From b4a048740ec93d8a05cb0fea80ada476e12f8468 Mon Sep 17 00:00:00 2001 From: "github-actions[bot]" Date: Mon, 30 Mar 2026 00:20:00 +0000 Subject: [PATCH] bot: update weekly RSS feed --- feed_weekly.xml | 1052 +++++++++++++++++++++++------------------------ 1 file changed, 526 insertions(+), 526 deletions(-) diff --git a/feed_weekly.xml b/feed_weekly.xml index 57ec60c..9ac6d0e 100644 --- a/feed_weekly.xml +++ b/feed_weekly.xml @@ -7,741 +7,741 @@ http://www.rssboard.org/rss-specification python-feedgen en - Mon, 23 Mar 2026 00:18:39 +0000 + Mon, 30 Mar 2026 00:20:00 +0000 - Recursive Language Models Meet Uncertainty: The Surprising Effectiveness of Self-Reflective Program Search for Long Context - https://arxiv.org/abs/2603.15653 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15653.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Keivan Alizadeh, Parshin Shojaee, Minsik Cho, Mehrdad Farajtabar</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Long-context handling remains a core challenge for language models: even with extended context windows, models often fail to reliably extract, reason over, and use the information across long contexts. Recent works like Recursive Language Models (RLM) have approached this challenge by agentic way of decomposing long contexts into recursive sub-calls through programmatic interaction at inference. While promising, the success of RLM critically depends on how these context-interaction programs are selected, which has remained largely unexplored. In this paper, we study this problem and introduce SRLM, a framework that augments programmatic context interaction with uncertainty-aware Self-Reflection. SRLM leverages three intrinsic signals: self consistency, reasoning length, and verbalized confidence. These serve as complementary indicators of a model's internal uncertainty, and the model uses them to evaluate and compare candidate context-interaction programs. Extensive experiments across diverse benchmark datasets, context lengths, and backbone models, show that SRLM consistently outperforms state-of-the-art baselines, yielding up to 22% improvement over RLM under the same time budget. Our findings show that recursion itself is not the primary driver of performance in RLM, and a simple self-reflective program search can match or surpass RLM without requiring self-query or explicit recursion mechanisms. We find that for context lengths within the model's window, RLMs with recursion often degrade performance relative to the base model, whereas SRLM yields consistent gains across both short and long contexts. We also find that RLM is less effective in tasks with semantically intensive nature, where heuristic program search is insufficient and broader contextual understanding is required, while self-reflection in SRLM provides a semantic signal that better steers reasoning in these scenarios.</p> - https://arxiv.org/abs/2603.15653 - Sat, 07 Mar 2026 01:18:04 +0000 + MSA: Memory Sparse Attention for Efficient End-to-End Memory Model Scaling to 100M Tokens + https://arxiv.org/abs/2603.23516 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.23516.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yu Chen, Runkai Chen, Sheng Yi, Xinda Zhao, Xiaohong Li, Jianjin Zhang, Jun Sun, Chuanrui Hu, Yunyun Han, Lidong Bing, Yafeng Deng, Tianqiao Chen</p><p><b>Upvotes:</b> 34</p><p><b>Summary:</b> Long-term memory is a cornerstone of human intelligence. Enabling AI to process lifetime-scale information remains a long-standing pursuit in the field. Due to the constraints of full-attention architectures, the effective context length of large language models (LLMs) is typically limited to 1M tokens. Existing approaches, such as hybrid linear attention, fixed-size memory states (e.g., RNNs), and external storage methods like RAG or agent systems, attempt to extend this limit. However, they often suffer from severe precision degradation and rapidly increasing latency as context length grows, an inability to dynamically modify memory content, or a lack of end-to-end optimization. These bottlenecks impede complex scenarios like large-corpus summarization, Digital Twins, and long-history agent reasoning, while limiting memory capacity and slowing inference. We present Memory Sparse Attention (MSA), an end-to-end trainable, efficient, and massively scalable memory model framework. Through core innovations including scalable sparse attention and document-wise RoPE, MSA achieves linear complexity in both training and inference while maintaining exceptional stability, exhibiting less than 9% degradation when scaling from 16K to 100M tokens. Furthermore, KV cache compression, combined with Memory Parallel, enables 100M-token inference on 2xA800 GPUs. We also propose Memory Interleaving to facilitate complex multi-hop reasoning across scattered memory segments. MSA significantly surpasses frontier LLMs, state-of-the-art RAG systems, and leading memory agents in long-context benchmarks. These results demonstrate that by decoupling memory capacity from reasoning, MSA provides a scalable foundation to endow general-purpose models with intrinsic, lifetime-scale memory.</p> + https://arxiv.org/abs/2603.23516 + Fri, 06 Mar 2026 02:29:54 +0000 - HybridStitch: Pixel and Timestep Level Model Stitching for Diffusion Acceleration - https://arxiv.org/abs/2603.07815 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.07815.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Desen Sun, Jason Hon, Jintao Zhang, Sihang Liu</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Diffusion models have demonstrated a remarkable ability in Text-to-Image (T2I) generation applications. Despite the advanced generation output, they suffer from heavy computation overhead, especially for large models that contain tens of billions of parameters. Prior work has illustrated that replacing part of the denoising steps with a smaller model still maintains the generation quality. However, these methods only focus on saving computation for some timesteps, ignoring the difference in compute demand within one timestep. In this work, we propose HybridStitch, a new T2I generation paradigm that treats generation like editing. Specifically, we introduce a hybrid stage that jointly incorporates both the large model and the small model. HybridStitch separates the entire image into two regions: one that is relatively easy to render, enabling an early transition to the smaller model, and another that is more complex and therefore requires refinement by the large model. HybridStitch employs the small model to construct a coarse sketch while exploiting the large model to edit and refine the complex regions. According to our evaluation, HybridStitch achieves 1.83times speedup on Stable Diffusion 3, which is faster than all existing mixture of model methods.</p> - https://arxiv.org/abs/2603.07815 - Sun, 08 Mar 2026 21:34:50 +0000 + Qworld: Question-Specific Evaluation Criteria for LLMs + https://arxiv.org/abs/2603.23522 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.23522.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shanghua Gao, Yuchang Su, Pengwei Sui, Curtis Ginder, Marinka Zitnik</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Evaluating large language models (LLMs) on open-ended questions is difficult because response quality depends on the question's context. Binary scores and static rubrics fail to capture these context-dependent requirements. Existing methods define criteria at the dataset level or generate them in a single pass, which limits their ability to explore the evaluation space implied by each question. We introduce One-Question-One-World (Qworld), a method that generates question-specific evaluation criteria using a recursive expansion tree. Given a question, Qworld decomposes it into scenarios, perspectives, and fine-grained binary criteria through structured hierarchical and horizontal expansion. The resulting criteria specify what a high-quality answer must address for that question. On HealthBench, Qworld covers 89% of expert-authored criteria and generates 79% novel criteria validated by human experts. Experts rate Qworld criteria higher in insight and granularity than those produced by prior methods. When applied to 11 frontier LLMs on HealthBench and Humanity's Last Exam, Qworld reveals capability differences in dimensions such as long-term impact, equity, error handling, and interdisciplinary reasoning that coarse rubrics do not distinguish. By formulating criteria generation as structured coverage of question-implied evaluation axes, Qworld enables evaluation that adapts to each question rather than relying on fixed task-level criteria.</p> + https://arxiv.org/abs/2603.23522 + Fri, 06 Mar 2026 15:20:45 +0000 - EvoScientist: Towards Multi-Agent Evolving AI Scientists for End-to-End Scientific Discovery - https://arxiv.org/abs/2603.08127 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.08127.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yougang Lyu, Xi Zhang, Xinhao Yi, Yuyue Zhao, Shuyu Guo, Wenxiang Hu, Jan Piotrowski, Jakub Kaliski, Jacopo Urbani, Zaiqiao Meng, Lun Zhou, Xiaohui Yan</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> The increasing adoption of Large Language Models (LLMs) has enabled AI scientists to perform complex end-to-end scientific discovery tasks requiring coordination of specialized roles, including idea generation and experimental execution. However, most state-of-the-art AI scientist systems rely on static, hand-designed pipelines and fail to adapt based on accumulated interaction histories. As a result, these systems overlook promising research directions, repeat failed experiments, and pursue infeasible ideas. To address this, we introduce EvoScientist, an evolving multi-agent AI scientist framework that continuously improves research strategies through persistent memory and self-evolution. EvoScientist comprises three specialized agents: a Researcher Agent (RA) for scientific idea generation, an Engineer Agent (EA) for experiment implementation and execution, and an Evolution Manager Agent (EMA) that distills insights from prior interactions into reusable knowledge. EvoScientist contains two persistent memory modules: (i) an ideation memory, which summarizes feasible research directions from top-ranked ideas while recording previously unsuccessful directions; and (ii) an experimentation memory, which captures effective data processing and model training strategies derived from code search trajectories and best-performing implementations. These modules enable the RA and EA to retrieve relevant prior strategies, improving idea quality and code execution success rates over time. Experiments show that EvoScientist outperforms 7 open-source and commercial state-of-the-art systems in scientific idea generation, achieving higher novelty, feasibility, relevance, and clarity via automatic and human evaluation. EvoScientist also substantially improves code execution success rates through multi-agent evolution, demonstrating persistent memory's effectiveness for end-to-end scientific discovery.</p> - https://arxiv.org/abs/2603.08127 - Mon, 09 Mar 2026 09:07:19 +0000 + Reasoning as Compression: Unifying Budget Forcing via the Conditional Information Bottleneck + https://arxiv.org/abs/2603.08462 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.08462.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fabio Valerio Massoli, Andrey Kuzmin, Arash Behboodi</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> Chain-of-Thought (CoT) prompting improves LLM accuracy on complex tasks but often increases token usage and inference cost. Existing "Budget Forcing" methods reducing cost via fine-tuning with heuristic length penalties, suppress both essential reasoning and redundant filler. We recast efficient reasoning as a lossy compression problem under the Information Bottleneck (IB) principle, and identify a key theoretical gap when applying naive IB to transformers: attention violates the Markov property between prompt, reasoning trace, and response. To resolve this issue, we model CoT generation under the Conditional Information Bottleneck (CIB) principle, where the reasoning trace Z acts as a computational bridge that contains only the information about the response Y that is not directly accessible from the prompt X. This yields a general Reinforcement Learning objective: maximize task reward while compressing completions under a prior over reasoning traces, subsuming common heuristics (e.g., length penalties) as special cases (e.g., uniform priors). In contrast to naive token-counting-based approaches, we introduce a semantic prior that measures token cost by surprisal under a language model prior. Empirically, our CIB objective prunes cognitive bloat while preserving fluency and logic, improving accuracy at moderate compression and enabling aggressive compression with minimal accuracy drop.</p> + https://arxiv.org/abs/2603.08462 + Mon, 09 Mar 2026 14:56:57 +0000 - FinToolBench: Evaluating LLM Agents for Real-World Financial Tool Use - https://arxiv.org/abs/2603.08262 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.08262.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiaxuan Lu, Kong Wang, Yemin Wang, Qingmei Tang, Hongwei Zeng, Xiang Chen, Jiahao Pi, Shujian Deng, Lingzhi Chen, Yi Fu, Kehua Yang, Xiao Sun</p><p><b>Upvotes:</b> 37</p><p><b>Summary:</b> The integration of Large Language Models (LLMs) into the financial domain is driving a paradigm shift from passive information retrieval to dynamic, agentic interaction. While general-purpose tool learning has witnessed a surge in benchmarks, the financial sector, characterized by high stakes, strict compliance, and rapid data volatility, remains critically underserved. Existing financial evaluations predominantly focus on static textual analysis or document-based QA, ignoring the complex reality of tool execution. Conversely, general tool benchmarks lack the domain-specific rigor required for finance, often relying on toy environments or a negligible number of financial APIs. To bridge this gap, we introduce FinToolBench, the first real-world, runnable benchmark dedicated to evaluating financial tool learning agents. Unlike prior works limited to a handful of mock tools, FinToolBench establishes a realistic ecosystem coupling 760 executable financial tools with 295 rigorous, tool-required queries. We propose a novel evaluation framework that goes beyond binary execution success, assessing agents on finance-critical dimensions: timeliness, intent type, and regulatory domain alignment. Furthermore, we present FATR, a finance-aware tool retrieval and reasoning baseline that enhances stability and compliance. By providing the first testbed for auditable, agentic financial execution, FinToolBench sets a new standard for trustworthy AI in finance. The tool manifest, execution environment, and evaluation code will be open-sourced to facilitate future research.</p> - https://arxiv.org/abs/2603.08262 - Mon, 09 Mar 2026 11:33:05 +0000 + Deep Tabular Research via Continual Experience-Driven Execution + https://arxiv.org/abs/2603.09151 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.09151.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junnan Dong, Chuang Zhou, Zheng Yuan, Yifei Yu, Qiufeng Wang, Yinghui Li, Siyu An, Di Yin, Xing Sun, Feiyue Huang</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Large language models often struggle with complex long-horizon analytical tasks over unstructured tables, which typically feature hierarchical and bidirectional headers and non-canonical layouts. We formalize this challenge as Deep Tabular Research (DTR), requiring multi-step reasoning over interdependent table regions. To address DTR, we propose a novel agentic framework that treats tabular reasoning as a closed-loop decision-making process. We carefully design a coupled query and table comprehension for path decision making and operational execution. Specifically, (i) DTR first constructs a hierarchical meta graph to capture bidirectional semantics, mapping natural language queries into an operation-level search space; (ii) To navigate this space, we introduce an expectation-aware selection policy that prioritizes high-utility execution paths; (iii) Crucially, historical execution outcomes are synthesized into a siamese structured memory, i.e., parameterized updates and abstracted texts, enabling continual refinement. Extensive experiments on challenging unstructured tabular benchmarks verify the effectiveness and highlight the necessity of separating strategic planning from low-level execution for long-horizon tabular reasoning.</p> + https://arxiv.org/abs/2603.09151 + Tue, 10 Mar 2026 03:42:54 +0000 - FineRMoE: Dimension Expansion for Finer-Grained Expert with Its Upcycling Approach - https://arxiv.org/abs/2603.13364 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.13364.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ning Liao, Xiaoxing Wang, Xiaohan Qin, Junchi Yan</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> As revealed by the scaling law of fine-grained MoE, model performance ceases to be improved once the granularity of the intermediate dimension exceeds the optimal threshold, limiting further gains from single-dimension fine-grained design. To address this bottleneck, we propose FineRMoE (FineR-Grained MoE), an architecture that extends fine-grained expert design to both intermediate and output dimensions, aiming to enhance expert specialization beyond the single-dimension limit. We further introduce a bi-level sparse forward computation paradigm and a specialized routing mechanism to govern the activation. In addition, to obviate the prohibitive cost of training FineRMoE from scratch, we devise a generalized upcycling method to build FineRMoE in a cost-effective manner. Extensive experiments demonstrate the superior performance achieved by FineRMoE across ten standard benchmarks. Compared with the strongest baseline, FineRMoE achieves 6 times higher parameter efficiency, 281 times lower prefill latency, and 136 timese higher decoding throughput during inference.</p> - https://arxiv.org/abs/2603.13364 - Mon, 09 Mar 2026 12:00:36 +0000 + ToolRosetta: Bridging Open-Source Repositories and Large Language Model Agents through Automated Tool Standardization + https://arxiv.org/abs/2603.09290 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.09290.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shimin Di, Xujie Yuan, Hanghui Guo, Chaoqian Ouyang, Zhangze Chen, Ling Yue, Libin Zheng, Jia Zhu, Shaowu Pan, Jian Yin, Min-Ling Zhang, Yong Rui</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Reusing and invoking existing code remains costly and unreliable, as most practical tools are embedded in heterogeneous code repositories and lack standardized, executable interfaces. Although large language models (LLMs) and Model Context Protocol (MCP)-based tool invocation frameworks enable natural language task execution, current approaches rely heavily on manual tool curation and standardization, which fundamentally limits scalability. In this paper, we propose ToolRosetta, a unified framework that automatically translates open-source code repositories and APIs into MCP-compatible tools that can be reliably invoked by LLMs. Given a user task, ToolRosetta autonomously plans toolchains, identifies relevant codebases, and converts them into executable MCP services, enabling end-to-end task completion with minimal human intervention. In addition, ToolRosetta incorporates a security inspection layer to mitigate risks inherent in executing arbitrary code. Extensive experiments across diverse scientific domains demonstrate that ToolRosetta can automatically standardize a large number of open-source tools and reduce the human effort required for code reproduction and deployment. Notably, by seamlessly leveraging specialized open-source tools, ToolRosetta-powered agents consistently improve task completion performance compared to commercial LLMs and existing agent systems.</p> + https://arxiv.org/abs/2603.09290 + Tue, 10 Mar 2026 07:19:43 +0000 - Thinking in Uncertainty: Mitigating Hallucinations in MLRMs with Latent Entropy-Aware Decoding - https://arxiv.org/abs/2603.13366 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.13366.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhongxing Xu, Zhonghua Wang, Zhe Qian, Dachuan Shi, Feilong Tang, Ming Hu, Shiyan Su, Xiaocheng Zou, Wei Feng, Dwarikanath Mahapatra, Yifan Peng, Mingquan Lin, Zongyuan Ge</p><p><b>Upvotes:</b> 92</p><p><b>Summary:</b> Recent advancements in multimodal large reasoning models (MLRMs) have significantly improved performance in visual question answering. However, we observe that transition words (e.g., because, however, and wait) are closely associated with hallucinations and tend to exhibit high-entropy states. We argue that adequate contextual reasoning information can be directly extracted from the token probability distribution. Inspired by superposed representation theory, we propose leveraging latent superposed reasoning to integrate multiple candidate semantics and maintain latent reasoning trajectories. The hypothesis is that reliance on discrete textual inputs may drive the model toward sequential explicit reasoning, underutilizing dense contextual cues during high-entropy reasoning stages. Therefore, we propose constructing rich semantic representations from the token probability distributions to enhance in-context reasoning. With this goal, we present Latent Entropy-Aware Decoding (LEAD), an efficient plug-and-play decoding strategy that leverages semantic context to achieve reliable reasoning. The heart of our method lies in entropy-aware reasoning mode switching. The model employs probability-weighted continuous embeddings under high-entropy states and transitions back to discrete token embeddings as entropy decreases. Moreover, we propose a prior-guided visual anchor injection strategy that encourages the model to focus on visual information. Extensive experiments show that LEAD effectively mitigates hallucinations across various MLRMs on multiple benchmarks.