748 lines
217 KiB
XML
748 lines
217 KiB
XML
<?xml version='1.0' encoding='UTF-8'?>
|
|
<rss xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/" version="2.0">
|
|
<channel>
|
|
<title>Hugging Face Daily Papers</title>
|
|
<link>https://huggingface.co/papers</link>
|
|
<description>Daily research papers curated by the Hugging Face community.</description>
|
|
<docs>http://www.rssboard.org/rss-specification</docs>
|
|
<generator>python-feedgen</generator>
|
|
<language>en</language>
|
|
<lastBuildDate>Mon, 09 Mar 2026 00:15:39 +0000</lastBuildDate>
|
|
<item>
|
|
<title>Spilled Energy in Large Language Models</title>
|
|
<link>https://arxiv.org/abs/2602.18671</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.18671</guid>
|
|
<pubDate>Sat, 21 Feb 2026 00:38:47 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Classroom Final Exam: An Instructor-Tested Reasoning Benchmark</title>
|
|
<link>https://arxiv.org/abs/2602.19517</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.19517</guid>
|
|
<pubDate>Mon, 23 Feb 2026 05:17:41 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>From Scale to Speed: Adaptive Test-Time Scaling for Image Editing</title>
|
|
<link>https://arxiv.org/abs/2603.00141</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.00141</guid>
|
|
<pubDate>Tue, 24 Feb 2026 09:13:16 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>LongVideo-R1: Smart Navigation for Low-cost Long Video Understanding</title>
|
|
<link>https://arxiv.org/abs/2602.20913</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.20913</guid>
|
|
<pubDate>Tue, 24 Feb 2026 13:49:47 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Shared Nature, Unique Nurture: PRISM for Pluralistic Reasoning via In-context Structure Modeling</title>
|
|
<link>https://arxiv.org/abs/2602.21317</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.21317</guid>
|
|
<pubDate>Tue, 24 Feb 2026 19:38:31 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Tool-R0: Self-Evolving LLM Agents for Tool-Learning from Zero Data</title>
|
|
<link>https://arxiv.org/abs/2602.21320</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.21320</guid>
|
|
<pubDate>Tue, 24 Feb 2026 19:41:18 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>How to Take a Memorable Picture? Empowering Users with Actionable Feedback</title>
|
|
<link>https://arxiv.org/abs/2602.21877</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.21877</guid>
|
|
<pubDate>Wed, 25 Feb 2026 13:02:35 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Recovered in Translation: Efficient Pipeline for Automated Translation of Benchmarks and Datasets</title>
|
|
<link>https://arxiv.org/abs/2602.22207</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.22207</guid>
|
|
<pubDate>Wed, 25 Feb 2026 18:58:25 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>dLLM: Simple Diffusion Language Modeling</title>
|
|
<link>https://arxiv.org/abs/2602.22661</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.22661</guid>
|
|
<pubDate>Thu, 26 Feb 2026 06:26:02 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Towards Simulating Social Media Users with LLMs: Evaluating the Operational Validity of Conditioned Comment Prediction</title>
|
|
<link>https://arxiv.org/abs/2602.22752</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.22752</guid>
|
|
<pubDate>Thu, 26 Feb 2026 08:40:21 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>SkillNet: Create, Evaluate, and Connect AI Skills</title>
|
|
<link>https://arxiv.org/abs/2603.04448</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.04448</guid>
|
|
<pubDate>Thu, 26 Feb 2026 14:24:02 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>AgentVista: Evaluating Multimodal Agents in Ultra-Challenging Realistic Visual Scenarios</title>
|
|
<link>https://arxiv.org/abs/2602.23166</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.23166</guid>
|
|
<pubDate>Thu, 26 Feb 2026 16:30:46 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Large Multimodal Models as General In-Context Classifiers</title>
|
|
<link>https://arxiv.org/abs/2602.23229</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.23229</guid>
|
|
<pubDate>Thu, 26 Feb 2026 17:08:18 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Truncated Step-Level Sampling with Process Rewards for Retrieval-Augmented Reasoning</title>
|
|
<link>https://arxiv.org/abs/2602.23440</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.23440</guid>
|
|
<pubDate>Thu, 26 Feb 2026 19:05:40 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>CiteAudit: You Cited It, But Did You Read It? A Benchmark for Verifying Scientific References in the LLM Era</title>
|
|
<link>https://arxiv.org/abs/2602.23452</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.23452</guid>
|
|
<pubDate>Thu, 26 Feb 2026 19:17:39 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Humans and LLMs Diverge on Probabilistic Inferences</title>
|
|
<link>https://arxiv.org/abs/2602.23546</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.23546</guid>
