presents substantial challenges. In this paper, we analyze SmoothQuant as a case study and identify two critical issues: Smoothing Misalignment and Cross-Modal Computational Invariance. To address these issues, we propose Modality-Aware Smoothing Quantization (MASQuant), a novel framework that introduces (1) Modality-Aware Smoothing (MAS), which learns separate, modality-specific smoothing factors to prevent Smoothing Misalignment, and (2) Cross-Modal Compensation (CMC), which addresses Cross-modal Computational Invariance by using SVD whitening to transform multi-modal activation differences into low-rank forms, enabling unified quantization across modalities. MASQuant demonstrates stable quantization performance across both dual-modal and tri-modal MLLMs. Experimental results show that MASQuant is competitive among the state-of-the-art PTQ algorithms. Source code: https://github.com/alibaba/EfficientAI.</p> + https://arxiv.org/abs/2603.04800 + Thu, 05 Mar 2026 04:41:32 +0000 - The Trinity of Consistency as a Defining Principle for General World Models - https://arxiv.org/abs/2602.23152 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.23152.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jingxuan Wei, Siyuan Li, Yuhang Xu, Zheng Sun, Junjie Jiang, Hexuan Jin, Caijun Jia, Honghao He, Xinglong Xu, Xi bai, Chang Yu, Yumou Liu, Junnan Zhu, Xuanhe Zhou, Jintao Chen, Xiaobin Hu, Shancheng Pang, Bihui Yu, Ran He, Zhen Lei, Stan Z. Li, Conghui He, Shuicheng Yan, Cheng Tan</p><p><b>Upvotes:</b> 188</p><p><b>Summary:</b> The construction of World Models capable of learning, simulating, and reasoning about objective physical laws constitutes a foundational challenge in the pursuit of Artificial General Intelligence. Recent advancements represented by video generation models like Sora have demonstrated the potential of data-driven scaling laws to approximate physical dynamics, while the emerging Unified Multimodal Model (UMM) offers a promising architectural paradigm for integrating perception, language, and reasoning. Despite these advances, the field still lacks a principled theoretical framework that defines the essential properties requisite for a General World Model. In this paper, we propose that a World Model must be grounded in the Trinity of Consistency: Modal Consistency as the semantic interface, Spatial Consistency as the geometric basis, and Temporal Consistency as the causal engine. Through this tripartite lens, we systematically review the evolution of multimodal learning, revealing a trajectory from loosely coupled specialized modules toward unified architectures that enable the synergistic emergence of internal world simulators. To complement this conceptual framework, we introduce CoW-Bench, a benchmark centered on multi-frame reasoning and generation scenarios. CoW-Bench evaluates both video generation models and UMMs under a unified evaluation protocol. Our work establishes a principled pathway toward general world models, clarifying both the limitations of current systems and the architectural requirements for future progress.</p> - https://arxiv.org/abs/2602.23152 - Thu, 26 Feb 2026 16:15:55 +0000 + Locality-Attending Vision Transformer + https://arxiv.org/abs/2603.04892 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.04892.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sina Hajimiri, Farzad Beizaee, Fereshteh Shakeri, Christian Desrosiers, Ismail Ben Ayed, Jose Dolz</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Vision transformers have demonstrated remarkable success in classification by leveraging global self-attention to capture long-range dependencies. However, this same mechanism can obscure fine-grained spatial details crucial for tasks such as segmentation. In this work, we seek to enhance segmentation performance of vision transformers after standard image-level classification training. More specifically, we present a simple yet effective add-on that improves performance on segmentation tasks while retaining vision transformers' image-level recognition capabilities. In our approach, we modulate the self-attention with a learnable Gaussian kernel that biases the attention toward neighboring patches. We further refine the patch representations to learn better embeddings at patch positions. These modifications encourage tokens to focus on local surroundings and ensure meaningful representations at spatial positions, while still preserving the model's ability to incorporate global information. Experiments demonstrate the effectiveness of our modifications, evidenced by substantial segmentation gains on three benchmarks (e.g., over 6% and 4% on ADE20K for ViT Tiny and Base), without changing the training regime or sacrificing classification performance. The code is available at https://github.com/sinahmr/LocAtViT/.