</p> - https://arxiv.org/abs/2603.13366 - Mon, 09 Mar 2026 12:47:54 +0000 + Attend Before Attention: Efficient and Scalable Video Understanding via Autoregressive Gazing + https://arxiv.org/abs/2603.12254 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.12254.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Baifeng Shi, Stephanie Fu, Long Lian, Hanrong Ye, David Eigen, Aaron Reite, Boyi Li, Jan Kautz, Song Han, David M. Chan, Pavlo Molchanov, Trevor Darrell, Hongxu Yin</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> Multi-modal large language models (MLLMs) have advanced general-purpose video understanding but struggle with long, high-resolution videos -- they process every pixel equally in their vision transformers (ViTs) or LLMs despite significant spatiotemporal redundancy. We introduce AutoGaze, a lightweight module that removes redundant patches before processed by a ViT or an MLLM. Trained with next-token prediction and reinforcement learning, AutoGaze autoregressively selects a minimal set of multi-scale patches that can reconstruct the video within a user-specified error threshold, eliminating redundancy while preserving information. Empirically, AutoGaze reduces visual tokens by 4x-100x and accelerates ViTs and MLLMs by up to 19x, enabling scaling MLLMs to 1K-frame 4K-resolution videos and achieving superior results on video benchmarks (e.g., 67.0% on VideoMME). Furthermore, we introduce HLVid: the first high-resolution, long-form video QA benchmark with 5-minute 4K-resolution videos, where an MLLM scaled with AutoGaze improves over the baseline by 10.1% and outperforms the previous best MLLM by 4.5%. Project page: https://autogaze.github.io/.</p> + https://arxiv.org/abs/2603.12254 + Thu, 12 Mar 2026 17:58:52 +0000 - Can Vision-Language Models Solve the Shell Game? - https://arxiv.org/abs/2603.08436 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.08436.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tiedong Liu, Wee Sun Lee</p><p><b>Upvotes:</b> 39</p><p><b>Summary:</b> Visual entity tracking is an innate cognitive ability in humans, yet it remains a critical bottleneck for Vision-Language Models (VLMs). This deficit is often obscured in existing video benchmarks by visual shortcuts. We introduce VET-Bench, a synthetic diagnostic testbed featuring visually identical objects that necessitate tracking exclusively through spatiotemporal continuity. Our experiments reveal that current state-of-the-art VLMs perform at or near chance level on VET-Bench, exposing a fundamental limitation: an over-reliance on static frame-level features and a failure to maintain entity representations over time. We provide a theoretical analysis drawing connections to the state-tracking problem, proving that fixed-depth transformer-based VLMs are fundamentally limited in tracking indistinguishable objects without intermediate supervision due to expressivity constraints. To address this, we propose Spatiotemporal Grounded Chain-of-Thought (SGCoT): generating object trajectories as explicit intermediate states. Leveraging Molmo2's object tracking ability, we elicit SGCoT reasoning by fine-tuning on synthesized text-only data for alignment. Our method achieves state-of-the-art accuracy exceeding 90% on VET-Bench, demonstrating that VLMs can reliably solve the video shell-game task end-to-end without external tools. Our code and data are available at https://vetbench.github.io .</p> - https://arxiv.org/abs/2603.08436 - Mon, 09 Mar 2026 14:33:25 +0000 + Look Where It Matters: High-Resolution Crops Retrieval for Efficient VLMs + https://arxiv.org/abs/2603.16932 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16932.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Nimrod Shabtay, Moshe Kimhi, Artem Spector, Sivan Haray, Ehud Rivlin, Chaim Baskin, Raja Giryes, Eli Schwartz</p><p><b>Upvotes:</b> 84</p><p><b>Summary:</b> Vision-language models (VLMs) typically process images at a native high-resolution, forcing a trade-off between accuracy and computational efficiency: high-resolution inputs capture fine details but incur significant computational costs, while low-resolution inputs advocate for efficiency, they potentially miss critical visual information, like small text. We present AwaRes, a spatial-on-demand framework that resolves this accuracy-efficiency trade-off by operating on a low-resolution global view and using tool-calling to retrieve only high-resolution segments needed for a given query. We construct supervised data automatically: a judge compares low- vs.\ high-resolution answers to label whether cropping is needed, and an oracle grounding model localizes the evidence for the correct answer, which we map to a discrete crop set to form multi-turn tool-use trajectories. We train our framework with cold-start SFT followed by multi-turn GRPO with a composite reward that combines semantic answer correctness with explicit crop-cost penalties. Project page: https://nimrodshabtay.github.io/AwaRes</p> + https://arxiv.org/abs/2603.16932 + Sat, 14 Mar 2026 10:11:32 +0000 - MEMO: Memory-Augmented Model Context Optimization for Robust Multi-Turn Multi-Agent LLM Games - https://arxiv.org/abs/2603.09022 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.09022.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yunfei Xie, Kevin Wang, Bobby Cheng, Jianzhu Yao, Zhizhou Sha, Alexander Duffy, Yihan Xi, Hongyuan Mei, Cheston Tan, Chen Wei, Pramod Viswanath, Zhangyang Wang</p><p><b>Upvotes:</b> 24</p><p><b>Summary:</b> Multi-turn, multi-agent LLM game evaluations often exhibit substantial run-to-run variance. In long-horizon interactions, small early deviations compound across turns and are amplified by multi-agent coupling. This biases win rate estimates and makes rankings unreliable across repeated tournaments. Prompt choice worsens this further by producing different effective policies. We address both instability and underperformance with MEMO (Memory-augmented MOdel context optimization), a self-play framework that optimizes inference-time context by coupling retention and exploration. Retention maintains a persistent memory bank that stores structured insights from self-play trajectories and injects them as priors during later play. Exploration runs tournament-style prompt evolution with uncertainty-aware selection via TrueSkill, and uses prioritized replay to revisit rare and decisive states. Across five text-based games, MEMO raises mean win rate from 25.1% to 49.5% for GPT-4o-mini and from 20.9% to 44.3% for Qwen-2.5-7B-Instruct, using 2,000 self-play games per task. Run-to-run variance also drops, giving more stable rankings across prompt variations. These results suggest that multi-agent LLM game performance and robustness have substantial room for improvement through context optimization. MEMO achieves the largest gains in negotiation and imperfect-information games, while RL remains more effective in perfect-information settings.</p> - https://arxiv.org/abs/2603.09022 - Mon, 09 Mar 2026 23:36:32 +0000 + Representation Alignment for Just Image Transformers is not Easier than You Think + https://arxiv.org/abs/2603.14366 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.14366.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jaeyo Shin, Jiwook Kim, Hyunjung Shim</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Representation Alignment (REPA) has emerged as a simple way to accelerate Diffusion Transformers training in latent space. At the same time, pixel-space diffusion transformers such as Just image Transformers (JiT) have attracted growing attention because they remove a dependency on a pretrained tokenizer, and then avoid the reconstruction bottleneck of latent diffusion. This paper shows that the REPA can fail for JiT. REPA yields worse FID for JiT as training proceeds and collapses diversity on image subsets that are tightly clustered in the representation space of pretrained semantic encoder on ImageNet. We trace the failure to an information asymmetry: denoising occurs in the high dimensional image space, while the semantic target is strongly compressed, making direct regression a shortcut objective. We propose PixelREPA, which transforms the alignment target and constrains alignment with a Masked Transformer Adapter that combines a shallow transformer adapter with partial token masking. PixelREPA improves both training convergence and final quality. PixelREPA reduces FID from 3.66 to 3.17 for JiT-B/16 and improves Inception Score (IS) from 275.1 to 284.6 on ImageNet 256 times 256, while achieving > 2times faster convergence. Finally, PixelREPA-H/16 achieves FID=1.81 and IS=317.2. Our code is available at https://github.com/kaist-cvml/PixelREPA.</p> + https://arxiv.org/abs/2603.14366 + Sun, 15 Mar 2026 13:08:31 +0000 - One-Eval: An Agentic System for Automated and Traceable LLM Evaluation - https://arxiv.org/abs/2603.09821 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.09821.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chengyu Shen, Yanheng Hou, Minghui Pan, Runming He, Zhen Hao Wong, Meiyi Qiang, Zhou Liu, Hao Liang, Peichao Lai, Zeang Sheng, Wentao Zhang</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Reliable evaluation is essential for developing and deploying large language models, yet in practice it often requires substantial manual effort: practitioners must identify appropriate benchmarks, reproduce heterogeneous evaluation codebases, configure dataset schema mappings, and interpret aggregated metrics. To address these challenges, we present One-Eval, an agentic evaluation system that converts natural-language evaluation requests into executable, traceable, and customizable evaluation workflows. One-Eval integrates (i) NL2Bench for intent structuring and personalized benchmark planning, (ii) BenchResolve for benchmark resolution, automatic dataset acquisition, and schema normalization to ensure executability, and (iii) Metrics \& Reporting for task-aware metric selection and decision-oriented reporting beyond scalar scores. The system further incorporates human-in-the-loop checkpoints for review, editing, and rollback, while preserving sample evidence trails for debugging and auditability. Experiments show that One-Eval can execute end-to-end evaluations from diverse natural-language requests with minimal user effort, supporting more efficient and reproducible evaluation in industrial settings. Our framework is publicly available at https://github.com/OpenDCAI/One-Eval.</p> - https://arxiv.org/abs/2603.09821 - Tue, 10 Mar 2026 15:45:51 +0000 + The Pulse of Motion: Measuring Physical Frame Rate from Visual Dynamics + https://arxiv.org/abs/2603.14375 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.14375.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiangbo Gao, Mingyang Wu, Siyuan Yang, Jiongze Yu, Pardis Taghavi, Fangzhou Lin, Zhengzhong Tu</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> While recent generative video models have achieved remarkable visual realism and are being explored as world models, true physical simulation requires mastering both space and time. Current models can produce visually smooth kinematics, yet they lack a reliable internal motion pulse to ground these motions in a consistent, real-world time scale. This temporal ambiguity stems from the common practice of indiscriminately training on videos with vastly different real-world speeds, forcing them into standardized frame rates. This leads to what we term chronometric hallucination: generated sequences exhibit ambiguous, unstable, and uncontrollable physical motion speeds. To address this, we propose Visual Chronometer, a predictor that recovers the Physical Frames Per Second (PhyFPS) directly from the visual dynamics of an input video. Trained via controlled temporal resampling, our method estimates the true temporal scale implied by the motion itself, bypassing unreliable metadata. To systematically quantify this issue, we establish two benchmarks, PhyFPS-Bench-Real and PhyFPS-Bench-Gen. Our evaluations reveal a harsh reality: state-of-the-art video generators suffer from severe PhyFPS misalignment and temporal instability. Finally, we demonstrate that applying PhyFPS corrections significantly improves the human-perceived naturalness of AI-generated videos. Our project page is https://xiangbogaobarry.github.io/Visual_Chronometer/.</p> + https://arxiv.org/abs/2603.14375 + Sun, 15 Mar 2026 13:29:31 +0000 - WebVR: Benchmarking Multimodal LLMs for WebPage Recreation from Videos via Human-Aligned Visual Rubrics - https://arxiv.org/abs/2603.13391 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.13391.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuhong Dai, Yanlin Lai, Mitt Huang, Hangyu Guo, Dingming Li, Hongbo Peng, Haodong Li, Yingxiu Zhao, Haoran Lyu, Zheng Ge, Xiangyu Zhang, Daxin Jiang</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> Existing web-generation benchmarks rely on text prompts or static screenshots as input. However, videos naturally convey richer signals such as interaction flow, transition timing, and motion continuity, which are essential for faithful webpage recreation. Despite this potential, video-conditioned webpage generation remains largely unexplored, with no dedicated benchmark for this task. To fill this gap, we introduce WebVR, a benchmark that evaluates whether MLLMs can faithfully recreate webpages from demonstration videos. WebVR contains 175 webpages across diverse categories, all constructed through a controlled synthesis pipeline rather than web crawling, ensuring varied and realistic demonstrations without overlap with existing online pages. We also design a fine-grained, human-aligned visual rubric that evaluates the generated webpages across multiple dimensions. Experiments on 19 models reveal substantial gaps in recreating fine-grained style and motion quality, while the rubric-based automatic evaluation achieves 96% agreement with human preferences. We release the dataset, evaluation toolkit, and baseline results to support future research on video-to-webpage generation.</p> - https://arxiv.org/abs/2603.13391 - Wed, 11 Mar 2026 07:48:23 +0000 + HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning + https://arxiv.org/abs/2603.17024 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.17024.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shenzhi Wang, Shixuan Liu, Jing Zhou, Chang Gao, Xiong-Hui Chen, Binghai Wang, An Yang, Shiji Song, Bowen Yu, Gao Huang, Junyang Lin</p><p><b>Upvotes:</b> 105</p><p><b>Summary:</b> VLMs show strong multimodal capabilities, but they still struggle with fine-grained vision-language reasoning. We find that long CoT reasoning exposes diverse failure modes, including perception, reasoning, knowledge, and hallucination errors, which can compound across intermediate steps. However, most existing vision-language data used for RLVR does not involve complex reasoning chains that rely on visual evidence throughout, leaving these weaknesses largely unexposed. We therefore propose HopChain, a scalable framework for synthesizing multi-hop vision-language reasoning data specifically for RLVR training of VLMs. Each synthesized multi-hop query forms a logically dependent chain of instance-grounded hops, where earlier hops establish the instances, sets, or conditions needed for later hops, while the final answer remains a specific, unambiguous number suitable for verifiable rewards. We add the multi-hop data synthesized by HopChain to the original RLVR data used to train Qwen3.5-35B-A3B and Qwen3.5-397B-A17B, and compare against RLVR on the original RLVR data alone across 24 benchmarks spanning STEM and Puzzle, General VQA, Text Recognition and Document Understanding, and Video Understanding. Although this multi-hop data is not synthesized to target any specific benchmark, adding it improves 20 out of 24 benchmarks on both models, indicating broad and generalizable gains. To demonstrate that full chained queries are important, we replace them with half-multi-hop or single-hop variants, reducing the 24-benchmark average accuracy by 5.3 and 7.0 points, respectively. Multi-hop training also strengthens long-CoT vision-language reasoning, with gains peaking at more than 50 accuracy points in the ultra-long-CoT regime. These experiments establish HopChain as an effective, scalable framework for synthesizing multi-hop data that improves generalizable vision-language reasoning.</p> + https://arxiv.org/abs/2603.17024 + Tue, 17 Mar 2026 18:04:58 +0000 - Safe and Scalable Web Agent Learning via Recreated Websites - https://arxiv.org/abs/2603.10505 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.10505.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hyungjoo Chae, Jungsoo Park, Alan Ritter</p><p><b>Upvotes:</b> 25</p><p><b>Summary:</b> Training autonomous web agents is fundamentally limited by the environments they learn from: real-world websites are unsafe to explore, hard to reset, and rarely provide verifiable feedback. We propose VeriEnv, a framework that treats language models as environment creators, automatically cloning real-world websites into fully executable, verifiable synthetic environments. By exposing controlled internal access via a Python SDK, VeriEnv enables agents to self-generate tasks with deterministic, programmatically verifiable rewards, eliminating reliance on heuristic or LLM-based judges. This design decouples agent learning from unsafe real-world interaction while enabling scalable self-evolution through environment expansion. Through experiments on web agent benchmarks, we show that agents trained with VeriEnv generalize to unseen websites, achieve site-specific mastery through self-evolving training, and benefit from scaling the number of training environments. Code and resources will be released at https://github.com/kyle8581/VeriEnv upon acceptance.</p> - https://arxiv.org/abs/2603.10505 - Wed, 11 Mar 2026 07:58:53 +0000 + Astrolabe: Steering Forward-Process Reinforcement Learning for Distilled Autoregressive Video Models + https://arxiv.org/abs/2603.17051 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.17051.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Songchun Zhang, Zeyue Xue, Siming Fu, Jie Huang, Xianghao Kong, Y Ma, Haoyang Huang, Nan Duan, Anyi Rao</p><p><b>Upvotes:</b> 106</p><p><b>Summary:</b> Distilled autoregressive (AR) video models enable efficient streaming generation but frequently misalign with human visual preferences. Existing reinforcement learning (RL) frameworks are not naturally suited to these architectures, typically requiring either expensive re-distillation or solver-coupled reverse-process optimization that introduces considerable memory and computational overhead. We present Astrolabe, an efficient online RL framework tailored for distilled AR models. To overcome existing bottlenecks, we introduce a forward-process RL formulation based on negative-aware fine-tuning. By contrasting positive and negative samples directly at inference endpoints, this approach establishes an implicit policy improvement direction without requiring reverse-process unrolling. To scale this alignment to long videos, we propose a streaming training scheme that generates sequences progressively via a rolling KV-cache, applying RL updates exclusively to local clip windows while conditioning on prior context to ensure long-range coherence. Finally, to mitigate reward hacking, we integrate a multi-reward objective stabilized by uncertainty-aware selective regularization and dynamic reference updates. Extensive experiments demonstrate that our method consistently enhances generation quality across multiple distilled AR video models, serving as a robust and scalable alignment solution.</p> + https://arxiv.org/abs/2603.17051 + Tue, 17 Mar 2026 18:32:18 +0000 - Qianfan-OCR: A Unified End-to-End Model for Document Intelligence - https://arxiv.org/abs/2603.13398 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.13398.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Daxiang Dong, Mingming Zheng, Dong Xu, Chunhua Luo, Bairong Zhuang, Yuxuan Li, Ruoyun He, Haoran Wang, Wenyu Zhang, Wenbo Wang, Yicheng Wang, Xue Xiong, Ayong Zheng, Xiaoying Zuo, Ziwei Ou, Jingnan Gu, Quanhao Guo, Jianmin Wu, Dawei Yin, Dou Shen</p><p><b>Upvotes:</b> 141</p><p><b>Summary:</b> We present Qianfan-OCR, a 4B-parameter end-to-end vision-language model that unifies document parsing, layout analysis, and document understanding within a single architecture. It performs direct image-to-Markdown conversion and supports diverse prompt-driven tasks including table extraction, chart understanding, document QA, and key information extraction. To address the loss of explicit layout analysis in end-to-end OCR, we propose Layout-as-Thought, an optional thinking phase triggered by special think tokens that generates structured layout representations -- bounding boxes, element types, and reading order -- before producing final outputs, recovering layout grounding capabilities while improving accuracy on complex layouts. Qianfan-OCR ranks first among end-to-end models on OmniDocBench v1.5 (93.12) and OlmOCR Bench (79.8), achieves competitive results on OCRBench, CCOCR, DocVQA, and ChartQA against general VLMs of comparable scale, and attains the highest average score on public key information extraction benchmarks, surpassing Gemini-3.1-Pro, Seed-2.0, and Qwen3-VL-235B. The model is publicly accessible via the Baidu AI Cloud Qianfan platform.