|
|
<pubDate>Thu, 26 Feb 2026 23:00:41 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>SWE-rebench V2: Language-Agnostic SWE Task Collection at Scale</title>
|
|
<link>https://arxiv.org/abs/2602.23866</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.23866</guid>
|
|
<pubDate>Fri, 27 Feb 2026 10:06:10 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>LK Losses: Direct Acceptance Rate Optimization for Speculative Decoding</title>
|
|
<link>https://arxiv.org/abs/2602.23881</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.23881</guid>
|
|
<pubDate>Fri, 27 Feb 2026 10:20:11 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Ref-Adv: Exploring MLLM Visual Reasoning in Referring Expression Tasks</title>
|
|
<link>https://arxiv.org/abs/2602.23898</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.23898</guid>
|
|
<pubDate>Fri, 27 Feb 2026 10:47:26 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Half-Truths Break Similarity-Based Retrieval</title>
|
|
<link>https://arxiv.org/abs/2602.23906</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.23906</guid>
|
|
<pubDate>Fri, 27 Feb 2026 10:56:31 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Accelerating Masked Image Generation by Learning Latent Controlled Dynamics</title>
|
|
<link>https://arxiv.org/abs/2602.23996</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.23996</guid>
|
|
<pubDate>Fri, 27 Feb 2026 13:16:58 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>InfoNCE Induces Gaussian Distribution</title>
|
|
<link>https://arxiv.org/abs/2602.24012</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.24012</guid>
|
|
<pubDate>Fri, 27 Feb 2026 13:35:58 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>SenCache: Accelerating Diffusion Model Inference via Sensitivity-Aware Caching</title>
|
|
<link>https://arxiv.org/abs/2602.24208</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.24208</guid>
|
|
<pubDate>Fri, 27 Feb 2026 17:36:09 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Enhancing Spatial Understanding in Image Generation via Reward Modeling</title>
|
|
<link>https://arxiv.org/abs/2602.24233</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.24233</guid>
|
|
<pubDate>Fri, 27 Feb 2026 17:59:57 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Compositional Generalization Requires Linear, Orthogonal Representations in Vision Embedding Models</title>
|
|
<link>https://arxiv.org/abs/2602.24264</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.24264</guid>
|
|
<pubDate>Fri, 27 Feb 2026 18:32:31 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Memory Caching: RNNs with Growing Memory</title>
|
|
<link>https://arxiv.org/abs/2602.24281</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.24281</guid>
|
|
<pubDate>Fri, 27 Feb 2026 18:53:41 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation</title>
|
|
<link>https://arxiv.org/abs/2602.24286</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.24286</guid>
|
|
<pubDate>Fri, 27 Feb 2026 18:58:05 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Mode Seeking meets Mean Seeking for Fast Long Video Generation</title>
|
|
<link>https://arxiv.org/abs/2602.24289</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.24289</guid>
|
|
<pubDate>Fri, 27 Feb 2026 18:59:02 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>DreamWorld: Unified World Modeling in Video Generation</title>
|
|
<link>https://arxiv.org/abs/2603.00466</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.00466</guid>
|
|
<pubDate>Sat, 28 Feb 2026 05:02:39 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Spectral Condition for μP under Width-Depth Scaling</title>
|
|
<link>https://arxiv.org/abs/2603.00541</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.00541</guid>
|
|
<pubDate>Sat, 28 Feb 2026 08:38:50 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>CMI-RewardBench: Evaluating Music Reward Models with Compositional Multimodal Instruction</title>
|
|
<link>https://arxiv.org/abs/2603.00610</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.00610</guid>
|
|
<pubDate>Sat, 28 Feb 2026 12:10:58 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>InfoPO: Information-Driven Policy Optimization for User-Centric Agents</title>
|
|
<link>https://arxiv.org/abs/2603.00656</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.00656</guid>
|
|
<pubDate>Sat, 28 Feb 2026 13:58:14 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>STMI: Segmentation-Guided Token Modulation with Cross-Modal Hypergraph Interaction for Multi-Modal Object Re-Identification</title>
|
|
<link>https://arxiv.org/abs/2603.00695</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.00695</guid>
|
|
<pubDate>Sat, 28 Feb 2026 15:07:10 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Qwen3-Coder-Next Technical Report</title>
|
|
<link>https://arxiv.org/abs/2603.00729</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.00729</guid>
|
|