</p> + https://arxiv.org/abs/2603.04892 + Thu, 05 Mar 2026 07:31:49 +0000 - EmbodMocap: In-the-Wild 4D Human-Scene Reconstruction for Embodied Agents - https://arxiv.org/abs/2602.23205 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.23205.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wenjia Wang, Liang Pan, Huaijin Pi, Yuke Lou, Xuqian Ren, Yifan Wu, Zhouyingcheng Liao, Lei Yang, Rishabh Dabral, Christian Theobalt, Taku Komura</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Human behaviors in the real world naturally encode rich, long-term contextual information that can be leveraged to train embodied agents for perception, understanding, and acting. However, existing capture systems typically rely on costly studio setups and wearable devices, limiting the large-scale collection of scene-conditioned human motion data in the wild. To address this, we propose EmbodMocap, a portable and affordable data collection pipeline using two moving iPhones. Our key idea is to jointly calibrate dual RGB-D sequences to reconstruct both humans and scenes within a unified metric world coordinate frame. The proposed method allows metric-scale and scene-consistent capture in everyday environments without static cameras or markers, bridging human motion and scene geometry seamlessly. Compared with optical capture ground truth, we demonstrate that the dual-view setting exhibits a remarkable ability to mitigate depth ambiguity, achieving superior alignment and reconstruction performance over single iphone or monocular models. Based on the collected data, we empower three embodied AI tasks: monocular human-scene-reconstruction, where we fine-tune on feedforward models that output metric-scale, world-space aligned humans and scenes; physics-based character animation, where we prove our data could be used to scale human-object interaction skills and scene-aware motion tracking; and robot motion control, where we train a humanoid robot via sim-to-real RL to replicate human motions depicted in videos. Experimental results validate the effectiveness of our pipeline and its contributions towards advancing embodied AI research.</p> - https://arxiv.org/abs/2602.23205 - Thu, 26 Feb 2026 16:53:41 +0000 + KARL: Knowledge Agents via Reinforcement Learning + https://arxiv.org/abs/2603.05218 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.05218.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jonathan D. Chang, Andrew Drozdov, Shubham Toshniwal, Owen Oertell, Alexander Trott, Jacob Portes, Abhay Gupta, Pallavi Koppol, Ashutosh Baheti, Sean Kulinski, Ivan Zhou, Irene Dea, Krista Opsahl-Ong, Simon Favreau-Lessard, Sean Owen, Jose Javier Gonzalez Ortiz, Arnav Singhvi, Xabi Andrade, Cindy Wang, Kartik Sreenivasan, Sam Havens, Jialu Liu, Peyton DeNiro, Wen Sun, Michael Bendersky, Jonathan Frankle</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> We present a system for training enterprise search agents via reinforcement learning that achieves state-of-the-art performance across a diverse suite of hard-to-verify agentic search tasks. Our work makes four core contributions. First, we introduce KARLBench, a multi-capability evaluation suite spanning six distinct search regimes, including constraint-driven entity search, cross-document report synthesis, tabular numerical reasoning, exhaustive entity retrieval, procedural reasoning over technical documentation, and fact aggregation over internal enterprise notes. Second, we show that models trained across heterogeneous search behaviors generalize substantially better than those optimized for any single benchmark. Third, we develop an agentic synthesis pipeline that employs long-horizon reasoning and tool use to generate diverse, grounded, and high-quality training data, with iterative bootstrapping from increasingly capable models. Fourth, we propose a new post-training paradigm based on iterative large-batch off-policy RL that is sample efficient, robust to train-inference engine discrepancies, and naturally extends to multi-task training with out-of-distribution generalization. Compared to Claude 4.6 and GPT 5.2, KARL is Pareto-optimal on KARLBench across cost-quality and latency-quality trade-offs, including tasks that were out-of-distribution during training. With sufficient test-time compute, it surpasses the strongest closed models. These results show that tailored synthetic data in combination with multi-task reinforcement learning enables cost-efficient and high-performing knowledge agents for grounded reasoning.