</p> - https://arxiv.org/abs/2603.13398 - Wed, 11 Mar 2026 16:08:22 +0000 + OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis + https://arxiv.org/abs/2603.20278 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.20278.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhuofeng Li, Dongfu Jiang, Xueguang Ma, Haoxiang Zhang, Ping Nie, Yuyu Zhang, Kai Zou, Jianwen Xie, Yu Zhang, Wenhu Chen</p><p><b>Upvotes:</b> 89</p><p><b>Summary:</b> Training deep research agents requires long-horizon trajectories that interleave search, evidence aggregation, and multi-step reasoning. However, existing data collection pipelines typically rely on proprietary web APIs, making large-scale trajectory synthesis costly, unstable, and difficult to reproduce. We present OpenResearcher, a reproducible pipeline that decouples one-time corpus bootstrapping from multi-turn trajectory synthesis and executes the search-and-browse loop entirely offline using three explicit browser primitives: search, open, and find, over a 15M-document corpus. Using GPT-OSS-120B as the teacher model, we synthesize over 97K trajectories, including a substantial long-horizon tail with 100+ tool calls. Supervised fine-tuning a 30B-A3B backbone on these trajectories achieves 54.8\% accuracy on BrowseComp-Plus, a +34.0 point improvement over the base model, while remaining competitive on BrowseComp, GAIA, and xbench-DeepSearch. Because the environment is offline and fully instrumented, it also enables controlled analysis, where our study reveals practical insights into deep research pipeline design, including data filtering strategies, agent configuration choices, and how retrieval success relates to final answer accuracy. We release the pipeline, synthesized trajectories, model checkpoints, and the offline search environment at https://github.com/TIGER-AI-Lab/OpenResearcher.</p> + https://arxiv.org/abs/2603.20278 + Tue, 17 Mar 2026 20:10:12 +0000 - Expert Threshold Routing for Autoregressive Language Modeling with Dynamic Computation Allocation and Load Balancing - https://arxiv.org/abs/2603.11535 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.11535.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hanchi Sun, Yixin Liu, Yonghui Wu, Lichao Sun</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Token-choice Mixture-of-Experts (TC-MoE) routes each token to a fixed number of experts, limiting dynamic computation allocation and requiring auxiliary losses to maintain load balance. We propose Expert Threshold (ET) routing, where each expert maintains an exponential moving average (EMA) threshold estimated from the global token distribution. At both training and inference, each token is independently routed to an expert if its score exceeds the expert's threshold, enabling dynamic computation allocation while achieving load balance without auxiliary losses. This fully causal mechanism eliminates dependence on other tokens in the batch, making it well-suited for autoregressive language modeling. In pretraining experiments scaling to 2.4B parameters on FineWeb-Edu, ET achieves 0.067 lower cross-entropy loss than TC-MoE, equivalent to reaching the same performance with 1.6times fewer tokens.</p> - https://arxiv.org/abs/2603.11535 - Thu, 12 Mar 2026 04:45:48 +0000 + Abstraction as a Memory-Efficient Inductive Bias for Continual Learning + https://arxiv.org/abs/2603.17198 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.17198.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Elnaz Rahmati, Nona Ghazizadeh, Zhivar Sourati, Nina Rouhani, Morteza Dehghani</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> The real world is non-stationary and infinitely complex, requiring intelligent agents to learn continually without the prohibitive cost of retraining from scratch. While online continual learning offers a framework for this setting, learning new information often interferes with previously acquired knowledge, causes forgetting and degraded generalization. To address this, we propose Abstraction-Augmented Training (AAT), a loss-level modification encouraging models to capture the latent relational structure shared across examples. By jointly optimizing over concrete instances and their abstract representations, AAT introduces a memory-efficient inductive bias that stabilizes learning in strictly online data streams, eliminating the need for a replay buffer. To capture the multi-faceted nature of abstraction, we introduce and evaluate AAT on two benchmarks: a controlled relational dataset where abstraction is realized through entity masking, and a narrative dataset where abstraction is expressed through shared proverbs. Our results show that AAT achieves performance comparable to or exceeding strong experience replay (ER) baselines, despite requiring zero additional memory and only minimal changes to the training objective. This work highlights structural abstraction as a powerful, memory-free alternative to ER.</p> + https://arxiv.org/abs/2603.17198 + Tue, 17 Mar 2026 22:59:13 +0000 - OmniForcing: Unleashing Real-time Joint Audio-Visual Generation - https://arxiv.org/abs/2603.11647 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.11647.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yaofeng Su, Yuming Li, Zeyue Xue, Jie Huang, Siming Fu, Haoran Li, Ying Li, Zezhong Qian, Haoyang Huang, Nan Duan</p><p><b>Upvotes:</b> 31</p><p><b>Summary:</b> Recent joint audio-visual diffusion models achieve remarkable generation quality but suffer from high latency due to their bidirectional attention dependencies, hindering real-time applications. We propose OmniForcing, the first framework to distill an offline, dual-stream bidirectional diffusion model into a high-fidelity streaming autoregressive generator. However, naively applying causal distillation to such dual-stream architectures triggers severe training instability, due to the extreme temporal asymmetry between modalities and the resulting token sparsity. We address the inherent information density gap by introducing an Asymmetric Block-Causal Alignment with a zero-truncation Global Prefix that prevents multi-modal synchronization drift. The gradient explosion caused by extreme audio token sparsity during the causal shift is further resolved through an Audio Sink Token mechanism equipped with an Identity RoPE constraint. Finally, a Joint Self-Forcing Distillation paradigm enables the model to dynamically self-correct cumulative cross-modal errors from exposure bias during long rollouts. Empowered by a modality-independent rolling KV-cache inference scheme, OmniForcing achieves state-of-the-art streaming generation at sim25 FPS on a single GPU, maintaining multi-modal synchronization and visual quality on par with the bidirectional teacher.Project Page: https://omniforcing.com{https://omniforcing.com}</p> - https://arxiv.org/abs/2603.11647 - Thu, 12 Mar 2026 08:17:36 +0000 + Insight-V++: Towards Advanced Long-Chain Visual Reasoning with Multimodal Large Language Models + https://arxiv.org/abs/2603.18118 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.18118.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuhao Dong, Zuyan Liu, Shulin Tian, Yongming Rao, Ziwei Liu</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Large Language Models (LLMs) have achieved remarkable reliability and advanced capabilities through extended test-time reasoning. However, extending these capabilities to Multi-modal Large Language Models (MLLMs) remains a significant challenge due to a critical scarcity of high-quality, long-chain reasoning data and optimized training pipelines. To bridge this gap, we present a unified multi-agent visual reasoning framework that systematically evolves from our foundational image-centric model, Insight-V, into a generalized spatial-temporal architecture, Insight-V++. We first propose a scalable data generation pipeline equipped with multi-granularity assessment that autonomously synthesizes structured, complex reasoning trajectories across image and video domains without human intervention. Recognizing that directly supervising MLLMs with such intricate data yields sub-optimal results, we design a dual-agent architecture comprising a reasoning agent to execute extensive analytical chains, and a summary agent to critically evaluate and distill final outcomes. While our initial framework utilized Direct Preference Optimization (DPO), its off-policy nature fundamentally constrained reinforcement learning potential. To overcome these limitations, particularly for long-horizon video understanding, Insight-V++ introduces two novel algorithms, ST-GRPO and J-GRPO, which enhance spatial-temporal reasoning and improve evaluative robustness. Crucially, by leveraging reliable feedback from the summary agent, we guide an iterative reasoning path generation process, retraining the entire multi-agent system in a continuous, self-improving loop. Extensive experiments on base models like LLaVA-NeXT and Qwen2.5-VL demonstrate significant performance gains across challenging image and video reasoning benchmarks while preserving strong capabilities on traditional perception-focused tasks.</p> + https://arxiv.org/abs/2603.18118 + Wed, 18 Mar 2026 15:28:07 +0000 - HomeSafe-Bench: Evaluating Vision-Language Models on Unsafe Action Detection for Embodied Agents in Household Scenarios - https://arxiv.org/abs/2603.11975 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.11975.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiayue Pu, Zhongxiang Sun, Zilu Zhang, Xiao Zhang, Jun Xu</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> The rapid evolution of embodied agents has accelerated the deployment of household robots in real-world environments. However, unlike structured industrial settings, household spaces introduce unpredictable safety risks, where system limitations such as perception latency and lack of common sense knowledge can lead to dangerous errors. Current safety evaluations, often restricted to static images, text, or general hazards, fail to adequately benchmark dynamic unsafe action detection in these specific contexts. To bridge this gap, we introduce HomeSafe-Bench, a challenging benchmark designed to evaluate Vision-Language Models (VLMs) on unsafe action detection in household scenarios. HomeSafe-Bench is contrusted via a hybrid pipeline combining physical simulation with advanced video generation and features 438 diverse cases across six functional areas with fine-grained multidimensional annotations. Beyond benchmarking, we propose Hierarchical Dual-Brain Guard for Household Safety (HD-Guard), a hierarchical streaming architecture for real-time safety monitoring. HD-Guard coordinates a lightweight FastBrain for continuous high-frequency screening with an asynchronous large-scale SlowBrain for deep multimodal reasoning, effectively balancing inference efficiency with detection accuracy. Evaluations demonstrate that HD-Guard achieves a superior trade-off between latency and performance, while our analysis identifies critical bottlenecks in current VLM-based safety detection.</p> - https://arxiv.org/abs/2603.11975 - Thu, 12 Mar 2026 14:25:44 +0000 + Versatile Editing of Video Content, Actions, and Dynamics without Training + https://arxiv.org/abs/2603.17989 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.17989.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Vladimir Kulikov, Roni Paiss, Andrey Voynov, Inbar Mosseri, Tali Dekel, Tomer Michaeli</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Controlled video generation has seen drastic improvements in recent years. However, editing actions and dynamic events, or inserting contents that should affect the behaviors of other objects in real-world videos, remains a major challenge. Existing trained models struggle with complex edits, likely due to the difficulty of collecting relevant training data. Similarly, existing training-free methods are inherently restricted to structure- and motion-preserving edits and do not support modification of motion or interactions. Here, we introduce DynaEdit, a training-free editing method that unlocks versatile video editing capabilities with pretrained text-to-video flow models. Our method relies on the recently introduced inversion-free approach, which does not intervene in the model internals, and is thus model-agnostic. We show that naively attempting to adapt this approach to general unconstrained editing results in severe low-frequency misalignment and high-frequency jitter. We explain the sources for these phenomena and introduce novel mechanisms for overcoming them. Through extensive experiments, we show that DynaEdit achieves state-of-the-art results on complex text-based video editing tasks, including modifying actions, inserting objects that interact with the scene, and introducing global effects.</p> + https://arxiv.org/abs/2603.17989 + Wed, 18 Mar 2026 17:50:56 +0000 - Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously - https://arxiv.org/abs/2603.12262 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.12262.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yiran Guan, Liang Yin, Dingkang Liang, Jianzhong Ju, Zhenbo Luo, Jian Luan, Yuliang Liu, Xiang Bai</p><p><b>Upvotes:</b> 30</p><p><b>Summary:</b> Online Video Large Language Models (VideoLLMs) play a critical role in supporting responsive, real-time interaction. Existing methods focus on streaming perception, lacking a synchronized logical reasoning stream. However, directly applying test-time scaling methods incurs unacceptable response latency. To address this trade-off, we propose Video Streaming Thinking (VST), a novel paradigm for streaming video understanding. It supports a thinking while watching mechanism, which activates reasoning over incoming video clips during streaming. This design improves timely comprehension and coherent cognition while preserving real-time responsiveness by amortizing LLM reasoning latency over video playback. Furthermore, we introduce a comprehensive post-training pipeline that integrates VST-SFT, which structurally adapts the offline VideoLLM to causal streaming reasoning, and VST-RL, which provides end-to-end improvement through self-exploration in a multi-turn video interaction environment. Additionally, we devise an automated training-data synthesis pipeline that uses video knowledge graphs to generate high-quality streaming QA pairs, with an entity-relation grounded streaming Chain-of-Thought to enforce multi-evidence reasoning and sustained attention to the video stream. Extensive evaluations show that VST-7B performs strongly on online benchmarks, e.g. 79.5% on StreamingBench and 59.3% on OVO-Bench. Meanwhile, VST remains competitive on offline long-form or reasoning benchmarks. Compared with Video-R1, VST responds 15.7 times faster and achieves +5.4% improvement on VideoHolmes, demonstrating higher efficiency and strong generalization across diverse video understanding tasks. Code, data, and models will be released at https://github.com/1ranGuan/VST.</p> - https://arxiv.org/abs/2603.12262 - Thu, 12 Mar 2026 17:59:51 +0000 + HiMu: Hierarchical Multimodal Frame Selection for Long Video Question Answering + https://arxiv.org/abs/2603.18558 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.18558.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dan Ben-Ami, Gabriele Serussi, Kobi Cohen, Chaim Baskin</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Long-form video question answering requires reasoning over extended temporal contexts, making frame selection critical for large vision-language models (LVLMs) bound by finite context windows. Existing methods face a sharp trade-off: similarity-based selectors are fast but collapse compositional queries into a single dense vector, losing sub-event ordering and cross-modal bindings; agent-based methods recover this structure through iterative LVLM inference, but at prohibitive cost. We introduce HiMu, a training-free framework that bridges this gap. A single text-only LLM call decomposes the query into a hierarchical logic tree whose leaves are atomic predicates, each routed to a lightweight expert spanning vision (CLIP, open-vocabulary detection, OCR) and audio (ASR, CLAP). The resulting signals are normalized, temporally smoothed to align different modalities, and composed bottom-up through fuzzy-logic operators that enforce temporal sequencing and adjacency, producing a continuous satisfaction curve. Evaluations on Video-MME, LongVideoBench and HERBench-Lite show that HiMu advances the efficiency-accuracy Pareto front: at 16 frames with Qwen3-VL 8B it outperforms all competing selectors, and with GPT-4o it surpasses agentic systems operating at 32-512 frames while requiring roughly 10x fewer FLOPs.</p> + https://arxiv.org/abs/2603.18558 + Thu, 19 Mar 2026 07:11:53 +0000 - MM-CondChain: A Programmatically Verified Benchmark for Visually Grounded Deep Compositional Reasoning - https://arxiv.org/abs/2603.12266 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.12266.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haozhan Shen, Shilin Yan, Hongwei Xue, Shuaiqi Lu, Xiaojun Tang, Guannan Zhang, Tiancheng Zhao, Jianwei Yin</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> Multimodal Large Language Models (MLLMs) are increasingly used to carry out visual workflows such as navigating GUIs, where the next step depends on verified visual compositional conditions (e.g., "if a permission dialog appears and the color of the interface is green, click Allow") and the process may branch or terminate early. Yet this capability remains under-evaluated: existing benchmarks focus on shallow-compositions or independent-constraints rather than deeply chained compositional conditionals. In this paper, we introduce MM-CondChain, a benchmark for visually grounded deep compositional reasoning. Each benchmark instance is organized as a multi-layer reasoning chain, where every layer contains a non-trivial compositional condition grounded in visual evidence and built from multiple objects, attributes, or relations. To answer correctly, an MLLM must perceive the image in detail, reason over multiple visual elements at each step, and follow the resulting execution path to the final outcome. To scalably construct such workflow-style data, we propose an agentic synthesis pipeline: a Planner orchestrates layer-by-layer generation of compositional conditions, while a Verifiable Programmatic Intermediate Representation (VPIR) ensures each layer's condition is mechanically verifiable. A Composer then assembles these verified layers into complete instructions. Using this pipeline, we construct benchmarks across three visual domains: natural images, data charts, and GUI trajectories. Experiments on a range of MLLMs show that even the strongest model attains only 53.33 Path F1, with sharp drops on hard negatives and as depth or predicate complexity grows, confirming that deep compositional reasoning remains a fundamental challenge.</p> - https://arxiv.org/abs/2603.12266 - Thu, 12 Mar 2026 17:59:56 +0000 + MemMA: Coordinating the Memory Cycle through Multi-Agent Reasoning and In-Situ Self-Evolution + https://arxiv.org/abs/2603.18718 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.18718.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Minhua Lin, Zhiwei Zhang, Hanqing Lu, Hui Liu, Xianfeng Tang, Qi He, Xiang Zhang, Suhang Wang</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Memory-augmented LLM agents maintain external memory banks to support long-horizon interaction, yet most existing systems treat construction, retrieval, and utilization as isolated subroutines. This creates two coupled challenges: strategic blindness on the forward path of the memory cycle, where construction and retrieval are driven by local heuristics rather than explicit strategic reasoning, and sparse, delayed supervision on the backward path, where downstream failures rarely translate into direct repairs of the memory bank. To address these challenges, we propose MemMA, a plug-and-play multi-agent framework that coordinates the memory cycle along both the forward and backward paths. On the forward path, a Meta-Thinker produces structured guidance that steers a Memory Manager during construction and directs a Query Reasoner during iterative retrieval. On the backward path, MemMA introduces in-situ self-evolving memory construction, which synthesizes probe QA pairs, verifies the current memory, and converts failures into repair actions before the memory is finalized. Extensive experiments on LoCoMo show that MemMA consistently outperforms existing baselines across multiple LLM backbones and improves three different storage backends in a plug-and-play manner. Our code is publicly available at https://github.com/ventr1c/memma.</p> + https://arxiv.org/abs/2603.18718 + Thu, 19 Mar 2026 10:15:59 +0000 - Efficient Reasoning with Balanced Thinking - https://arxiv.org/abs/2603.12372 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.12372.