<pubDate>Sat, 28 Feb 2026 16:25:04 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>CHIMERA: Compact Synthetic Data for Generalizable LLM Reasoning</title>
|
|
<link>https://arxiv.org/abs/2603.00889</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.00889</guid>
|
|
<pubDate>Sun, 01 Mar 2026 03:23:41 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>VGGT-Det: Mining VGGT Internal Priors for Sensor-Geometry-Free Multi-View Indoor 3D Object Detection</title>
|
|
<link>https://arxiv.org/abs/2603.00912</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.00912</guid>
|
|
<pubDate>Sun, 01 Mar 2026 04:25:52 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>LLaDA-o: An Effective and Length-Adaptive Omni Diffusion Model</title>
|
|
<link>https://arxiv.org/abs/2603.01068</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.01068</guid>
|
|
<pubDate>Sun, 01 Mar 2026 12:05:06 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Unified Vision-Language Modeling via Concept Space Alignment</title>
|
|
<link>https://arxiv.org/abs/2603.01096</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.01096</guid>
|
|
<pubDate>Sun, 01 Mar 2026 13:22:44 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Learn Hard Problems During RL with Reference Guided Fine-tuning</title>
|
|
<link>https://arxiv.org/abs/2603.01223</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.01223</guid>
|
|
<pubDate>Sun, 01 Mar 2026 18:41:28 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>AgilePruner: An Empirical Study of Attention and Diversity for Adaptive Visual Token Pruning in Large Vision-Language Models</title>
|
|
<link>https://arxiv.org/abs/2603.01236</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.01236</guid>
|
|
<pubDate>Sun, 01 Mar 2026 19:14:39 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Spectral Attention Steering for Prompt Highlighting</title>
|
|
<link>https://arxiv.org/abs/2603.01281</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.01281</guid>
|
|
<pubDate>Sun, 01 Mar 2026 21:35:09 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>When Does RL Help Medical VLMs? Disentangling Vision, SFT, and RL Gains</title>
|
|
<link>https://arxiv.org/abs/2603.01301</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.01301</guid>
|
|
<pubDate>Sun, 01 Mar 2026 22:16:19 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>SciDER: Scientific Data-centric End-to-end Researcher</title>
|
|
<link>https://arxiv.org/abs/2603.01421</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.01421</guid>
|
|
<pubDate>Mon, 02 Mar 2026 03:53:20 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>LaSER: Internalizing Explicit Reasoning into Latent Space for Dense Retrieval</title>
|
|
<link>https://arxiv.org/abs/2603.01425</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.01425</guid>
|
|
<pubDate>Mon, 02 Mar 2026 04:11:18 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>PhotoBench: Beyond Visual Matching Towards Personalized Intent-Driven Photo Retrieval</title>
|
|
<link>https://arxiv.org/abs/2603.01493</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.01493</guid>
|
|
<pubDate>Mon, 02 Mar 2026 06:02:40 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>RubricBench: Aligning Model-Generated Rubrics with Human Standards</title>
|
|
<link>https://arxiv.org/abs/2603.01562</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.01562</guid>
|
|
<pubDate>Mon, 02 Mar 2026 07:39:49 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Beyond Length Scaling: Synergizing Breadth and Depth for Generative Reward Models</title>
|
|
<link>https://arxiv.org/abs/2603.01571</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.01571</guid>
|
|
<pubDate>Mon, 02 Mar 2026 07:54:29 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Surgical Post-Training: Cutting Errors, Keeping Knowledge</title>
|
|
<link>https://arxiv.org/abs/2603.01683</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.01683</guid>
|
|
<pubDate>Mon, 02 Mar 2026 10:12:56 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Legal RAG Bench: an end-to-end benchmark for legal RAG</title>
|
|
<link>https://arxiv.org/abs/2603.01710</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.01710</guid>
|
|
<pubDate>Mon, 02 Mar 2026 10:34:28 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>OpenAutoNLU: Open Source AutoML Library for NLU</title>
|
|
<link>https://arxiv.org/abs/2603.01824</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.01824</guid>
|
|
<pubDate>Mon, 02 Mar 2026 12:56:54 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>FireRed-OCR Technical Report</title>
|
|
<link>https://arxiv.org/abs/2603.01840</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.01840</guid>
|
|
<pubDate>Mon, 02 Mar 2026 13:19:23 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Agentic Code Reasoning</title>
|
|
<link>https://arxiv.org/abs/2603.01896</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.01896</guid>
|
|