</p> + https://arxiv.org/abs/2603.05218 + Thu, 05 Mar 2026 14:30:25 +0000 - AgentDropoutV2: Optimizing Information Flow in Multi-Agent Systems via Test-Time Rectify-or-Reject Pruning - https://arxiv.org/abs/2602.23258 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.23258.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yutong Wang, Siyuan Xiong, Xuebo Liu, Wenkang Zhou, Liang Ding, Miao Zhang, Min Zhang</p><p><b>Upvotes:</b> 25</p><p><b>Summary:</b> While Multi-Agent Systems (MAS) excel in complex reasoning, they suffer from the cascading impact of erroneous information generated by individual participants. Current solutions often resort to rigid structural engineering or expensive fine-tuning, limiting their deployability and adaptability. We propose AgentDropoutV2, a test-time rectify-or-reject pruning framework designed to dynamically optimize MAS information flow without retraining. Our approach acts as an active firewall, intercepting agent outputs and employing a retrieval-augmented rectifier to iteratively correct errors based on a failure-driven indicator pool. This mechanism allows for the precise identification of potential errors using distilled failure patterns as prior knowledge. Irreparable outputs are subsequently pruned to prevent error propagation, while a fallback strategy preserves system integrity. Empirical results on extensive math benchmarks show that AgentDropoutV2 significantly boosts the MAS's task performance, achieving an average accuracy gain of 6.3 percentage points on math benchmarks. Furthermore, the system exhibits robust generalization and adaptivity, dynamically modulating rectification efforts based on task difficulty while leveraging context-aware indicators to resolve a wide spectrum of error patterns. Our code and dataset are released at https://github.com/TonySY2/AgentDropoutV2.</p> - https://arxiv.org/abs/2602.23258 - Thu, 26 Feb 2026 17:31:43 +0000 + UltraDexGrasp: Learning Universal Dexterous Grasping for Bimanual Robots with Synthetic Data + https://arxiv.org/abs/2603.05312 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.05312.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sizhe Yang, Yiman Xie, Zhixuan Liang, Yang Tian, Jia Zeng, Dahua Lin, Jiangmiao Pang</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Grasping is a fundamental capability for robots to interact with the physical world. Humans, equipped with two hands, autonomously select appropriate grasp strategies based on the shape, size, and weight of objects, enabling robust grasping and subsequent manipulation. In contrast, current robotic grasping remains limited, particularly in multi-strategy settings. Although substantial efforts have targeted parallel-gripper and single-hand grasping, dexterous grasping for bimanual robots remains underexplored, with data being a primary bottleneck. Achieving physically plausible and geometrically conforming grasps that can withstand external wrenches poses significant challenges. To address these issues, we introduce UltraDexGrasp, a framework for universal dexterous grasping with bimanual robots. The proposed data-generation pipeline integrates optimization-based grasp synthesis with planning-based demonstration generation, yielding high-quality and diverse trajectories across multiple grasp strategies. With this framework, we curate UltraDexGrasp-20M, a large-scale, multi-strategy grasp dataset comprising 20 million frames across 1,000 objects. Based on UltraDexGrasp-20M, we further develop a simple yet effective grasp policy that takes point clouds as input, aggregates scene features via unidirectional attention, and predicts control commands. Trained exclusively on synthetic data, the policy achieves robust zero-shot sim-to-real transfer and consistently succeeds on novel objects with varied shapes, sizes, and weights, attaining an average success rate of 81.2% in real-world universal dexterous grasping. To facilitate future research on grasping with bimanual robots, we open-source the data generation pipeline at https://github.com/InternRobotics/UltraDexGrasp.</p> + https://arxiv.org/abs/2603.05312 + Thu, 05 Mar 2026 15:54:21 +0000 - Risk-Aware World Model Predictive Control for Generalizable End-to-End Autonomous Driving - https://arxiv.org/abs/2602.23259 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.23259.