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yulin Li, Tengyao Tu, Li Ding, Junjie Wang, Huiling Zhen, Yixin Chen, Yong Li, Zhuotao Tian</p><p><b>Upvotes:</b> 133</p><p><b>Summary:</b> Large Reasoning Models (LRMs) have shown remarkable reasoning capabilities, yet they often suffer from overthinking, expending redundant computational steps on simple problems, or underthinking, failing to explore sufficient reasoning paths despite inherent capabilities. These issues lead to inefficiencies and potential inaccuracies, limiting practical deployment in resource-constrained settings. Existing methods to mitigate overthinking, such as suppressing reflective keywords or adjusting reasoning length, may inadvertently induce underthinking, compromising accuracy. Therefore, we propose ReBalance, a training-free framework that achieves efficient reasoning with balanced thinking. ReBalance leverages confidence as a continuous indicator of reasoning dynamics, identifying overthinking through high confidence variance and underthinking via consistent overconfidence. By aggregating hidden states from a small-scale dataset into reasoning mode prototypes, we compute a steering vector to guide LRMs' reasoning trajectories. A dynamic control function modulates this vector's strength and direction based on real-time confidence, pruning redundancy during overthinking, and promoting exploration during underthinking. Extensive experiments conducted on four models ranging from 0.5B to 32B, and across nine benchmarks in math reasoning, general question answering, and coding tasks demonstrate that ReBalance effectively reduces output redundancy while improving accuracy, offering a general, training-free, and plug-and-play strategy for efficient and robust LRM deployment. Code is available at https://github.com/yu-lin-li/ReBalance .</p> - https://arxiv.org/abs/2603.12372 - Thu, 12 Mar 2026 18:48:07 +0000 + Perceptio: Perception Enhanced Vision Language Models via Spatial Token Generation + https://arxiv.org/abs/2603.18795 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.18795.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuchen Li, Amanmeet Garg, Shalini Chaudhuri, Rui Zhao, Garin Kessler</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Large Vision Language Models (LVLMs) excel at semantic understanding but struggle with fine grained spatial grounding, as the model must implicitly infer complex geometry without ever producing a spatial interpretation. We present Perceptio, a perception enhanced LVLM with 2D and 3D spatial reasoning abilities, enabled via explicit semantic segmentation tokens and depth tokens generated directly within the autoregressive sequence. Concretely, we (i) distill a VQVAE depth codebook from a strong monocular teacher to tokenize dense depth into compact sequences, and (ii) integrate SAM2 based semantic segmentation tokens and VQ-VAE depth tokens inside the LLM so the model first emits spatial tokens and then answers. To stabilize depth token generation, we introduce novel composite depth-token objectives (marker, token, and count losses) and a soft-merging technique for differentiable reconstruction. We adopt a multi-task co-training strategy across diverse datasets, letting the model learn perception tokens to tackle multiple downstream tasks. Building on InternVL, Perceptio achieves state-of-the-art performance across benchmarks: improving referring expression segmentation by +0.8/+1.4/+1.1 cIoU on RefCOCO/+/g HardBLINK spatial understanding accuracy by 10.3%, and MMBench accuracy by 1.0%, demonstrating that explicit spatial chain-of-thought materially strengthens spatial grounding in LVLMs.</p> + https://arxiv.org/abs/2603.18795 + Thu, 19 Mar 2026 11:46:01 +0000 - TERMINATOR: Learning Optimal Exit Points for Early Stopping in Chain-of-Thought Reasoning - https://arxiv.org/abs/2603.12529 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.12529.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Alliot Nagle, Jakhongir Saydaliev, Dhia Garbaya, Michael Gastpar, Ashok Vardhan Makkuva, Hyeji Kim</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> Large Reasoning Models (LRMs) achieve impressive performance on complex reasoning tasks via Chain-of-Thought (CoT) reasoning, which enables them to generate intermediate thinking tokens before arriving at the final answer. However, LRMs often suffer from significant overthinking, spending excessive compute time even after the answer is generated early on. Prior work has identified the existence of an optimal reasoning length such that truncating reasoning at this point significantly shortens CoT outputs with virtually no change in performance. However, determining optimal CoT lengths for practical datasets is highly non-trivial as they are fully task and model-dependent. In this paper, we precisely address this and design TERMINATOR, an early-exit strategy for LRMs at inference to mitigate overthinking. The central idea underpinning TERMINATOR is that the first arrival of an LRM's final answer is often predictable, and we leverage these first answer positions to create a novel dataset of optimal reasoning lengths to train TERMINATOR. Powered by this approach, TERMINATOR achieves significant reductions in CoT lengths of 14%-55% on average across four challenging practical datasets: MATH-500, AIME 2025, HumanEval, and GPQA, whilst outperforming current state-of-the-art methods.</p> - https://arxiv.org/abs/2603.12529 - Fri, 13 Mar 2026 00:07:18 +0000 + AgentDS Technical Report: Benchmarking the Future of Human-AI Collaboration in Domain-Specific Data Science + https://arxiv.org/abs/2603.19005 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19005.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> An Luo, Jin Du, Xun Xian, Robert Specht, Fangqiao Tian, Ganghua Wang, Xuan Bi, Charles Fleming, Ashish Kundu, Jayanth Srinivasa, Mingyi Hong, Rui Zhang, Tianxi Li, Galin Jones, Jie Ding</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Data science plays a critical role in transforming complex data into actionable insights across numerous domains. Recent developments in large language models (LLMs) and artificial intelligence (AI) agents have significantly automated data science workflow. However, it remains unclear to what extent AI agents can match the performance of human experts on domain-specific data science tasks, and in which aspects human expertise continues to provide advantages. We introduce AgentDS, a benchmark and competition designed to evaluate both AI agents and human-AI collaboration performance in domain-specific data science. AgentDS consists of 17 challenges across six industries: commerce, food production, healthcare, insurance, manufacturing, and retail banking. We conducted an open competition involving 29 teams and 80 participants, enabling systematic comparison between human-AI collaborative approaches and AI-only baselines. Our results show that current AI agents struggle with domain-specific reasoning. AI-only baselines perform near or below the median of competition participants, while the strongest solutions arise from human-AI collaboration. These findings challenge the narrative of complete automation by AI and underscore the enduring importance of human expertise in data science, while illuminating directions for the next generation of AI. Visit the AgentDS website here: https://agentds.org/ and open source datasets here: https://huggingface.co/datasets/lainmn/AgentDS .</p> + https://arxiv.org/abs/2603.19005 + Thu, 19 Mar 2026 15:11:13 +0000 - LMEB: Long-horizon Memory Embedding Benchmark - https://arxiv.org/abs/2603.12572 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.12572.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xinping Zhao, Xinshuo Hu, Jiaxin Xu, Danyu Tang, Xin Zhang, Mengjia Zhou, Yan Zhong, Yao Zhou, Zifei Shan, Meishan Zhang, Baotian Hu, Min Zhang</p><p><b>Upvotes:</b> 69</p><p><b>Summary:</b> Memory embeddings are crucial for memory-augmented systems, such as OpenClaw, but their evaluation is underexplored in current text embedding benchmarks, which narrowly focus on traditional passage retrieval and fail to assess models' ability to handle long-horizon memory retrieval tasks involving fragmented, context-dependent, and temporally distant information. To address this, we introduce the Long-horizon Memory Embedding Benchmark (LMEB), a comprehensive framework that evaluates embedding models' capabilities in handling complex, long-horizon memory retrieval tasks. LMEB spans 22 datasets and 193 zero-shot retrieval tasks across 4 memory types: episodic, dialogue, semantic, and procedural, with both AI-generated and human-annotated data. These memory types differ in terms of level of abstraction and temporal dependency, capturing distinct aspects of memory retrieval that reflect the diverse challenges of the real world. We evaluate 15 widely used embedding models, ranging from hundreds of millions to ten billion parameters. The results reveal that (1) LMEB provides a reasonable level of difficulty; (2) Larger models do not always perform better; (3) LMEB and MTEB exhibit orthogonality. This suggests that the field has yet to converge on a universal model capable of excelling across all memory retrieval tasks, and that performance in traditional passage retrieval may not generalize to long-horizon memory retrieval. In summary, by providing a standardized and reproducible evaluation framework, LMEB fills a crucial gap in memory embedding evaluation, driving further advancements in text embedding for handling long-term, context-dependent memory retrieval. LMEB is available at https://github.com/KaLM-Embedding/LMEB.</p> - https://arxiv.org/abs/2603.12572 - Fri, 13 Mar 2026 02:09:57 +0000 + SEM: Sparse Embedding Modulation for Post-Hoc Debiasing of Vision-Language Models + https://arxiv.org/abs/2603.19028 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19028.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Quentin Guimard, Federico Bartsch, Simone Caldarella, Rahaf Aljundi, Elisa Ricci, Massimiliano Mancini</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Models that bridge vision and language, such as CLIP, are key components of multimodal AI, yet their large-scale, uncurated training data introduce severe social and spurious biases. Existing post-hoc debiasing methods often operate directly in the dense CLIP embedding space, where bias and task-relevant information are highly entangled. This entanglement limits their ability to remove bias without degrading semantic fidelity. In this work, we propose Sparse Embedding Modulation (SEM), a post-hoc, zero-shot debiasing framework that operates in a Sparse Autoencoder (SAE) latent space. By decomposing CLIP text embeddings into disentangled features, SEM identifies and modulates bias-relevant neurons while preserving query-relevant ones. This enables more precise, non-linear interventions. Across four benchmark datasets and two CLIP backbones, SEM achieves substantial fairness gains in retrieval and zero-shot classification. Our results demonstrate that sparse latent representations provide an effective foundation for post-hoc debiasing of vision-language models.</p> + https://arxiv.org/abs/2603.19028 + Thu, 19 Mar 2026 15:28:08 +0000 - EvoClaw: Evaluating AI Agents on Continuous Software Evolution - https://arxiv.org/abs/2603.13428 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.13428.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Gangda Deng, Zhaoling Chen, Zhongming Yu, Haoyang Fan, Yuhong Liu, Yuxin Yang, Dhruv Parikh, Rajgopal Kannan, Le Cong, Mengdi Wang, Qian Zhang, Viktor Prasanna, Xiangru Tang, Xingyao Wang</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> With AI agents increasingly deployed as long-running systems, it becomes essential to autonomously construct and continuously evolve customized software to enable interaction within dynamic environments. Yet, existing benchmarks evaluate agents on isolated, one-off coding tasks, neglecting the temporal dependencies and technical debt inherent in real-world software evolution. To bridge this gap, we introduce DeepCommit, an agentic pipeline that reconstructs verifiable Milestone DAGs from noisy commit logs, where milestones are defined as semantically cohesive development goals. These executable sequences enable EvoClaw, a novel benchmark that requires agents to sustain system integrity and limit error accumulation, dimensions of long-term software evolution largely missing from current benchmarks. Our evaluation of 12 frontier models across 4 agent frameworks reveals a critical vulnerability: overall performance scores drop significantly from >80% on isolated tasks to at most 38% in continuous settings, exposing agents' profound struggle with long-term maintenance and error propagation.</p> - https://arxiv.org/abs/2603.13428 - Fri, 13 Mar 2026 03:20:40 +0000 + TerraScope: Pixel-Grounded Visual Reasoning for Earth Observation + https://arxiv.org/abs/2603.19039 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19039.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yan Shu, Bin Ren, Zhitong Xiong, Xiao Xiang Zhu, Begüm Demir, Nicu Sebe, Paolo Rota</p><p><b>Upvotes:</b> 50</p><p><b>Summary:</b> Vision-language models (VLMs) have shown promise in earth observation (EO), yet they struggle with tasks that require grounding complex spatial reasoning in precise pixel-level visual representations. To address this problem, we introduce TerraScope, a unified VLM that delivers pixel-grounded geospatial reasoning with two key capabilities: (1) modality-flexible reasoning: it handles single-modality inputs (optical or SAR) and adaptively fuses different modalities into the reasoning process when both are available; (2) multi-temporal reasoning: it integrates temporal sequences for change analysis across multiple time points. In addition, we curate Terra-CoT, a large-scale dataset containing 1 million samples with pixel-level masks embedded in reasoning chains across multiple sources. We also propose TerraScope-Bench, the first benchmark for pixel-grounded geospatial reasoning with six sub-tasks that evaluates both answer accuracy and mask quality to ensure authentic pixel-grounded reasoning. Experiments show that TerraScope significantly outperforms existing VLMs on pixel-grounded geospatial reasoning while providing interpretable visual evidence.</p> + https://arxiv.org/abs/2603.19039 + Thu, 19 Mar 2026 15:38:02 +0000 - Spend Less, Reason Better: Budget-Aware Value Tree Search for LLM Agents - https://arxiv.org/abs/2603.12634 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.12634.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yushu Li, Wenlong Deng, Jiajin Li, Xiaoxiao Li</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Test-time scaling has become a dominant paradigm for improving LLM agent reliability, yet current approaches treat compute as an abundant resource, allowing agents to exhaust token and tool budgets on redundant steps or dead-end trajectories. Existing budget-aware methods either require expensive fine-tuning or rely on coarse, trajectory-level heuristics that cannot intervene mid-execution. We propose the Budget-Aware Value Tree (BAVT), a training-free inference-time framework that models multi-hop reasoning as a dynamic search tree guided by step-level value estimation within a single LLM backbone. Another key innovation is a budget-conditioned node selection mechanism that uses the remaining resource ratio as a natural scaling exponent over node values, providing a principled, parameter-free transition from broad exploration to greedy exploitation as the budget depletes. To combat the well-known overconfidence of LLM self-evaluation, BAVT employs a residual value predictor that scores relative progress rather than absolute state quality, enabling reliable pruning of uninformative or redundant tool calls. We further provide a theoretical convergence guarantee, proving that BAVT reaches a terminal answer with probability at least 1-ε under an explicit finite budget bound. Extensive evaluations on four multi-hop QA benchmarks across two model families demonstrate that BAVT consistently outperforms parallel sampling baselines. Most notably, BAVT under strict low-budget constraints surpasses baseline performance at 4times the resource allocation, establishing that intelligent budget management fundamentally outperforms brute-force compute scaling.</p> - https://arxiv.org/abs/2603.12634 - Fri, 13 Mar 2026 04:10:27 +0000 + BubbleRAG: Evidence-Driven Retrieval-Augmented Generation for Black-Box Knowledge Graphs + https://arxiv.org/abs/2603.20309 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.20309.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Duyi Pan, Tianao Lou, Xin Li, Haoze Song, Yiwen Wu, Mengyi Deng, Mingyu Yang, Wei Wang</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> Large Language Models (LLMs) exhibit hallucinations in knowledge-intensive tasks. Graph-based retrieval augmented generation (RAG) has emerged as a promising solution, yet existing approaches suffer from fundamental recall and precision limitations when operating over black-box knowledge graphs -- graphs whose schema and structure are unknown in advance. We identify three core challenges that cause recall loss (semantic instantiation uncertainty and structural path uncertainty) and precision loss (evidential comparison uncertainty). To address these challenges, we formalize the retrieval task as the Optimal Informative Subgraph Retrieval (OISR) problem -- a variant of Group Steiner Tree -- and prove it to be NP-hard and APX-hard. We propose BubbleRAG, a training-free pipeline that systematically optimizes for both recall and precision through semantic anchor grouping, heuristic bubble expansion to discover candidate evidence graphs (CEGs), composite ranking, and reasoning-aware expansion. Experiments on multi-hop QA benchmarks demonstrate that BubbleRAG achieves state-of-the-art results, outperforming strong baselines in both F1 and accuracy while remaining plug-and-play.</p> + https://arxiv.org/abs/2603.20309 + Thu, 19 Mar 2026 16:00:36 +0000 - From Sparse to Dense: Multi-View GRPO for Flow Models via Augmented Condition Space - https://arxiv.org/abs/2603.12648 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.12648.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiazi Bu, Pengyang Ling, Yujie Zhou, Yibin Wang, Yuhang Zang, Tianyi Wei, Xiaohang Zhan, Jiaqi Wang, Tong Wu, Xingang Pan, Dahua Lin</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Group Relative Policy Optimization (GRPO) has emerged as a powerful framework for preference alignment in text-to-image (T2I) flow models. However, we observe that the standard paradigm where evaluating a group of generated samples against a single condition suffers from insufficient exploration of inter-sample relationships, constraining both alignment efficacy and performance ceilings. To address this sparse single-view evaluation scheme, we propose Multi-View GRPO (MV-GRPO), a novel approach that enhances relationship exploration by augmenting the condition space to create a dense multi-view reward mapping. Specifically, for a group of samples generated from one prompt, MV-GRPO leverages a flexible Condition Enhancer to generate semantically adjacent yet diverse captions. These captions enable multi-view advantage re-estimation, capturing diverse semantic attributes and providing richer optimization signals. By deriving the probability distribution of the original samples conditioned on these new captions, we can incorporate them into the training process without costly sample regeneration. Extensive experiments demonstrate that MV-GRPO achieves superior alignment performance over state-of-the-art methods.</p> - https://arxiv.org/abs/2603.12648 - Fri, 13 Mar 2026 04:35:13 +0000 + Do VLMs Need Vision Transformers? Evaluating State Space Models as Vision Encoders + https://arxiv.org/abs/2603.19209 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19209.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shang-Jui Ray Kuo, Paola Cascante-Bonilla</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Large vision--language models (VLMs) often use a frozen vision backbone, whose image features are mapped into a large language model through a lightweight connector. While transformer-based encoders are the standard visual backbone, we ask whether state space model (SSM) vision backbones can be a strong alternative. We systematically evaluate SSM vision backbones for VLMs in a controlled setting. Under matched ImageNet-1K initialization, the SSM backbone achieves the strongest overall performance across both VQA and grounding/localization. We further adapt both SSM and ViT-family backbones with detection or segmentation training and find that dense-task tuning generally improves performance across families; after this adaptation, the SSM backbone remains competitive while operating at a substantially smaller model scale. We further observe that (i) higher ImageNet accuracy or larger backbones do not reliably translate into better VLM performance, and (ii) some visual backbones are unstable in localization. Based on these findings, we propose stabilization strategies that improve robustness for both backbone families and highlight SSM backbones as a strong alternative to transformer-based vision encoders in VLMs.