<pubDate>Mon, 02 Mar 2026 14:17:06 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Efficient RLVR Training via Weighted Mutual Information Data Selection</title>
|
|
<link>https://arxiv.org/abs/2603.01907</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.01907</guid>
|
|
<pubDate>Mon, 02 Mar 2026 14:25:07 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>CoVe: Training Interactive Tool-Use Agents via Constraint-Guided Verification</title>
|
|
<link>https://arxiv.org/abs/2603.01940</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.01940</guid>
|
|
<pubDate>Mon, 02 Mar 2026 14:56:35 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>CharacterFlywheel: Scaling Iterative Improvement of Engaging and Steerable LLMs in Production</title>
|
|
<link>https://arxiv.org/abs/2603.01973</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.01973</guid>
|
|
<pubDate>Mon, 02 Mar 2026 15:27:31 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>MMR-Life: Piecing Together Real-life Scenes for Multimodal Multi-image Reasoning</title>
|
|
<link>https://arxiv.org/abs/2603.02024</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.02024</guid>
|
|
<pubDate>Mon, 02 Mar 2026 16:06:23 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>WorldStereo: Bridging Camera-Guided Video Generation and Scene Reconstruction via 3D Geometric Memories</title>
|
|
<link>https://arxiv.org/abs/2603.02049</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.02049</guid>
|
|
<pubDate>Mon, 02 Mar 2026 16:36:56 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Recursive Think-Answer Process for LLMs and VLMs</title>
|
|
<link>https://arxiv.org/abs/2603.02099</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.02099</guid>
|
|
<pubDate>Mon, 02 Mar 2026 17:20:10 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>OmniLottie: Generating Vector Animations via Parameterized Lottie Tokens</title>
|
|
<link>https://arxiv.org/abs/2603.02138</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.02138</guid>
|
|
<pubDate>Mon, 02 Mar 2026 17:59:05 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>SageBwd: A Trainable Low-bit Attention</title>
|
|
<link>https://arxiv.org/abs/2603.02170</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.02170</guid>
|
|
<pubDate>Mon, 02 Mar 2026 18:39:49 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Kiwi-Edit: Versatile Video Editing via Instruction and Reference Guidance</title>
|
|
<link>https://arxiv.org/abs/2603.02175</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.02175</guid>
|
|
<pubDate>Mon, 02 Mar 2026 18:46:28 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Tool Verification for Test-Time Reinforcement Learning</title>
|
|
<link>https://arxiv.org/abs/2603.02203</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.02203</guid>
|
|
<pubDate>Mon, 02 Mar 2026 18:57:52 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Reasoning Core: A Scalable Procedural Data Generation Suite for Symbolic Pre-training and Post-Training</title>
|
|
<link>https://arxiv.org/abs/2603.02208</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.02208</guid>
|
|
<pubDate>Mon, 02 Mar 2026 18:59:29 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>HiFi-Inpaint: Towards High-Fidelity Reference-Based Inpainting for Generating Detail-Preserving Human-Product Images</title>
|
|
<link>https://arxiv.org/abs/2603.02210</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.02210</guid>
|
|
<pubDate>Mon, 02 Mar 2026 18:59:36 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>PRISM: Pushing the Frontier of Deep Think via Process Reward Model-Guided Inference</title>
|
|
<link>https://arxiv.org/abs/2603.02479</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.02479</guid>
|
|
<pubDate>Tue, 03 Mar 2026 00:03:42 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>MUSE: A Run-Centric Platform for Multimodal Unified Safety Evaluation of Large Language Models</title>
|
|
<link>https://arxiv.org/abs/2603.02482</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.02482</guid>
|
|
<pubDate>Tue, 03 Mar 2026 00:10:23 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>MemSifter: Offloading LLM Memory Retrieval via Outcome-Driven Proxy Reasoning</title>
|
|
<link>https://arxiv.org/abs/2603.03379</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.03379</guid>
|
|
<pubDate>Tue, 03 Mar 2026 02:57:38 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Track4World: Feedforward World-centric Dense 3D Tracking of All Pixels</title>
|
|
<link>https://arxiv.org/abs/2603.02573</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.02573</guid>
|
|
<pubDate>Tue, 03 Mar 2026 03:45:43 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>How Controllable Are Large Language Models? A Unified Evaluation across Behavioral Granularities</title>
|
|
<link>https://arxiv.org/abs/2603.02578</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.02578</guid>
|
|
<pubDate>Tue, 03 Mar 2026 03:50:13 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Heterogeneous Agent Collaborative Reinforcement Learning</title>