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiangxin Sun, Feng Xue, Teng Long, Chang Liu, Jian-Fang Hu, Wei-Shi Zheng, Nicu Sebe</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> With advances in imitation learning (IL) and large-scale driving datasets, end-to-end autonomous driving (E2E-AD) has made great progress recently. Currently, IL-based methods have become a mainstream paradigm: models rely on standard driving behaviors given by experts, and learn to minimize the discrepancy between their actions and expert actions. However, this objective of "only driving like the expert" suffers from limited generalization: when encountering rare or unseen long-tail scenarios outside the distribution of expert demonstrations, models tend to produce unsafe decisions in the absence of prior experience. This raises a fundamental question: Can an E2E-AD system make reliable decisions without any expert action supervision? Motivated by this, we propose a unified framework named Risk-aware World Model Predictive Control (RaWMPC) to address this generalization dilemma through robust control, without reliance on expert demonstrations. Practically, RaWMPC leverages a world model to predict the consequences of multiple candidate actions and selects low-risk actions through explicit risk evaluation. To endow the world model with the ability to predict the outcomes of risky driving behaviors, we design a risk-aware interaction strategy that systematically exposes the world model to hazardous behaviors, making catastrophic outcomes predictable and thus avoidable. Furthermore, to generate low-risk candidate actions at test time, we introduce a self-evaluation distillation method to distill riskavoidance capabilities from the well-trained world model into a generative action proposal network without any expert demonstration. Extensive experiments show that RaWMPC outperforms state-of-the-art methods in both in-distribution and out-of-distribution scenarios, while providing superior decision interpretability.</p> - https://arxiv.org/abs/2602.23259 - Thu, 26 Feb 2026 17:32:30 +0000 + On-Policy Self-Distillation for Reasoning Compression + https://arxiv.org/abs/2603.05433 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.05433.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hejian Sang, Yuanda Xu, Zhengze Zhou, Ran He, Zhipeng Wang, Jiachen Sun</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Reasoning models think out loud, but much of what they say is noise. We introduce OPSDC (On-Policy Self-Distillation for Reasoning Compression), a method that teaches models to reason more concisely by distilling their own concise behavior back into themselves. The entire approach reduces to one idea: condition the same model on a "be concise" instruction to obtain teacher logits, and minimize per-token reverse KL on the student's own rollouts. No ground-truth answers, no token budgets, no difficulty estimators. Just self-distillation. Yet this simplicity belies surprising sophistication: OPSDC automatically compresses easy problems aggressively while preserving the deliberation needed for hard ones. On Qwen3-8B and Qwen3-14B, we achieve 57-59% token reduction on MATH-500 while improving accuracy by 9-16 points absolute. On AIME 2024, the 14B model gains 10 points with 41% compression. The secret? Much of what reasoning models produce is not just redundant-it is actively harmful, compounding errors with every unnecessary token.</p> + https://arxiv.org/abs/2603.05433 + Thu, 05 Mar 2026 17:54:40 +0000 - Retrieve and Segment: Are a Few Examples Enough to Bridge the Supervision Gap in Open-Vocabulary Segmentation? - https://arxiv.org/abs/2602.23339 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.23339.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tilemachos Aravanis, Vladan Stojnić, Bill Psomas, Nikos Komodakis, Giorgos Tolias</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Open-vocabulary segmentation (OVS) extends the zero-shot recognition capabilities of vision-language models (VLMs) to pixel-level prediction, enabling segmentation of arbitrary categories specified by text prompts. Despite recent progress, OVS lags behind fully supervised approaches due to two challenges: the coarse image-level supervision used to train VLMs and the semantic ambiguity of natural language. We address these limitations by introducing a few-shot setting that augments textual prompts with a support set of pixel-annotated images. Building on this, we propose a retrieval-augmented test-time adapter that learns a lightweight, per-image classifier by fusing textual and visual support features. Unlike prior methods relying on late, hand-crafted fusion, our approach performs learned, per-query fusion, achieving stronger synergy between modalities. The method supports continually expanding support sets, and applies to fine-grained tasks such as personalized segmentation. Experiments show that we significantly narrow the gap between zero-shot and supervised segmentation while preserving open-vocabulary ability.