</p> + https://arxiv.org/abs/2603.19209 + Thu, 19 Mar 2026 17:56:32 +0000 - Cheers: Decoupling Patch Details from Semantic Representations Enables Unified Multimodal Comprehension and Generation - https://arxiv.org/abs/2603.12793 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.12793.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yichen Zhang, Da Peng, Zonghao Guo, Zijian Zhang, Xuesong Yang, Tong Sun, Shichu Sun, Yidan Zhang, Yanghao Li, Haiyan Zhao, Wang Xu, Qi Shi, Yangang Sun, Chi Chen, Shuo Wang, Yukun Yan, Xu Han, Qiang Ma, Wei Ke, Liang Wang, Zhiyuan Liu, Maosong Sun</p><p><b>Upvotes:</b> 37</p><p><b>Summary:</b> A recent cutting-edge topic in multimodal modeling is to unify visual comprehension and generation within a single model. However, the two tasks demand mismatched decoding regimes and visual representations, making it non-trivial to jointly optimize within a shared feature space. In this work, we present Cheers, a unified multimodal model that decouples patch-level details from semantic representations, thereby stabilizing semantics for multimodal understanding and improving fidelity for image generation via gated detail residuals. Cheers includes three key components: (i) a unified vision tokenizer that encodes and compresses image latent states into semantic tokens for efficient LLM conditioning, (ii) an LLM-based Transformer that unifies autoregressive decoding for text generation and diffusion decoding for image generation, and (iii) a cascaded flow matching head that decodes visual semantics first and then injects semantically gated detail residuals from the vision tokenizer to refine high-frequency content. Experiments on popular benchmarks demonstrate that Cheers matches or surpasses advanced UMMs in both visual understanding and generation. Cheers also achieves 4x token compression, enabling more efficient high-resolution image encoding and generation. Notably, Cheers outperforms the Tar-1.5B on the popular benchmarks GenEval and MMBench, while requiring only 20% of the training cost, indicating effective and efficient (i.e., 4x token compression) unified multimodal modeling. We will release all code and data for future research.</p> - https://arxiv.org/abs/2603.12793 - Fri, 13 Mar 2026 08:55:27 +0000 + Scalable Prompt Routing via Fine-Grained Latent Task Discovery + https://arxiv.org/abs/2603.19415 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19415.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yunyi Zhang, Soji Adeshina, Patrick Guan, Ashwin Ganesh, Zhen Han, Vassilis N. Ioannidis, Huzefa Rangwala, George Karypis</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Prompt routing dynamically selects the most appropriate large language model from a pool of candidates for each query, optimizing performance while managing costs. As model pools scale to include dozens of frontier models with narrow performance gaps, existing approaches face significant challenges: manually defined task taxonomies cannot capture fine-grained capability distinctions, while monolithic routers struggle to differentiate subtle differences across diverse tasks. We propose a two-stage routing architecture that addresses these limitations through automated fine-grained task discovery and task-aware quality estimation. Our first stage employs graph-based clustering to discover latent task types and trains a classifier to assign prompts to discovered tasks. The second stage uses a mixture-of-experts architecture with task-specific prediction heads for specialized quality estimates. At inference, we aggregate predictions from both stages to balance task-level stability with prompt-specific adaptability. Evaluated on 10 benchmarks with 11 frontier models, our method consistently outperforms existing baselines and surpasses the strongest individual model while incurring less than half its cost.</p> + https://arxiv.org/abs/2603.19415 + Thu, 19 Mar 2026 19:15:51 +0000 - daVinci-Env: Open SWE Environment Synthesis at Scale - https://arxiv.org/abs/2603.13023 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.13023.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dayuan Fu, Shenyu Wu, Yunze Wu, Zerui Peng, Yaxing Huang, Jie Sun, Ji Zeng, Mohan Jiang, Lin Zhang, Yukun Li, Jiarui Hu, Liming Liu, Jinlong Hou, Pengfei Liu</p><p><b>Upvotes:</b> 29</p><p><b>Summary:</b> Training capable software engineering (SWE) agents demands large-scale, executable, and verifiable environments that provide dynamic feedback loops for iterative code editing, test execution, and solution refinement. However, existing open-source datasets remain limited in scale and repository diversity, while industrial solutions are opaque with unreleased infrastructure, creating a prohibitive barrier for most academic research groups. We present OpenSWE, the largest fully transparent framework for SWE agent training in Python, comprising 45,320 executable Docker environments spanning over 12.8k repositories, with all Dockerfiles, evaluation scripts, and infrastructure fully open-sourced for reproducibility. OpenSWE is built through a multi-agent synthesis pipeline deployed across a 64-node distributed cluster, automating repository exploration, Dockerfile construction, evaluation script generation, and iterative test analysis. Beyond scale, we propose a quality-centric filtering pipeline that characterizes the inherent difficulty of each environment, filtering out instances that are either unsolvable or insufficiently challenging and retaining only those that maximize learning efficiency. With 891K spent on environment construction and an additional 576K on trajectory sampling and difficulty-aware curation, the entire project represents a total investment of approximately $1.47 million, yielding about 13,000 curated trajectories from roughly 9,000 quality guaranteed environments. Extensive experiments validate OpenSWE's effectiveness: OpenSWE-32B and OpenSWE-72B achieve 62.4% and 66.0% on SWE-bench Verified, establishing SOTA among Qwen2.5 series. Moreover, SWE-focused training yields substantial out-of-domain improvements, including up to 12 points on mathematical reasoning and 5 points on science benchmarks, without degrading factual recall.</p> - https://arxiv.org/abs/2603.13023 - Fri, 13 Mar 2026 14:32:40 +0000 + Hyperagents + https://arxiv.org/abs/2603.19461 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19461.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jenny Zhang, Bingchen Zhao, Wannan Yang, Jakob Foerster, Jeff Clune, Minqi Jiang, Sam Devlin, Tatiana Shavrina</p><p><b>Upvotes:</b> 36</p><p><b>Summary:</b> Self-improving AI systems aim to reduce reliance on human engineering by learning to improve their own learning and problem-solving processes. Existing approaches to self-improvement rely on fixed, handcrafted meta-level mechanisms, fundamentally limiting how fast such systems can improve. The Darwin Gödel Machine (DGM) demonstrates open-ended self-improvement in coding by repeatedly generating and evaluating self-modified variants. Because both evaluation and self-modification are coding tasks, gains in coding ability can translate into gains in self-improvement ability. However, this alignment does not generally hold beyond coding domains. We introduce hyperagents, self-referential agents that integrate a task agent (which solves the target task) and a meta agent (which modifies itself and the task agent) into a single editable program. Crucially, the meta-level modification procedure is itself editable, enabling metacognitive self-modification, improving not only the task-solving behavior, but also the mechanism that generates future improvements. We instantiate this framework by extending DGM to create DGM-Hyperagents (DGM-H), eliminating the assumption of domain-specific alignment between task performance and self-modification skill to potentially support self-accelerating progress on any computable task. Across diverse domains, the DGM-H improves performance over time and outperforms baselines without self-improvement or open-ended exploration, as well as prior self-improving systems. Furthermore, the DGM-H improves the process by which it generates new agents (e.g., persistent memory, performance tracking), and these meta-level improvements transfer across domains and accumulate across runs. DGM-Hyperagents offer a glimpse of open-ended AI systems that do not merely search for better solutions, but continually improve their search for how to improve.</p> + https://arxiv.org/abs/2603.19461 + Thu, 19 Mar 2026 20:50:08 +0000 - Multimodal OCR: Parse Anything from Documents - https://arxiv.org/abs/2603.13032 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.13032.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Handong Zheng, Yumeng Li, Kaile Zhang, Liang Xin, Guangwei Zhao, Hao Liu, Jiayu Chen, Jie Lou, Jiyu Qiu, Qi Fu, Rui Yang, Shuo Jiang, Weijian Luo, Weijie Su, Weijun Zhang, Xingyu Zhu, Yabin Li, Yiwei ma, Yu Chen, Zhaohui Yu, Guang Yang, Colin Zhang, Lei Zhang, Yuliang Liu, Xiang Bai</p><p><b>Upvotes:</b> 31</p><p><b>Summary:</b> We present Multimodal OCR (MOCR), a document parsing paradigm that jointly parses text and graphics into unified textual representations. Unlike conventional OCR systems that focus on text recognition and leave graphical regions as cropped pixels, our method, termed dots.mocr, treats visual elements such as charts, diagrams, tables, and icons as first-class parsing targets, enabling systems to parse documents while preserving semantic relationships across elements. It offers several advantages: (1) it reconstructs both text and graphics as structured outputs, enabling more faithful document reconstruction; (2) it supports end-to-end training over heterogeneous document elements, allowing models to exploit semantic relations between textual and visual components; and (3) it converts previously discarded graphics into reusable code-level supervision, unlocking multimodal supervision embedded in existing documents. To make this paradigm practical at scale, we build a comprehensive data engine from PDFs, rendered webpages, and native SVG assets, and train a compact 3B-parameter model through staged pretraining and supervised fine-tuning. We evaluate dots.mocr from two perspectives: document parsing and structured graphics parsing. On document parsing benchmarks, it ranks second only to Gemini 3 Pro on our OCR Arena Elo leaderboard, surpasses existing open-source document parsing systems, and sets a new state of the art of 83.9 on olmOCR Bench. On structured graphics parsing, dots.mocr achieves higher reconstruction quality than Gemini 3 Pro across image-to-SVG benchmarks, demonstrating strong performance on charts, UI layouts, scientific figures, and chemical diagrams. These results show a scalable path toward building large-scale image-to-code corpora for multimodal pretraining. Code and models are publicly available at https://github.com/rednote-hilab/dots.mocr.</p> - https://arxiv.org/abs/2603.13032 - Fri, 13 Mar 2026 14:42:21 +0000 + ProactiveBench: Benchmarking Proactiveness in Multimodal Large Language Models + https://arxiv.org/abs/2603.19466 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19466.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Thomas De Min, Subhankar Roy, Stéphane Lathuilière, Elisa Ricci, Massimiliano Mancini</p><p><b>Upvotes:</b> 41</p><p><b>Summary:</b> Effective collaboration begins with knowing when to ask for help. For example, when trying to identify an occluded object, a human would ask someone to remove the obstruction. Can MLLMs exhibit a similar "proactive" behavior by requesting simple user interventions? To investigate this, we introduce ProactiveBench, a benchmark built from seven repurposed datasets that tests proactiveness across different tasks such as recognizing occluded objects, enhancing image quality, and interpreting coarse sketches. We evaluate 22 MLLMs on ProactiveBench, showing that (i) they generally lack proactiveness; (ii) proactiveness does not correlate with model capacity; (iii) "hinting" at proactiveness yields only marginal gains. Surprisingly, we found that conversation histories and in-context learning introduce negative biases, hindering performance. Finally, we explore a simple fine-tuning strategy based on reinforcement learning: its results suggest that proactiveness can be learned, even generalizing to unseen scenarios. We publicly release ProactiveBench as a first step toward building proactive multimodal models.</p> + https://arxiv.org/abs/2603.19466 + Thu, 19 Mar 2026 20:58:03 +0000 - V-Bridge: Bridging Video Generative Priors to Versatile Few-shot Image Restoration - https://arxiv.org/abs/2603.13089 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.13089.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shenghe Zheng, Junpeng Jiang, Wenbo Li</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Large-scale video generative models are trained on vast and diverse visual data, enabling them to internalize rich structural, semantic, and dynamic priors of the visual world. While these models have demonstrated impressive generative capability, their potential as general-purpose visual learners remains largely untapped. In this work, we introduce V-Bridge, a framework that bridges this latent capacity to versatile few-shot image restoration tasks. We reinterpret image restoration not as a static regression problem, but as a progressive generative process, and leverage video models to simulate the gradual refinement from degraded inputs to high-fidelity outputs. Surprisingly, with only 1,000 multi-task training samples (less than 2% of existing restoration methods), pretrained video models can be induced to perform competitive image restoration, achieving multiple tasks with a single model, rivaling specialized architectures designed explicitly for this purpose. Our findings reveal that video generative models implicitly learn powerful and transferable restoration priors that can be activated with only extremely limited data, challenging the traditional boundary between generative modeling and low-level vision, and opening a new design paradigm for foundation models in visual tasks.</p> - https://arxiv.org/abs/2603.13089 - Fri, 13 Mar 2026 15:39:44 +0000 + Teaching an Agent to Sketch One Part at a Time + https://arxiv.org/abs/2603.19500 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19500.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiaodan Du, Ruize Xu, David Yunis, Yael Vinker, Greg Shakhnarovich</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> We develop a method for producing vector sketches one part at a time. To do this, we train a multi-modal language model-based agent using a novel multi-turn process-reward reinforcement learning following supervised fine-tuning. Our approach is enabled by a new dataset we call ControlSketch-Part, containing rich part-level annotations for sketches, obtained using a novel, generic automatic annotation pipeline that segments vector sketches into semantic parts and assigns paths to parts with a structured multi-stage labeling process. Our results indicate that incorporating structured part-level data and providing agent with the visual feedback through the process enables interpretable, controllable, and locally editable text-to-vector sketch generation.</p> + https://arxiv.org/abs/2603.19500 + Thu, 19 Mar 2026 22:08:53 +0000 - Visual-ERM: Reward Modeling for Visual Equivalence - https://arxiv.org/abs/2603.13224 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.13224.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ziyu Liu, Shengyuan Ding, Xinyu Fang, Xuanlang Dai, Penghui Yang, Jianze Liang, Jiaqi Wang, Kai Chen, Dahua Lin, Yuhang Zang</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> Vision-to-code tasks require models to reconstruct structured visual inputs, such as charts, tables, and SVGs, into executable or structured representations with high visual fidelity. While recent Large Vision Language Models (LVLMs) achieve strong results via supervised fine-tuning, reinforcement learning remains challenging due to misaligned reward signals. Existing rewards either rely on textual rules or coarse visual embedding similarity, both of which fail to capture fine-grained visual discrepancies and are vulnerable to reward hacking. We propose Visual Equivalence Reward Model (Visual-ERM), a multimodal generative reward model that provides fine-grained, interpretable, and task-agnostic feedback to evaluate vision-to-code quality directly in the rendered visual space. Integrated into RL, Visual-ERM improves Qwen3-VL-8B-Instruct by +8.4 on chart-to-code and yields consistent gains on table and SVG parsing (+2.7, +4.1 on average), and further strengthens test-time scaling via reflection and revision. We also introduce VisualCritic-RewardBench (VC-RewardBench), a benchmark for judging fine-grained image-to-image discrepancies on structured visual data, where Visual-ERM at 8B decisively outperforms Qwen3-VL-235B-Instruct and approaches leading closed-source models. Our results suggest that fine-grained visual reward supervision is both necessary and sufficient for vision-to-code RL, regardless of task specificity.</p> - https://arxiv.org/abs/2603.13224 - Fri, 13 Mar 2026 17:58:14 +0000 + FlowScene: Style-Consistent Indoor Scene Generation with Multimodal Graph Rectified Flow + https://arxiv.org/abs/2603.19598 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19598.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhifei Yang, Guangyao Zhai, Keyang Lu, YuYang Yin, Chao Zhang, Zhen Xiao, Jieyi Long, Nassir Navab, Yikai Wang</p><p><b>Upvotes:</b> 32</p><p><b>Summary:</b> Scene generation has extensive industrial applications, demanding both high realism and precise control over geometry and appearance. Language-driven retrieval methods compose plausible scenes from a large object database, but overlook object-level control and often fail to enforce scene-level style coherence. Graph-based formulations offer higher controllability over objects and inform holistic consistency by explicitly modeling relations, yet existing methods struggle to produce high-fidelity textured results, thereby limiting their practical utility. We present FlowScene, a tri-branch scene generative model conditioned on multimodal graphs that collaboratively generates scene layouts, object shapes, and object textures. At its core lies a tight-coupled rectified flow model that exchanges object information during generation, enabling collaborative reasoning across the graph. This enables fine-grained control of objects' shapes, textures, and relations while enforcing scene-level style coherence across structure and appearance. Extensive experiments show that FlowScene outperforms both language-conditioned and graph-conditioned baselines in terms of generation realism, style consistency, and alignment with human preferences.</p> + https://arxiv.org/abs/2603.19598 + Fri, 20 Mar 2026 03:15:42 +0000 - EnterpriseOps-Gym: Environments and Evaluations for Stateful Agentic Planning and Tool Use in Enterprise Settings - https://arxiv.org/abs/2603.13594 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.13594.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shiva Krishna Reddy Malay, Shravan Nayak, Jishnu Sethumadhavan Nair, Sagar Davasam, Aman Tiwari, Sathwik Tejaswi Madhusudhan, Sridhar Krishna Nemala, Srinivas Sunkara, Sai Rajeswar</p><p><b>Upvotes:</b> 141</p><p><b>Summary:</b> Large language models are shifting from passive information providers to active agents intended for complex workflows. However, their deployment as reliable AI workers in enterprise is stalled by benchmarks that fail to capture the intricacies of professional environments, specifically, the need for long-horizon planning amidst persistent state changes and strict access protocols. In this work, we introduce EnterpriseOps-Gym, a benchmark designed to evaluate agentic planning in realistic enterprise settings. Specifically, EnterpriseOps-Gym features a containerized sandbox with 164 database tables and 512 functional tools to mimic real-world search friction. Within this environment, agents are evaluated on 1,150 expert-curated tasks across eight mission-critical verticals (including Customer Service, HR, and IT). Our evaluation of 14 frontier models reveals critical limitations in state-of-the-art models: the top-performing Claude Opus 4.5 achieves only 37.4% success. Further analysis shows that providing oracle human plans improves performance by 14-35 percentage points, pinpointing strategic reasoning as the primary bottleneck. Additionally, agents frequently fail to refuse infeasible tasks (best model achieves 53.9%), leading to unintended and potentially harmful side effects. Our findings underscore that current agents are not yet ready for autonomous enterprise deployment. More broadly, EnterpriseOps-Gym provides a concrete testbed to advance the robustness of agentic planning in professional workflows.</p> - https://arxiv.org/abs/2603.13594 - Fri, 13 Mar 2026 21:09:39 +0000 + BEAVER: A Training-Free Hierarchical Prompt Compression Method via Structure-Aware Page Selection + https://arxiv.org/abs/2603.19635 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19635.