|
|
<link>https://arxiv.org/abs/2603.02604</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.02604</guid>
|
|
<pubDate>Tue, 03 Mar 2026 05:09:49 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>DREAM: Where Visual Understanding Meets Text-to-Image Generation</title>
|
|
<link>https://arxiv.org/abs/2603.02667</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.02667</guid>
|
|
<pubDate>Tue, 03 Mar 2026 06:54:19 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Next Embedding Prediction Makes World Models Stronger</title>
|
|
<link>https://arxiv.org/abs/2603.02765</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.02765</guid>
|
|
<pubDate>Tue, 03 Mar 2026 09:04:28 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>NOVA: Sparse Control, Dense Synthesis for Pair-Free Video Editing</title>
|
|
<link>https://arxiv.org/abs/2603.02802</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.02802</guid>
|
|
<pubDate>Tue, 03 Mar 2026 09:41:06 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Kling-MotionControl Technical Report</title>
|
|
<link>https://arxiv.org/abs/2603.03160</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.03160</guid>
|
|
<pubDate>Tue, 03 Mar 2026 17:02:45 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing?</title>
|
|
<link>https://arxiv.org/abs/2603.03194</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.03194</guid>
|
|
<pubDate>Tue, 03 Mar 2026 17:52:01 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Chain of World: World Model Thinking in Latent Motion</title>
|
|
<link>https://arxiv.org/abs/2603.03195</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.03195</guid>
|
|
<pubDate>Tue, 03 Mar 2026 17:52:06 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Specificity-aware reinforcement learning for fine-grained open-world classification</title>
|
|
<link>https://arxiv.org/abs/2603.03197</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.03197</guid>
|
|
<pubDate>Tue, 03 Mar 2026 17:52:39 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Code2Math: Can Your Code Agent Effectively Evolve Math Problems Through Exploration?</title>
|
|
<link>https://arxiv.org/abs/2603.03202</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.03202</guid>
|
|
<pubDate>Tue, 03 Mar 2026 17:55:10 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Learning When to Act or Refuse: Guarding Agentic Reasoning Models for Safe Multi-Step Tool Use</title>
|
|
<link>https://arxiv.org/abs/2603.03205</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.03205</guid>
|
|
<pubDate>Tue, 03 Mar 2026 17:59:35 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>UniG2U-Bench: Do Unified Models Advance Multimodal Understanding?</title>
|
|
<link>https://arxiv.org/abs/2603.03241</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.03241</guid>
|
|
<pubDate>Tue, 03 Mar 2026 18:36:16 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Beyond Language Modeling: An Exploration of Multimodal Pretraining</title>
|
|
<link>https://arxiv.org/abs/2603.03276</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.03276</guid>
|
|
<pubDate>Tue, 03 Mar 2026 18:58:00 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>CFG-Ctrl: Control-Based Classifier-Free Diffusion Guidance</title>
|
|
<link>https://arxiv.org/abs/2603.03281</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.03281</guid>
|
|
<pubDate>Tue, 03 Mar 2026 18:59:48 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Utonia: Toward One Encoder for All Point Clouds</title>
|
|
<link>https://arxiv.org/abs/2603.03283</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.03283</guid>
|
|
<pubDate>Tue, 03 Mar 2026 18:59:58 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Proact-VL: A Proactive VideoLLM for Real-Time AI Companions</title>
|
|
<link>https://arxiv.org/abs/2603.03447</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.03447</guid>
|
|
<pubDate>Tue, 03 Mar 2026 19:02:46 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>InfinityStory: Unlimited Video Generation with World Consistency and Character-Aware Shot Transitions</title>
|
|
<link>https://arxiv.org/abs/2603.03646</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.03646</guid>
|
|
<pubDate>Wed, 04 Mar 2026 02:10:32 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>MOOSE-Star: Unlocking Tractable Training for Scientific Discovery by Breaking the Complexity Barrier</title>
|
|
<link>https://arxiv.org/abs/2603.03756</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.03756</guid>
|
|
<pubDate>Wed, 04 Mar 2026 06:11:18 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>T2S-Bench & Structure-of-Thought: Benchmarking and Prompting Comprehensive Text-to-Structure Reasoning</title>
|
|
<link>https://arxiv.org/abs/2603.03790</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.03790</guid>
|
|
<pubDate>Wed, 04 Mar 2026 07:05:09 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Phi-4-reasoning-vision-15B Technical Report</title>
|
|