</p> - https://arxiv.org/abs/2602.23339 - Thu, 26 Feb 2026 18:45:33 +0000 + RealWonder: Real-Time Physical Action-Conditioned Video Generation + https://arxiv.org/abs/2603.05449 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.05449.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wei Liu, Ziyu Chen, Zizhang Li, Yue Wang, Hong-Xing Yu, Jiajun Wu</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Current video generation models cannot simulate physical consequences of 3D actions like forces and robotic manipulations, as they lack structural understanding of how actions affect 3D scenes. We present RealWonder, the first real-time system for action-conditioned video generation from a single image. Our key insight is using physics simulation as an intermediate bridge: instead of directly encoding continuous actions, we translate them through physics simulation into visual representations (optical flow and RGB) that video models can process. RealWonder integrates three components: 3D reconstruction from single images, physics simulation, and a distilled video generator requiring only 4 diffusion steps. Our system achieves 13.2 FPS at 480x832 resolution, enabling interactive exploration of forces, robot actions, and camera controls on rigid objects, deformable bodies, fluids, and granular materials. We envision RealWonder opens new opportunities to apply video models in immersive experiences, AR/VR, and robot learning. Our code and model weights are publicly available in our project website: https://liuwei283.github.io/RealWonder/</p> + https://arxiv.org/abs/2603.05449 + Thu, 05 Mar 2026 18:22:54 +0000 - VGG-T^3: Offline Feed-Forward 3D Reconstruction at Scale - https://arxiv.org/abs/2602.23361 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.23361.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sven Elflein, Ruilong Li, Sérgio Agostinho, Zan Gojcic, Laura Leal-Taixé, Qunjie Zhou, Aljosa Osep</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> We present a scalable 3D reconstruction model that addresses a critical limitation in offline feed-forward methods: their computational and memory requirements grow quadratically w.r.t. the number of input images. Our approach is built on the key insight that this bottleneck stems from the varying-length Key-Value (KV) space representation of scene geometry, which we distill into a fixed-size Multi-Layer Perceptron (MLP) via test-time training. VGG-T^3 (Visual Geometry Grounded Test Time Training) scales linearly w.r.t. the number of input views, similar to online models, and reconstructs a 1k image collection in just 54 seconds, achieving a 11.6times speed-up over baselines that rely on softmax attention. Since our method retains global scene aggregation capability, our point map reconstruction error outperforming other linear-time methods by large margins. Finally, we demonstrate visual localization capabilities of our model by querying the scene representation with unseen images.</p> - https://arxiv.org/abs/2602.23361 - Thu, 26 Feb 2026 18:59:33 +0000 + Towards Multimodal Lifelong Understanding: A Dataset and Agentic Baseline + https://arxiv.org/abs/2603.05484 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.05484.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Guo Chen, Lidong Lu, Yicheng Liu, Liangrui Dong, Lidong Zou, Jixin Lv, Zhenquan Li, Xinyi Mao, Baoqi Pei, Shihao Wang, Zhiqi Li, Karan Sapra, Fuxiao Liu, Yin-Dong Zheng, Yifei Huang, Limin Wang, Zhiding Yu, Andrew Tao, Guilin Liu, Tong Lu</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> While datasets for video understanding have scaled to hour-long durations, they typically consist of densely concatenated clips that differ from natural, unscripted daily life. To bridge this gap, we introduce MM-Lifelong, a dataset designed for Multimodal Lifelong Understanding. Comprising 181.1 hours of footage, it is structured across Day, Week, and Month scales to capture varying temporal densities. Extensive evaluations reveal two critical failure modes in current paradigms: end-to-end MLLMs suffer from a Working Memory Bottleneck due to context saturation, while representative agentic baselines experience Global Localization Collapse when navigating sparse, month-long timelines. To address this, we propose the Recursive Multimodal Agent (ReMA), which employs dynamic memory management to iteratively update a recursive belief state, significantly outperforming existing methods. Finally, we establish dataset splits designed to isolate temporal and domain biases, providing a rigorous foundation for future research in supervised learning and out-of-distribution generalization.