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhengpei Hu, Kai Li, Dapeng Fu, Chang Zeng, Yue Li, Yuanhao Tang, Jianqiang Huang</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> The exponential expansion of context windows in LLMs has unlocked capabilities for long-document understanding but introduced severe bottlenecks in inference latency and information utilization. Existing compression methods often suffer from high training costs or semantic fragmentation due to aggressive token pruning. In this paper, we propose BEAVER, a novel training-free framework that shifts compression from linear token removal to structure-aware hierarchical selection. BEAVER maximizes hardware parallelism by mapping variable-length contexts into dense page-level tensors via dual-path pooling, and preserves discourse integrity through a hybrid planner combining semantic and lexical dual-branch selection with sentence smoothing. Extensive evaluations on four long-context benchmarks demonstrate that BEAVER achieves comparable performance to state-of-the-art (SOTA) methods like LongLLMLingua. Notably, on the RULER benchmark, BEAVER maintains high fidelity in multi-needle retrieval where baselines deteriorate. Regarding efficiency, BEAVER reduces latency by 26.4x on 128k contexts, offering a scalable solution for high-throughput applications. Our code is available at https://cslikai.cn/BEAVER/.</p> + https://arxiv.org/abs/2603.19635 + Fri, 20 Mar 2026 04:35:04 +0000 - GradMem: Learning to Write Context into Memory with Test-Time Gradient Descent - https://arxiv.org/abs/2603.13875 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.13875.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuri Kuratov, Matvey Kairov, Aydar Bulatov, Ivan Rodkin, Mikhail Burtsev</p><p><b>Upvotes:</b> 31</p><p><b>Summary:</b> Many large language model applications require conditioning on long contexts. Transformers typically support this by storing a large per-layer KV-cache of past activations, which incurs substantial memory overhead. A desirable alternative is ompressive memory: read a context once, store it in a compact state, and answer many queries from that state. We study this in a context removal setting, where the model must generate an answer without access to the original context at inference time. We introduce GradMem, which writes context into memory via per-sample test-time optimization. Given a context, GradMem performs a few steps of gradient descent on a small set of prefix memory tokens while keeping model weights frozen. GradMem explicitly optimizes a model-level self-supervised context reconstruction loss, resulting in a loss-driven write operation with iterative error correction, unlike forward-only methods. On associative key--value retrieval, GradMem outperforms forward-only memory writers with the same memory size, and additional gradient steps scale capacity much more effectively than repeated forward writes. We further show that GradMem transfers beyond synthetic benchmarks: with pretrained language models, it attains competitive results on natural language tasks including bAbI and SQuAD variants, relying only on information encoded in memory.</p> - https://arxiv.org/abs/2603.13875 - Sat, 14 Mar 2026 10:17:33 +0000 + A Subgoal-driven Framework for Improving Long-Horizon LLM Agents + https://arxiv.org/abs/2603.19685 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19685.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Taiyi Wang, Sian Gooding, Florian Hartmann, Oriana Riva, Edward Grefenstette</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> Large language model (LLM)-based agents have emerged as powerful autonomous controllers for digital environments, including mobile interfaces, operating systems, and web browsers. Web navigation, for example, requires handling dynamic content and long sequences of actions, making it particularly challenging. Existing LLM-based agents struggle with long-horizon planning in two main ways. During online execution, they often lose track as new information arrives, lacking a clear and adaptive path toward the final goal. This issue is further exacerbated during reinforcement learning (RL) fine-tuning, where sparse and delayed rewards make it difficult for agents to identify which actions lead to success, preventing them from maintaining coherent reasoning over extended tasks. To address these challenges, we propose two contributions. First, we introduce an agent framework that leverages proprietary models for online planning through subgoal decomposition. Second, we present MiRA (Milestoning your Reinforcement Learning Enhanced Agent), an RL training framework that uses dense, milestone-based reward signals. The real-time planning mechanism improves proprietary models such as Gemini by approximately a 10% absolute increase in success rate (SR) on the WebArena-Lite benchmark. Meanwhile, applying MiRA to the open Gemma3-12B model increases its success rate from 6.4% to 43.0%. This performance surpasses proprietary systems such as GPT-4-Turbo (17.6%) and GPT-4o (13.9%), as well as the previous open-model state of the art, WebRL (38.4%). Overall, our findings demonstrate that combining explicit inference-time planning with milestone-based rewards significantly improves an agent's long-horizon capabilities, paving the way for more robust and general-purpose autonomous systems.</p> + https://arxiv.org/abs/2603.19685 + Fri, 20 Mar 2026 06:32:16 +0000 - Supervised Fine-Tuning versus Reinforcement Learning: A Study of Post-Training Methods for Large Language Models - https://arxiv.org/abs/2603.13985 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.13985.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haitao Jiang, Wenbo Zhang, Jiarui Yao, Hengrui Cai, Sheng Wang, Rui Song</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Pre-trained Large Language Model (LLM) exhibits broad capabilities, yet, for specific tasks or domains their attainment of higher accuracy and more reliable reasoning generally depends on post-training through Supervised Fine-Tuning (SFT) or Reinforcement Learning (RL). Although often treated as distinct methodologies, recent theoretical and empirical developments demonstrate that SFT and RL are closely connected. This study presents a comprehensive and unified perspective on LLM post-training with SFT and RL. We first provide an in-depth overview of both techniques, examining their objectives, algorithmic structures, and data requirements. We then systematically analyze their interplay, highlighting frameworks that integrate SFT and RL, hybrid training pipelines, and methods that leverage their complementary strengths. Drawing on a representative set of recent application studies from 2023 to 2025, we identify emerging trends, characterize the rapid shift toward hybrid post-training paradigms, and distill key takeaways that clarify when and why each method is most effective. By synthesizing theoretical insights, practical methodologies, and empirical evidence, this study establishes a coherent understanding of SFT and RL within a unified framework and outlines promising directions for future research in scalable, efficient, and generalizable LLM post-training.</p> - https://arxiv.org/abs/2603.13985 - Sat, 14 Mar 2026 15:24:38 +0000 + WorldAgents: Can Foundation Image Models be Agents for 3D World Models? + https://arxiv.org/abs/2603.19708 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19708.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ziya Erkoç, Angela Dai, Matthias Nießner</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Given the remarkable ability of 2D foundation image models to generate high-fidelity outputs, we investigate a fundamental question: do 2D foundation image models inherently possess 3D world model capabilities? To answer this, we systematically evaluate multiple state-of-the-art image generation models and Vision-Language Models (VLMs) on the task of 3D world synthesis. To harness and benchmark their potential implicit 3D capability, we propose an agentic framing to facilitate 3D world generation. Our approach employs a multi-agent architecture: a VLM-based director that formulates prompts to guide image synthesis, a generator that synthesizes new image views, and a VLM-backed two-step verifier that evaluates and selectively curates generated frames from both 2D image and 3D reconstruction space. Crucially, we demonstrate that our agentic approach provides coherent and robust 3D reconstruction, producing output scenes that can be explored by rendering novel views. Through extensive experiments across various foundation models, we demonstrate that 2D models do indeed encapsulate a grasp of 3D worlds. By exploiting this understanding, our method successfully synthesizes expansive, realistic, and 3D-consistent worlds.</p> + https://arxiv.org/abs/2603.19708 + Fri, 20 Mar 2026 07:22:41 +0000 - MMOU: A Massive Multi-Task Omni Understanding and Reasoning Benchmark for Long and Complex Real-World Videos - https://arxiv.org/abs/2603.14145 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.14145.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Arushi Goel, Sreyan Ghosh, Vatsal Agarwal, Nishit Anand, Kaousheik Jayakumar, Lasha Koroshinadze, Yao Xu, Katie Lyons, James Case, Karan Sapra, Kevin J. Shih, Siddharth Gururani, Abhinav Shrivastava, Ramani Duraiswami, Dinesh Manocha, Andrew Tao, Bryan Catanzaro, Mohammad Shoeybi, Wei Ping</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Multimodal Large Language Models (MLLMs) have shown strong performance in visual and audio understanding when evaluated in isolation. However, their ability to jointly reason over omni-modal (visual, audio, and textual) signals in long and complex videos remains largely unexplored. We introduce MMOU, a new benchmark designed to systematically evaluate multimodal understanding and reasoning under these challenging, real-world conditions. MMOU consists of 15,000 carefully curated questions paired with 9038 web-collected videos of varying length, spanning diverse domains and exhibiting rich, tightly coupled audio-visual content. The benchmark covers 13 fundamental skill categories, all of which require integrating evidence across modalities and time. All questions are manually annotated across multiple turns by professional annotators, ensuring high quality and reasoning fidelity. We evaluate 20+ state-of-the-art open-source and proprietary multimodal models on MMOU. The results expose substantial performance gaps: the best closed-source model achieves only 64.2% accuracy, while the strongest open-source model reaches just 46.8%. Our results highlight the challenges of long-form omni-modal understanding, revealing that current models frequently fail to apply even fundamental skills in long videos. Through detailed analysis, we further identify systematic failure modes and provide insights into where and why current models break.</p> - https://arxiv.org/abs/2603.14145 - Sat, 14 Mar 2026 22:28:38 +0000 + LoopRPT: Reinforcement Pre-Training for Looped Language Models + https://arxiv.org/abs/2603.19714 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19714.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Guo Tang, Shixin Jiang, Heng Chang, Nuo Chen, Yuhan Li, Huiming Fan, Jia Li, Ming Liu, Bing Qin</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Looped language models (LoopLMs) perform iterative latent computation to refine internal representations, offering a promising alternative to explicit chain-of-thought (CoT) reasoning. However, existing reinforcement learning (RL) paradigms primarily target output tokens, creating a structural mismatch with looped architectures whose reasoning unfolds implicitly. In this work, we propose LoopRPT, a reinforcement pre-training framework tailored for LoopLMs. By reframing next-token prediction as a next-token reasoning task, LoopRPT assigns reinforcement signals directly to latent steps using an EMA teacher reference and noisy latent rollouts. This formulation enables RL to directly shape intermediate representations, compressing effective reasoning into fewer iterations. We instantiate LoopRPT on the Ouro architecture across multiple model scales. Results demonstrate that LoopRPT consistently improves per-step representation quality, achieving Pareto dominance in accuracy-computation trade-offs. Notably, significant gains on hard tokens indicate that LoopRPT enhances early-stage reasoning rather than merely encouraging premature exits. Our findings highlight reinforcement pre-training as a principled paradigm for learning efficient latent reasoning in LoopLMs.</p> + https://arxiv.org/abs/2603.19714 + Fri, 20 Mar 2026 07:35:38 +0000 - Motivation in Large Language Models - https://arxiv.org/abs/2603.14347 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.14347.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Omer Nahum, Asael Sklar, Ariel Goldstein, Roi Reichart</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Motivation is a central driver of human behavior, shaping decisions, goals, and task performance. As large language models (LLMs) become increasingly aligned with human preferences, we ask whether they exhibit something akin to motivation. We examine whether LLMs "report" varying levels of motivation, how these reports relate to their behavior, and whether external factors can influence them. Our experiments reveal consistent and structured patterns that echo human psychology: self-reported motivation aligns with different behavioral signatures, varies across task types, and can be modulated by external manipulations. These findings demonstrate that motivation is a coherent organizing construct for LLM behavior, systematically linking reports, choices, effort, and performance, and revealing motivational dynamics that resemble those documented in human psychology. This perspective deepens our understanding of model behavior and its connection to human-inspired concepts.</p> - https://arxiv.org/abs/2603.14347 - Sun, 15 Mar 2026 12:30:36 +0000 + How Well Does Generative Recommendation Generalize? + https://arxiv.org/abs/2603.19809 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19809.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yijie Ding, Zitian Guo, Jiacheng Li, Letian Peng, Shuai Shao, Wei Shao, Xiaoqiang Luo, Luke Simon, Jingbo Shang, Julian McAuley, Yupeng Hou</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> A widely held hypothesis for why generative recommendation (GR) models outperform conventional item ID-based models is that they generalize better. However, there is few systematic way to verify this hypothesis beyond a superficial comparison of overall performance. To address this gap, we categorize each data instance based on the specific capability required for a correct prediction: either memorization (reusing item transition patterns observed during training) or generalization (composing known patterns to predict unseen item transitions). Extensive experiments show that GR models perform better on instances that require generalization, whereas item ID-based models perform better when memorization is more important. To explain this divergence, we shift the analysis from the item level to the token level and show that what appears to be item-level generalization often reduces to token-level memorization for GR models. Finally, we show that the two paradigms are complementary. We propose a simple memorization-aware indicator that adaptively combines them on a per-instance basis, leading to improved overall recommendation performance.</p> + https://arxiv.org/abs/2603.19809 + Fri, 20 Mar 2026 09:48:57 +0000 - AgentProcessBench: Diagnosing Step-Level Process Quality in Tool-Using Agents - https://arxiv.org/abs/2603.14465 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.14465.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shengda Fan, Xuyan Ye, Yupeng Huo, Zhi-Yuan Chen, Yiju Guo, Shenzhi Yang, Wenkai Yang, Shuqi Ye, Jingwen Chen, Haotian Chen, Xin Cong, Yankai Lin</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> While Large Language Models (LLMs) have evolved into tool-using agents, they remain brittle in long-horizon interactions. Unlike mathematical reasoning where errors are often rectifiable via backtracking, tool-use failures frequently induce irreversible side effects, making accurate step-level verification critical. However, existing process-level benchmarks are predominantly confined to closed-world mathematical domains, failing to capture the dynamic and open-ended nature of tool execution. To bridge this gap, we introduce AgentProcessBench, the first benchmark dedicated to evaluating step-level effectiveness in realistic, tool-augmented trajectories. The benchmark comprises 1,000 diverse trajectories and 8,509 human-labeled step annotations with 89.1% inter-annotator agreement. It features a ternary labeling scheme to capture exploration and an error propagation rule to reduce labeling ambiguity. Extensive experiments reveal key insights: (1) weaker policy models exhibit inflated ratios of correct steps due to early termination; (2) distinguishing neutral and erroneous actions remains a significant challenge for current models; and (3) process-derived signals provide complementary value to outcome supervision, significantly enhancing test-time scaling. We hope AgentProcessBench can foster future research in reward models and pave the way toward general agents. The code and data are available at https://github.com/RUCBM/AgentProcessBench.</p> - https://arxiv.org/abs/2603.14465 - Sun, 15 Mar 2026 16:13:58 +0000 + Breaking the Capability Ceiling of LLM Post-Training by Reintroducing Markov States + https://arxiv.org/abs/2603.19987 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19987.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yurun Yuan, Tengyang Xie</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Reinforcement learning (RL) has become a standard paradigm for post-training and aligning Large Language Models (LLMs), yet recent evidence suggests it faces a persistent "capability ceiling": unlike classical RL systems that discover novel strategies, RL for LLMs often acts as a mere refiner of patterns already latent in pre-trained weights. In this work, we identify a fundamental structural bottleneck: while classical RL relies on compact, informative Markov states, current LLM post-training formulations are tethered to an ever-expanding history of actions. We revisit a classical principle long central to RL yet absent from LLM post-training: explicit Markov states. Theoretically, we provide rigorous guarantees demonstrating that leveraging estimated Markov states can significantly reduce sample complexity. Empirically, we show that introducing Markov states consistently breaks the performance boundaries of standard RL post-training across a suite of complex logic puzzles. Our findings suggest that moving beyond "history-as-state" modeling in favor of structured Markovian representations is essential for unlocking open-ended discovery and genuinely new reasoning capabilities in Generative AI.</p> + https://arxiv.org/abs/2603.19987 + Fri, 20 Mar 2026 14:35:49 +0000 - AI Can Learn Scientific Taste - https://arxiv.org/abs/2603.14473 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.14473.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jingqi Tong, Mingzhe Li, Hangcheng Li, Yongzhuo Yang, Yurong Mou, Weijie Ma, Zhiheng Xi, Hongji Chen, Xiaoran Liu, Qinyuan Cheng, Ming Zhang, Qiguang Chen, Weifeng Ge, Qipeng Guo, Tianlei Ying, Tianxiang Sun, Yining Zheng, Xinchi Chen, Jun Zhao, Ning Ding, Xuanjing Huang, Yugang Jiang, Xipeng Qiu</p><p><b>Upvotes:</b> 316</p><p><b>Summary:</b> Great scientists have strong judgement and foresight, closely tied to what we call scientific taste. Here, we use the term to refer to the capacity to judge and propose research ideas with high potential impact. However, most relative research focuses on improving an AI scientist's executive capability, while enhancing an AI's scientific taste remains underexplored. In this work, we propose Reinforcement Learning from Community Feedback (RLCF), a training paradigm that uses large-scale community signals as supervision, and formulate scientific taste learning as a preference modeling and alignment problem. For preference modeling, we train Scientific Judge on 700K field- and time-matched pairs of high- vs. low-citation papers to judge ideas. For preference alignment, using Scientific Judge as a reward model, we train a policy model, Scientific Thinker, to propose research ideas with high potential impact. Experiments show Scientific Judge outperforms SOTA LLMs (e.g., GPT-5.2, Gemini 3 Pro) and generalizes to future-year test, unseen fields, and peer-review preference. Furthermore, Scientific Thinker proposes research ideas with higher potential impact than baselines. Our findings show that AI can learn scientific taste, marking a key step toward reaching human-level AI scientists.</p> - https://arxiv.org/abs/2603.14473 - Sun, 15 Mar 2026 16:31:51 +0000 + The Y-Combinator for LLMs: Solving Long-Context Rot with λ-Calculus + https://arxiv.org/abs/2603.20105 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.20105.