<link>https://arxiv.org/abs/2603.03975</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.03975</guid>
|
|
<pubDate>Wed, 04 Mar 2026 12:16:53 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>RIVER: A Real-Time Interaction Benchmark for Video LLMs</title>
|
|
<link>https://arxiv.org/abs/2603.03985</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.03985</guid>
|
|
<pubDate>Wed, 04 Mar 2026 12:29:34 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Memex(RL): Scaling Long-Horizon LLM Agents via Indexed Experience Memory</title>
|
|
<link>https://arxiv.org/abs/2603.04257</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.04257</guid>
|
|
<pubDate>Wed, 04 Mar 2026 16:45:06 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>CubeComposer: Spatio-Temporal Autoregressive 4K 360° Video Generation from Perspective Video</title>
|
|
<link>https://arxiv.org/abs/2603.04291</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.04291</guid>
|
|
<pubDate>Wed, 04 Mar 2026 17:06:56 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>V_1: Unifying Generation and Self-Verification for Parallel Reasoners</title>
|
|
<link>https://arxiv.org/abs/2603.04304</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.04304</guid>
|
|
<pubDate>Wed, 04 Mar 2026 17:22:16 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>ArtHOI: Articulated Human-Object Interaction Synthesis by 4D Reconstruction from Video Priors</title>
|
|
<link>https://arxiv.org/abs/2603.04338</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.04338</guid>
|
|
<pubDate>Wed, 04 Mar 2026 17:58:04 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Helios: Real Real-Time Long Video Generation Model</title>
|
|
<link>https://arxiv.org/abs/2603.04379</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.04379</guid>
|
|
<pubDate>Wed, 04 Mar 2026 18:45:21 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Interactive Benchmarks</title>
|
|
<link>https://arxiv.org/abs/2603.04737</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.04737</guid>
|
|
<pubDate>Thu, 05 Mar 2026 02:18:26 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>DARE: Aligning LLM Agents with the R Statistical Ecosystem via Distribution-Aware Retrieval</title>
|
|
<link>https://arxiv.org/abs/2603.04743</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.04743</guid>
|
|
<pubDate>Thu, 05 Mar 2026 02:29:54 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Timer-S1: A Billion-Scale Time Series Foundation Model with Serial Scaling</title>
|
|
<link>https://arxiv.org/abs/2603.04791</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.04791</guid>
|
|
<pubDate>Thu, 05 Mar 2026 04:13:57 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>MASQuant: Modality-Aware Smoothing Quantization for Multimodal Large Language Models</title>
|
|
<link>https://arxiv.org/abs/2603.04800</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.04800</guid>
|
|
<pubDate>Thu, 05 Mar 2026 04:41:32 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Locality-Attending Vision Transformer</title>
|
|
<link>https://arxiv.org/abs/2603.04892</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.04892</guid>
|
|
<pubDate>Thu, 05 Mar 2026 07:31:49 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>KARL: Knowledge Agents via Reinforcement Learning</title>
|
|
<link>https://arxiv.org/abs/2603.05218</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.05218</guid>
|
|
<pubDate>Thu, 05 Mar 2026 14:30:25 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>UltraDexGrasp: Learning Universal Dexterous Grasping for Bimanual Robots with Synthetic Data</title>
|
|
<link>https://arxiv.org/abs/2603.05312</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.05312</guid>
|
|
<pubDate>Thu, 05 Mar 2026 15:54:21 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>On-Policy Self-Distillation for Reasoning Compression</title>
|
|
<link>https://arxiv.org/abs/2603.05433</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.05433</guid>
|
|
<pubDate>Thu, 05 Mar 2026 17:54:40 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>RealWonder: Real-Time Physical Action-Conditioned Video Generation</title>
|
|
<link>https://arxiv.org/abs/2603.05449</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.05449</guid>
|
|
<pubDate>Thu, 05 Mar 2026 18:22:54 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Towards Multimodal Lifelong Understanding: A Dataset and Agentic Baseline</title>
|
|
<link>https://arxiv.org/abs/2603.05484</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.05484</guid>
|
|
<pubDate>Thu, 05 Mar 2026 18:52:12 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>RoboPocket: Improve Robot Policies Instantly with Your Phone</title>
|
|
<link>https://arxiv.org/abs/2603.05504</link>
|
|
<description><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></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.05504</guid>
|
|
<pubDate>Thu, 05 Mar 2026 18:59:38 +0000</pubDate>
|
|
</item>
|
|
</channel>
|
|
</rss>
|