</p> + https://arxiv.org/abs/2603.05484 + Thu, 05 Mar 2026 18:52:12 +0000 - MediX-R1: Open Ended Medical Reinforcement Learning - https://arxiv.org/abs/2602.23363 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.23363.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sahal Shaji Mullappilly, Mohammed Irfan Kurpath, Omair Mohamed, Mohamed Zidan, Fahad Khan, Salman Khan, Rao Anwer, Hisham Cholakkal</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> We introduce MediX-R1, an open-ended Reinforcement Learning (RL) framework for medical multimodal large language models (MLLMs) that enables clinically grounded, free-form answers beyond multiple-choice formats. MediX-R1 fine-tunes a baseline vision-language backbone with Group Based RL and a composite reward tailored for medical reasoning: an LLM-based accuracy reward that judges semantic correctness with a strict YES/NO decision, a medical embedding-based semantic reward to capture paraphrases and terminology variants, and lightweight format and modality rewards that enforce interpretable reasoning and modality recognition. This multi-signal design provides stable, informative feedback for open-ended outputs where traditional verifiable or MCQ-only rewards fall short. To measure progress, we propose a unified evaluation framework for both text-only and image+text tasks that uses a Reference-based LLM-as-judge in place of brittle string-overlap metrics, capturing semantic correctness, reasoning, and contextual alignment. Despite using only sim51K instruction examples, MediX-R1 achieves excellent results across standard medical LLM (text-only) and VLM (image + text) benchmarks, outperforming strong open-source baselines and delivering particularly large gains on open-ended clinical tasks. Our results demonstrate that open-ended RL with comprehensive reward signals and LLM-based evaluation is a practical path toward reliable medical reasoning in multimodal models. Our trained models, curated datasets and source code are available at https://medix.cvmbzuai.com</p> - https://arxiv.org/abs/2602.23363 - Thu, 26 Feb 2026 18:59:46 +0000 + RoboPocket: Improve Robot Policies Instantly with Your Phone + https://arxiv.org/abs/2603.05504 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.05504.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junjie Fang, Wendi Chen, Han Xue, Fangyuan Zhou, Tian Le, Yi Wang, Yuting Zhang, Jun Lv, Chuan Wen, Cewu Lu</p><p><b>Upvotes:</b> 30</p><p><b>Summary:</b> Scaling imitation learning is fundamentally constrained by the efficiency of data collection. While handheld interfaces have emerged as a scalable solution for in-the-wild data acquisition, they predominantly operate in an open-loop manner: operators blindly collect demonstrations without knowing the underlying policy's weaknesses, leading to inefficient coverage of critical state distributions. Conversely, interactive methods like DAgger effectively address covariate shift but rely on physical robot execution, which is costly and difficult to scale. To reconcile this trade-off, we introduce RoboPocket, a portable system that enables Robot-Free Instant Policy Iteration using single consumer smartphones. Its core innovation is a Remote Inference framework that visualizes the policy's predicted trajectory via Augmented Reality (AR) Visual Foresight. This immersive feedback allows collectors to proactively identify potential failures and focus data collection on the policy's weak regions without requiring a physical robot. Furthermore, we implement an asynchronous Online Finetuning pipeline that continuously updates the policy with incoming data, effectively closing the learning loop in minutes. Extensive experiments demonstrate that RoboPocket adheres to data scaling laws and doubles the data efficiency compared to offline scaling strategies, overcoming their long-standing efficiency bottleneck. Moreover, our instant iteration loop also boosts sample efficiency by up to 2times in distributed environments a small number of interactive corrections per person. Project page and videos: https://robo-pocket.github.io.</p> + https://arxiv.org/abs/2603.05504 + Thu, 05 Mar 2026 18:59:38 +0000