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Amartya Roy, Rasul Tutunov, Xiaotong Ji, Matthieu Zimmer, Haitham Bou-Ammar</p><p><b>Upvotes:</b> 32</p><p><b>Summary:</b> LLMs are increasingly used as general-purpose reasoners, but long inputs remain bottlenecked by a fixed context window. Recursive Language Models (RLMs) address this by externalising the prompt and recursively solving subproblems. Yet existing RLMs depend on an open-ended read-eval-print loop (REPL) in which the model generates arbitrary control code, making execution difficult to verify, predict, and analyse. We introduce λ-RLM, a framework for long-context reasoning that replaces free-form recursive code generation with a typed functional runtime grounded in λ-calculus. It executes a compact library of pre-verified combinators and uses neural inference only on bounded leaf subproblems, turning recursive reasoning into a structured functional program with explicit control flow. We show that λ-RLM admits formal guarantees absent from standard RLMs, including termination, closed-form cost bounds, controlled accuracy scaling with recursion depth, and an optimal partition rule under a simple cost model. Empirically, across four long-context reasoning tasks and nine base models, λ-RLM outperforms standard RLM in 29 of 36 model-task comparisons, improves average accuracy by up to +21.9 points across model tiers, and reduces latency by up to 4.1x. These results show that typed symbolic control yields a more reliable and efficient foundation for long-context reasoning than open-ended recursive code generation. The complete implementation of λ-RLM, is open-sourced for the community at: https://github.com/lambda-calculus-LLM/lambda-RLM.</p> + https://arxiv.org/abs/2603.20105 + Fri, 20 Mar 2026 16:29:51 +0000 - V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning - https://arxiv.org/abs/2603.14482 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.14482.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lorenzo Mur-Labadia, Matthew Muckley, Amir Bar, Mido Assran, Koustuv Sinha, Mike Rabbat, Yann LeCun, Nicolas Ballas, Adrien Bardes</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> We present V-JEPA 2.1, a family of self-supervised models that learn dense, high-quality visual representations for both images and videos while retaining strong global scene understanding. The approach combines four key components. First, a dense predictive loss uses a masking-based objective in which both visible and masked tokens contribute to the training signal, encouraging explicit spatial and temporal grounding. Second, deep self-supervision applies the self-supervised objective hierarchically across multiple intermediate encoder layers to improve representation quality. Third, multi-modal tokenizers enable unified training across images and videos. Finally, the model benefits from effective scaling in both model capacity and training data. Together, these design choices produce representations that are spatially structured, semantically coherent, and temporally consistent. Empirically, V-JEPA 2.1 achieves state-of-the-art performance on several challenging benchmarks, including 7.71 mAP on Ego4D for short-term object-interaction anticipation and 40.8 Recall@5 on EPIC-KITCHENS for high-level action anticipation, as well as a 20-point improvement in real-robot grasping success rate over V-JEPA-2 AC. The model also demonstrates strong performance in robotic navigation (5.687 ATE on TartanDrive), depth estimation (0.307 RMSE on NYUv2 with a linear probe), and global recognition (77.7 on Something-Something-V2). These results show that V-JEPA 2.1 significantly advances the state of the art in dense visual understanding and world modeling.</p> - https://arxiv.org/abs/2603.14482 - Sun, 15 Mar 2026 17:02:40 +0000 + AgentSLR: Automating Systematic Literature Reviews in Epidemiology with Agentic AI + https://arxiv.org/abs/2603.22327 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22327.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shreyansh Padarha, Ryan Othniel Kearns, Tristan Naidoo, Lingyi Yang, Łukasz Borchmann, Piotr BŁaszczyk, Christian Morgenstern, Ruth McCabe, Sangeeta Bhatia, Philip H. Torr, Jakob Foerster, Scott A. Hale, Thomas Rawson, Anne Cori, Elizaveta Semenova, Adam Mahdi</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Systematic literature reviews are essential for synthesizing scientific evidence but are costly, difficult to scale and time-intensive, creating bottlenecks for evidence-based policy. We study whether large language models can automate the complete systematic review workflow, from article retrieval, article screening, data extraction to report synthesis. Applied to epidemiological reviews of nine WHO-designated priority pathogens and validated against expert-curated ground truth, our open-source agentic pipeline (AgentSLR) achieves performance comparable to human researchers while reducing review time from approximately 7 weeks to 20 hours (a 58x speed-up). Our comparison of five frontier models reveals that performance on SLR is driven less by model size or inference cost than by each model's distinctive capabilities. Through human-in-the-loop validation, we identify key failure modes. Our results demonstrate that agentic AI can substantially accelerate scientific evidence synthesis in specialised domains.</p> + https://arxiv.org/abs/2603.22327 + Fri, 20 Mar 2026 17:11:58 +0000 - Make it SING: Analyzing Semantic Invariants in Classifiers - https://arxiv.org/abs/2603.14610 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.14610.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Harel Yadid, Meir Yossef Levi, Roy Betser, Guy Gilboa</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> All classifiers, including state-of-the-art vision models, possess invariants, partially rooted in the geometry of their linear mappings. These invariants, which reside in the null-space of the classifier, induce equivalent sets of inputs that map to identical outputs. The semantic content of these invariants remains vague, as existing approaches struggle to provide human-interpretable information. To address this gap, we present Semantic Interpretation of the Null-space Geometry (SING), a method that constructs equivalent images, with respect to the network, and assigns semantic interpretations to the available variations. We use a mapping from network features to multi-modal vision language models. This allows us to obtain natural language descriptions and visual examples of the induced semantic shifts. SING can be applied to a single image, uncovering local invariants, or to sets of images, allowing a breadth of statistical analysis at the class and model levels. For example, our method reveals that ResNet50 leaks relevant semantic attributes to the null space, whereas DinoViT, a ViT pretrained with self-supervised DINO, is superior in maintaining class semantics across the invariant space.</p> - https://arxiv.org/abs/2603.14610 - Sun, 15 Mar 2026 21:13:14 +0000 + Beyond Single Tokens: Distilling Discrete Diffusion Models via Discrete MMD + https://arxiv.org/abs/2603.20155 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.20155.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Emiel Hoogeboom, David Ruhe, Jonathan Heek, Thomas Mensink, Tim Salimans</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> It is currently difficult to distill discrete diffusion models. In contrast, continuous diffusion literature has many distillation approaches methods that can reduce sampling steps to a handful. Our method, Discrete Moment Matching Distillation (D-MMD), leverages ideas that have been highly successful in the continuous domain. Whereas previous discrete distillation methods collapse, D-MMD maintains high quality and diversity (given sufficient sampling steps). This is demonstrated on both text and image datasets. Moreover, the newly distilled generators can outperform their teachers.</p> + https://arxiv.org/abs/2603.20155 + Fri, 20 Mar 2026 17:29:12 +0000 - POLCA: Stochastic Generative Optimization with LLM - https://arxiv.org/abs/2603.14769 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.14769.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xuanfei Ren, Allen Nie, Tengyang Xie, Ching-An Cheng</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> Optimizing complex systems, ranging from LLM prompts to multi-turn agents, traditionally requires labor-intensive manual iteration. We formalize this challenge as a stochastic generative optimization problem where a generative language model acts as the optimizer, guided by numerical rewards and text feedback to discover the best system. We introduce Prioritized Optimization with Local Contextual Aggregation (POLCA), a scalable framework designed to handle stochasticity in optimization -- such as noisy feedback, sampling minibatches, and stochastic system behaviors -- while effectively managing the unconstrained expansion of solution space. POLCA maintains a priority queue to manage the exploration-exploitation tradeoff, systematically tracking candidate solutions and their evaluation histories. To enhance efficiency, we integrate an varepsilon-Net mechanism to maintain parameter diversity and an LLM Summarizer to perform meta-learning across historical trials. We theoretically prove that POLCA converges to near-optimal candidate solutions under stochasticity. We evaluate our framework on diverse benchmarks, including τ-bench, HotpotQA (agent optimization), VeriBench (code translation) and KernelBench (CUDA kernel generation). Experimental results demonstrate that POLCA achieves robust, sample and time-efficient performance, consistently outperforming state-of-the-art algorithms in both deterministic and stochastic problems. The codebase for this work is publicly available at https://github.com/rlx-lab/POLCA.</p> - https://arxiv.org/abs/2603.14769 - Mon, 16 Mar 2026 03:07:44 +0000 + EgoForge: Goal-Directed Egocentric World Simulator + https://arxiv.org/abs/2603.20169 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.20169.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yifan Shen, Jiateng Liu, Xinzhuo Li, Yuanzhe Liu, Bingxuan Li, Houze Yang, Wenqi Jia, Yijiang Li, Tianjiao Yu, James Matthew Rehg, Xu Cao, Ismini Lourentzou</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Generative world models have shown promise for simulating dynamic environments, yet egocentric video remains challenging due to rapid viewpoint changes, frequent hand-object interactions, and goal-directed procedures whose evolution depends on latent human intent. Existing approaches either focus on hand-centric instructional synthesis with limited scene evolution, perform static view translation without modeling action dynamics, or rely on dense supervision, such as camera trajectories, long video prefixes, synchronized multicamera capture, etc. In this work, we introduce EgoForge, an egocentric goal-directed world simulator that generates coherent, first-person video rollouts from minimal static inputs: a single egocentric image, a high-level instruction, and an optional auxiliary exocentric view. To improve intent alignment and temporal consistency, we propose VideoDiffusionNFT, a trajectory-level reward-guided refinement that optimizes goal completion, temporal causality, scene consistency, and perceptual fidelity during diffusion sampling. Extensive experiments show EgoForge achieves consistent gains in semantic alignment, geometric stability, and motion fidelity over strong baselines, and robust performance in real-world smart-glasses experiments.</p> + https://arxiv.org/abs/2603.20169 + Fri, 20 Mar 2026 17:46:55 +0000 - Video-CoE: Reinforcing Video Event Prediction via Chain of Events - https://arxiv.org/abs/2603.14935 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.14935.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qile Su, Jing Tang, Rui Chen, Lei Sun, Xiangxiang Chu</p><p><b>Upvotes:</b> 90</p><p><b>Summary:</b> Despite advances in the application of MLLMs for various video tasks, video event prediction (VEP) remains relatively underexplored. VEP requires the model to perform fine-grained temporal modeling of videos and establish logical relationships between videos and future events, which current MLLMs still struggle with. In this work, we first present a comprehensive evaluation of current leading MLLMs on the VEP task, revealing the reasons behind their inaccurate predictions, including lack of logical reasoning ability for future events prediction and insufficient utilization of visual information. To address these challenges, we propose Chain of Events (CoE) paradigm, which constructs temporal event chains to implicitly enforce MLLM focusing on the visual content and the logical connections between videos and future events, incentivizing model's reasoning capability with multiple training protocols. Experimental results on public benchmarks demonstrate that our method outperforms both leading open-source and commercial MLLMs, establishing a new state-of-the-art on the VEP task. Codes and models will be released soon.</p> - https://arxiv.org/abs/2603.14935 - Mon, 16 Mar 2026 07:38:15 +0000 + LagerNVS: Latent Geometry for Fully Neural Real-time Novel View Synthesis + https://arxiv.org/abs/2603.20176 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.20176.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Stanislaw Szymanowicz, Minghao Chen, Jianyuan Wang, Christian Rupprecht, Andrea Vedaldi</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Recent work has shown that neural networks can perform 3D tasks such as Novel View Synthesis (NVS) without explicit 3D reconstruction. Even so, we argue that strong 3D inductive biases are still helpful in the design of such networks. We show this point by introducing LagerNVS, an encoder-decoder neural network for NVS that builds on `3D-aware' latent features. The encoder is initialized from a 3D reconstruction network pre-trained using explicit 3D supervision. This is paired with a lightweight decoder, and trained end-to-end with photometric losses. LagerNVS achieves state-of-the-art deterministic feed-forward Novel View Synthesis (including 31.4 PSNR on Re10k), with and without known cameras, renders in real time, generalizes to in-the-wild data, and can be paired with a diffusion decoder for generative extrapolation.</p> + https://arxiv.org/abs/2603.20176 + Fri, 20 Mar 2026 17:53:06 +0000 - Riemannian Motion Generation: A Unified Framework for Human Motion Representation and Generation via Riemannian Flow Matching - https://arxiv.org/abs/2603.15016 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15016.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fangran Miao, Jian Huang, Ting Li</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Human motion generation is often learned in Euclidean spaces, although valid motions follow structured non-Euclidean geometry. We present Riemannian Motion Generation (RMG), a unified framework that represents motion on a product manifold and learns dynamics via Riemannian flow matching. RMG factorizes motion into several manifold factors, yielding a scale-free representation with intrinsic normalization, and uses geodesic interpolation, tangent-space supervision, and manifold-preserving ODE integration for training and sampling. On HumanML3D, RMG achieves state-of-the-art FID in the HumanML3D format (0.043) and ranks first on all reported metrics under the MotionStreamer format. On MotionMillion, it also surpasses strong baselines (FID 5.6, R@1 0.86). Ablations show that the compact T+R (translation + rotations) representation is the most stable and effective, highlighting geometry-aware modeling as a practical and scalable route to high-fidelity motion generation.</p> - https://arxiv.org/abs/2603.15016 - Mon, 16 Mar 2026 09:19:10 +0000 + LumosX: Relate Any Identities with Their Attributes for Personalized Video Generation + https://arxiv.org/abs/2603.20192 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.20192.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiazheng Xing, Fei Du, Hangjie Yuan, Pengwei Liu, Hongbin Xu, Hai Ci, Ruigang Niu, Weihua Chen, Fan Wang, Yong Liu</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> Recent advances in diffusion models have significantly improved text-to-video generation, enabling personalized content creation with fine-grained control over both foreground and background elements. However, precise face-attribute alignment across subjects remains challenging, as existing methods lack explicit mechanisms to ensure intra-group consistency. Addressing this gap requires both explicit modeling strategies and face-attribute-aware data resources. We therefore propose LumosX, a framework that advances both data and model design. On the data side, a tailored collection pipeline orchestrates captions and visual cues from independent videos, while multimodal large language models (MLLMs) infer and assign subject-specific dependencies. These extracted relational priors impose a finer-grained structure that amplifies the expressive control of personalized video generation and enables the construction of a comprehensive benchmark. On the modeling side, Relational Self-Attention and Relational Cross-Attention intertwine position-aware embeddings with refined attention dynamics to inscribe explicit subject-attribute dependencies, enforcing disciplined intra-group cohesion and amplifying the separation between distinct subject clusters. Comprehensive evaluations on our benchmark demonstrate that LumosX achieves state-of-the-art performance in fine-grained, identity-consistent, and semantically aligned personalized multi-subject video generation. Code and models are available at https://jiazheng-xing.github.io/lumosx-home/.</p> + https://arxiv.org/abs/2603.20192 + Fri, 20 Mar 2026 17:59:46 +0000 - VTC-Bench: Evaluating Agentic Multimodal Models via Compositional Visual Tool Chaining - https://arxiv.org/abs/2603.15030 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15030.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xuanyu Zhu, Yuhao Dong, Rundong Wang, Yang Shi, Zhipeng Wu, Yinlun Peng, YiFan Zhang, Yihang Lou, Yuanxing Zhang, Ziwei Liu, Yan Bai, Yuan Zhou</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Recent advancements extend Multimodal Large Language Models (MLLMs) beyond standard visual question answering to utilizing external tools for advanced visual tasks. Despite this progress, precisely executing and effectively composing diverse tools for complex tasks remain persistent bottleneck. Constrained by sparse tool-sets and simple tool-use trajectories, existing benchmarks fail to capture complex and diverse tool interactions, falling short in evaluating model performance under practical, real-world conditions. To bridge this gap, we introduce VisualToolChain-Bench(VTC-Bench), a comprehensive benchmark designed to evaluate tool-use proficiency in MLLMs. To align with realistic computer vision pipelines, our framework features 32 diverse OpenCV-based visual operations. This rich tool-set enables extensive combinations, allowing VTC-Bench to rigorously assess multi-tool composition and long-horizon, multi-step plan execution. For precise evaluation, we provide 680 curated problems structured across a nine-category cognitive hierarchy, each with ground-truth execution trajectories. Extensive experiments on 19 leading MLLMs reveal critical limitations in current models' visual agentic capabilities. Specifically, models struggle to adapt to diverse tool-sets and generalize to unseen operations, with the leading model Gemini-3.0-Pro only achieving 51% on our benchmark. Furthermore, multi-tool composition remains a persistent challenge. When facing complex tasks, models struggle to formulate efficient execution plans, relying heavily on a narrow, suboptimal subset of familiar functions rather than selecting the optimal tools. By identifying these fundamental challenges, VTC-Bench establishes a rigorous baseline to guide the development of more generalized visual agentic models.</p> - https://arxiv.org/abs/2603.15030 - Mon, 16 Mar 2026 09:31:44 +0000 + PEARL: Personalized Streaming Video Understanding Model + https://arxiv.org/abs/2603.20422 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.20422.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuanhong Zheng, Ruichuan An, Xiaopeng Lin, Yuxing Liu, Sihan Yang, Huanyu Zhang, Haodong Li, Qintong Zhang, Renrui Zhang, Guopeng Li, Yifan Zhang, Yuheng Li, Wentao Zhang</p><p><b>Upvotes:</b> 38</p><p><b>Summary:</b> Human cognition of new concepts is inherently a streaming process: we continuously recognize new objects or identities and update our memories over time. However, current multimodal personalization methods are largely limited to static images or offline videos. This disconnects continuous visual input from instant real-world feedback, limiting their ability to provide the real-time, interactive personalized responses essential for future AI assistants. To bridge this gap, we first propose and formally define the novel task of Personalized Streaming Video Understanding (PSVU). To facilitate research in this new direction, we introduce PEARL-Bench, the first comprehensive benchmark designed specifically to evaluate this challenging setting. It evaluates a model's ability to respond to personalized concepts at exact timestamps under two modes: (1) Frame-level, focusing on a specific person or object in discrete frames, and (2) a novel Video-level, focusing on personalized actions unfolding across continuous frames. PEARL-Bench comprises 132 unique videos and 2,173 fine-grained annotations with precise timestamps. Concept diversity and annotation quality are strictly ensured through a combined pipeline of automated generation and human verification. To tackle this challenging new setting, we further propose PEARL, a plug-and-play, training-free strategy that serves as a strong baseline. Extensive evaluations across 8 offline and online models demonstrate that PEARL achieves state-of-the-art performance. Notably, it brings consistent PSVU improvements when applied to 3 distinct architectures, proving to be a highly effective and robust strategy. We hope this work advances vision-language model (VLM) personalization and inspires further research into streaming personalized AI assistants. Code is available at https://github.com/Yuanhong-Zheng/PEARL.</p> + https://arxiv.org/abs/2603.20422 + Fri, 20 Mar 2026 18:47:54 +0000 - Attention Residuals - https://arxiv.org/abs/2603.15031 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15031.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kimi Team, Guangyu Chen, Yu Zhang, Jianlin Su, Weixin Xu, Siyuan Pan, Yaoyu Wang, Yucheng Wang, Guanduo Chen, Bohong Yin, Yutian Chen, Junjie Yan, Ming Wei, Y. Zhang, Fanqing Meng, Chao Hong, Xiaotong Xie, Shaowei Liu, Enzhe Lu, Yunpeng Tai, Yanru Chen, Xin Men, Haiqing Guo, Y. Charles, Haoyu Lu, Lin Sui, Jinguo Zhu, Zaida Zhou, Weiran He, Weixiao Huang, Xinran Xu, Yuzhi Wang, Guokun Lai, Yulun Du, Yuxin Wu, Zhilin Yang, Xinyu Zhou</p><p><b>Upvotes:</b> 137</p><p><b>Summary:</b> Residual connections with PreNorm are standard in modern LLMs, yet they accumulate all layer outputs with fixed unit weights. This uniform aggregation causes uncontrolled hidden-state growth with depth, progressively diluting each layer's contribution. We propose Attention Residuals (AttnRes), which replaces this fixed accumulation with softmax attention over preceding layer outputs, allowing each layer to selectively aggregate earlier representations with learned, input-dependent weights. To address the memory and communication overhead of attending over all preceding layer outputs for large-scale model training, we introduce Block AttnRes, which partitions layers into blocks and attends over block-level representations, reducing the memory footprint while preserving most of the gains of full AttnRes. Combined with cache-based pipeline communication and a two-phase computation strategy, Block AttnRes becomes a practical drop-in replacement for standard residual connections with minimal overhead. Scaling law experiments confirm that the improvement is consistent across model sizes, and ablations validate the benefit of content-dependent depth-wise selection. We further integrate AttnRes into the Kimi Linear architecture (48B total / 3B activated parameters) and pre-train on 1.4T tokens, where AttnRes mitigates PreNorm dilution, yielding more uniform output magnitudes and gradient distribution across depth, and improves downstream performance across all evaluated tasks.</p> - https://arxiv.org/abs/2603.15031 - Mon, 16 Mar 2026 09:32:21 +0000 + Agentic AI and the next intelligence explosion + https://arxiv.org/abs/2603.20639 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.20639.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> James Evans, Benjamin Bratton, Blaise Agüera y Arcas</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> The "AI singularity" is often miscast as a monolithic, godlike mind. Evolution suggests a different path: intelligence is fundamentally plural, social, and relational. Recent advances in agentic AI reveal that frontier reasoning models, such as DeepSeek-R1, do not improve simply by "thinking longer". Instead, they simulate internal "societies of thought," spontaneous cognitive debates that argue, verify, and reconcile to solve complex tasks. Moreover, we are entering an era of human-AI centaurs: hybrid actors where collective agency transcends individual control. Scaling this intelligence requires shifting from dyadic alignment (RLHF) toward institutional alignment. By designing digital protocols, modeled on organizations and markets, we can build a social infrastructure of checks and balances. The next intelligence explosion will not be a single silicon brain, but a complex, combinatorial society specializing and sprawling like a city. No mind is an island.</p> + https://arxiv.org/abs/2603.20639 + Sat, 21 Mar 2026 04:23:11 +0000 - ReactMotion: Generating Reactive Listener Motions from Speaker Utterance - https://arxiv.org/abs/2603.15083 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15083.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Cheng Luo, Bizhu Wu, Bing Li, Jianfeng Ren, Ruibin Bai, Rong Qu, Linlin Shen, Bernard Ghanem</p><p><b>Upvotes:</b> 23</p><p><b>Summary:</b> In this paper, we introduce a new task, Reactive Listener Motion Generation from Speaker Utterance, which aims to generate naturalistic listener body motions that appropriately respond to a speaker's utterance. However, modeling such nonverbal listener behaviors remains underexplored and challenging due to the inherently non-deterministic nature of human reactions. To facilitate this task, we present ReactMotionNet, a large-scale dataset that pairs speaker utterances with multiple candidate listener motions annotated with varying degrees of appropriateness. This dataset design explicitly captures the one-to-many nature of listener behavior and provides supervision beyond a single ground-truth motion. Building on this dataset design, we develop preference-oriented evaluation protocols tailored to evaluate reactive appropriateness, where conventional motion metrics focusing on input-motion alignment ignore. We further propose ReactMotion, a unified generative framework that jointly models text, audio, emotion, and motion, and is trained with preference-based objectives to encourage both appropriate and diverse listener responses. Extensive experiments show that ReactMotion outperforms retrieval baselines and cascaded LLM-based pipelines, generating more natural, diverse, and appropriate listener motions.</p> - https://arxiv.org/abs/2603.15083 - Mon, 16 Mar 2026 10:37:42 +0000 + REVERE: Reflective Evolving Research Engineer for Scientific Workflows + https://arxiv.org/abs/2603.20667 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.20667.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Balaji Dinesh Gangireddi, Aniketh Garikaparthi, Manasi Patwardhan, Arman Cohan</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Existing prompt-optimization techniques rely on local signals to update behavior, often neglecting broader and recurring patterns across tasks, leading to poor generalization; they further rely on full-prompt rewrites or unstructured merges, resulting in knowledge loss. These limitations are magnified in research-coding workflows, which involve heterogeneous repositories, underspecified environments, and weak feedback, where reproducing results from public codebases is an established evaluation regime. We introduce Reflective Evolving Research Engineer (REVERE), a framework that continuously learns from Global Training Context, recognizes recurring failure modes in cross-repository execution trajectories, distills them into reusable heuristics, and performs targeted edits across three configurable fields: the system prompt, a task-prompt template, and a cumulative cheatsheet. REVERE, via this reflective optimization framework, improves performance over prior state-of-the-art expert-crafted instructions on research coding tasks by 4.50% on SUPER, 3.51% on ResearchCodeBench, and 4.89% on ScienceAgentBench across their respective metrics. These results demonstrate that agents equipped with mechanisms for continual learning and global memory consolidation can meaningfully evolve their capabilities over time.</p> + https://arxiv.org/abs/2603.20667 + Sat, 21 Mar 2026 05:58:30 +0000 - WiT: Waypoint Diffusion Transformers via Trajectory Conflict Navigation - https://arxiv.org/abs/2603.15132 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15132.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hainuo Wang, Mingjia Li, Xiaojie Guo</p><p><b>Upvotes:</b> 35</p><p><b>Summary:</b> While recent Flow Matching models avoid the reconstruction bottlenecks of latent autoencoders by operating directly in pixel space, the lack of semantic continuity in the pixel manifold severely intertwines optimal transport paths. This induces severe trajectory conflicts near intersections, yielding sub-optimal solutions. Rather than bypassing this issue via information-lossy latent representations, we directly untangle the pixel-space trajectories by proposing Waypoint Diffusion Transformers (WiT). WiT factorizes the continuous vector field via intermediate semantic waypoints projected from pre-trained vision models. It effectively disentangles the generation trajectories by breaking the optimal transport into prior-to-waypoint and waypoint-to-pixel segments. Specifically, during the iterative denoising process, a lightweight generator dynamically infers these intermediate waypoints from the current noisy state. They then continuously condition the primary diffusion transformer via the Just-Pixel AdaLN mechanism, steering the evolution towards the next state, ultimately yielding the final RGB pixels. Evaluated on ImageNet 256x256, WiT beats strong pixel-space baselines, accelerating JiT training convergence by 2.2x. Code will be publicly released at https://github.com/hainuo-wang/WiT.git.</p> - https://arxiv.org/abs/2603.15132 - Mon, 16 Mar 2026 11:25:09 +0000 + T-MAP: Red-Teaming LLM Agents with Trajectory-aware Evolutionary Search + https://arxiv.org/abs/2603.22341 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22341.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hyomin Lee, Sangwoo Park, Yumin Choi, Sohyun An, Seanie Lee, Sung Ju Hwang</p><p><b>Upvotes:</b> 34</p><p><b>Summary:</b> While prior red-teaming efforts have focused on eliciting harmful text outputs from large language models (LLMs), such approaches fail to capture agent-specific vulnerabilities that emerge through multi-step tool execution, particularly in rapidly growing ecosystems such as the Model Context Protocol (MCP). To address this gap, we propose a trajectory-aware evolutionary search method, T-MAP, which leverages execution trajectories to guide the discovery of adversarial prompts. Our approach enables the automatic generation of attacks that not only bypass safety guardrails but also reliably realize harmful objectives through actual tool interactions. Empirical evaluations across diverse MCP environments demonstrate that T-MAP substantially outperforms baselines in attack realization rate (ARR) and remains effective against frontier models, including GPT-5.2, Gemini-3-Pro, Qwen3.5, and GLM-5, thereby revealing previously underexplored vulnerabilities in autonomous LLM agents.</p> + https://arxiv.org/abs/2603.22341 + Sat, 21 Mar 2026 12:33:34 +0000 - SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering? - https://arxiv.org/abs/2603.15401 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15401.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tingxu Han, Yi Zhang, Wei Song, Chunrong Fang, Zhenyu Chen, Youcheng Sun, Lijie Hu</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Agent skills, structured procedural knowledge packages injected at inference time, are increasingly used to augment LLM agents on software engineering tasks. However, their real utility in end-to-end development settings remains unclear. We present SWE-Skills-Bench, the first requirement-driven benchmark that isolates the marginal utility of agent skills in real-world software engineering (SWE). It pairs 49 public SWE skills with authentic GitHub repositories pinned at fixed commits and requirement documents with explicit acceptance criteria, yielding approximately 565 task instances across six SWE subdomains. We introduce a deterministic verification framework that maps each task's acceptance criteria to execution-based tests, enabling controlled paired evaluation with and without the skill. Our results show that skill injection benefits are far more limited than rapid adoption suggests: 39 of 49 skills yield zero pass-rate improvement, and the average gain is only +1.2%. Token overhead varies from modest savings to a 451% increase while pass rates remain unchanged. Only seven specialized skills produce meaningful gains (up to +30%), while three degrade performance (up to -10%) due to version-mismatched guidance conflicting with project context. These findings suggest that agent skills are a narrow intervention whose utility depends strongly on domain fit, abstraction level, and contextual compatibility. SWE-Skills-Bench provides a testbed for evaluating the design, selection, and deployment of skills in software engineering agents. SWE-Skills-Bench is available at https://github.com/GeniusHTX/SWE-Skills-Bench.</p> - https://arxiv.org/abs/2603.15401 - Mon, 16 Mar 2026 15:16:31 +0000 + 2Xplat: Two Experts Are Better Than One Generalist + https://arxiv.org/abs/2603.21064 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.21064.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hwasik Jeong, Seungryong Lee, Gyeongjin Kang, Seungkwon Yang, Xiangyu Sun, Seungtae Nam, Eunbyung Park</p><p><b>Upvotes:</b> 25</p><p><b>Summary:</b> Pose-free feed-forward 3D Gaussian Splatting (3DGS) has opened a new frontier for rapid 3D modeling, enabling high-quality Gaussian representations to be generated from uncalibrated multi-view images in a single forward pass. The dominant approach in this space adopts unified monolithic architectures, often built on geometry-centric 3D foundation models, to jointly estimate camera poses and synthesize 3DGS representations within a single network. While architecturally streamlined, such "all-in-one" designs may be suboptimal for high-fidelity 3DGS generation, as they entangle geometric reasoning and appearance modeling within a shared representation. In this work, we introduce 2Xplat, a pose-free feed-forward 3DGS framework based on a two-expert design that explicitly separates geometry estimation from Gaussian generation. A dedicated geometry expert first predicts camera poses, which are then explicitly passed to a powerful appearance expert that synthesizes 3D Gaussians. Despite its conceptual simplicity, being largely underexplored in prior works, the proposed approach proves highly effective. In fewer than 5K training iterations, the proposed two-experts pipeline substantially outperforms prior pose-free feed-forward 3DGS approaches and achieves performance on par with state-of-the-art posed methods. These results challenge the prevailing unified paradigm and suggest the potential advantages of modular design principles for complex 3D geometric estimation and appearance synthesis tasks.</p> + https://arxiv.org/abs/2603.21064 + Sun, 22 Mar 2026 05:14:38 +0000 - ViFeEdit: A Video-Free Tuner of Your Video Diffusion Transformer - https://arxiv.org/abs/2603.15478 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15478.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ruonan Yu, Zhenxiong Tan, Zigeng Chen, Songhua Liu, Xinchao Wang</p><p><b>Upvotes:</b> 24</p><p><b>Summary:</b> Diffusion Transformers (DiTs) have demonstrated remarkable scalability and quality in image and video generation, prompting growing interest in extending them to controllable generation and editing tasks. However, compared to the image counterparts, progress in video control and editing remains limited, mainly due to the scarcity of paired video data and the high computational cost of training video diffusion models. To address this issue, in this paper, we propose a video-free tuning framework termed ViFeEdit for video diffusion transformers. Without requiring any forms of video training data, ViFeEdit achieves versatile video generation and editing, adapted solely with 2D images. At the core of our approach is an architectural reparameterization that decouples spatial independence from the full 3D attention in modern video diffusion transformers, which enables visually faithful editing while maintaining temporal consistency with only minimal additional parameters. Moreover, this design operates in a dual-path pipeline with separate timestep embeddings for noise scheduling, exhibiting strong adaptability to diverse conditioning signals. Extensive experiments demonstrate that our method delivers promising results of controllable video generation and editing with only minimal training on 2D image data. Codes are available https://github.com/Lexie-YU/ViFeEdit.</p> - https://arxiv.org/abs/2603.15478 - Mon, 16 Mar 2026 16:10:46 +0000 + LongCat-Flash-Prover: Advancing Native Formal Reasoning via Agentic Tool-Integrated Reinforcement Learning + https://arxiv.org/abs/2603.21065 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.21065.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jianing Wang, Jianfei Zhang, Qi Guo, Linsen Guo, Rumei Li, Chao Zhang, Chong Peng, Cunguang Wang, Dengchang Zhao, Jiarong Shi, Jingang Wang, Liulin Feng, Mengxia Shen, Qi Li, Shengnan An, Shun Wang, Wei Shi, Xiangyu Xi, Xiaoyu Li, Xuezhi Cao, Yi Lu, Yunke Zhao, Zhengyu Chen, Zhimin Lin, Wei Wang, Peng Pei, Xunliang Cai</p><p><b>Upvotes:</b> 75</p><p><b>Summary:</b> We introduce LongCat-Flash-Prover, a flagship 560-billion-parameter open-source Mixture-of- Experts (MoE) model that advances Native Formal Reasoning in Lean4 through agentic tool-integrated reasoning (TIR). We decompose the native formal reasoning task into three independent formal capabilities, i.e., auto-formalization, sketching, and proving. To facilitate these capabilities, we propose a Hybrid-Experts Iteration Framework to expand high-quality task trajectories, including generating a formal statement based on a given informal problem, producing a whole-proof directly from the statement, or a lemma-style sketch. During agentic RL, we present a Hierarchical Importance Sampling Policy Optimization (HisPO) algorithm, which aims to stabilize the MoE model training on such long-horizon tasks. It employs a gradient masking strategy that accounts for the policy staleness and the inherent train-inference engine discrepancies at both sequence and token levels. Additionally, we also incorporate theorem consistency and legality detection mechanisms to eliminate reward hacking issues. Extensive evaluations show that our LongCat-Flash-Prover sets a new state-of-the-art for open-weights models in both auto-formalization and theorem proving. Demonstrating remarkable sample efficiency, it achieves a 97.1% pass rate on MiniF2F-Test using only 72 inference budget per problem. On more challenging benchmarks, it solves 70.8% of ProverBench and 41.5% of PutnamBench with no more than 220 attempts per problem, significantly outperforming existing open-weights baselines.</p> + https://arxiv.org/abs/2603.21065 + Sun, 22 Mar 2026 05:16:09 +0000 - Understanding Reasoning in LLMs through Strategic Information Allocation under Uncertainty - https://arxiv.org/abs/2603.15500 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15500.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jeonghye Kim, Xufang Luo, Minbeom Kim, Sangmook Lee, Dongsheng Li, Yuqing Yang</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> LLMs often exhibit Aha moments during reasoning, such as apparent self-correction following tokens like "Wait," yet their underlying mechanisms remain unclear. We introduce an information-theoretic framework that decomposes reasoning into procedural information and epistemic verbalization - the explicit externalization of uncertainty that supports downstream control actions. We show that purely procedural reasoning can become informationally stagnant, whereas epistemic verbalization enables continued information acquisition and is critical for achieving information sufficiency. Empirical results demonstrate that strong reasoning performance is driven by uncertainty externalization rather than specific surface tokens. Our framework unifies prior findings on Aha moments and post-training experiments, and offers insights for future reasoning model design.</p> - https://arxiv.org/abs/2603.15500 - Mon, 16 Mar 2026 16:31:24 +0000 + When Models Judge Themselves: Unsupervised Self-Evolution for Multimodal Reasoning + https://arxiv.org/abs/2603.21289 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.21289.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhengxian Wu, Kai Shi, Chuanrui Zhang, Zirui Liao, Jun Yang, Ni Yang, Qiuying Peng, Luyuan Zhang, Hangrui Xu, Tianhuang Su, Zhenyu Yang, Haonan Lu, Haoqian Wang</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Recent progress in multimodal large language models has led to strong performance on reasoning tasks, but these improvements largely rely on high-quality annotated data or teacher-model distillation, both of which are costly and difficult to scale. To address this, we propose an unsupervised self-evolution training framework for multimodal reasoning that achieves stable performance improvements without using human-annotated answers or external reward models. For each input, we sample multiple reasoning trajectories and jointly model their within group structure. We use the Actor's self-consistency signal as a training prior, and introduce a bounded Judge based modulation to continuously reweight trajectories of different quality. We further model the modulated scores as a group level distribution and convert absolute scores into relative advantages within each group, enabling more robust policy updates. Trained with Group Relative Policy Optimization (GRPO) on unlabeled data, our method consistently improves reasoning performance and generalization on five mathematical reasoning benchmarks, offering a scalable path toward self-evolving multimodal models. The code are available at https://github.com/OPPO-Mente-Lab/LLM-Self-Judge.</p> + https://arxiv.org/abs/2603.21289 + Sun, 22 Mar 2026 15:22:19 +0000 - Anatomy of a Lie: A Multi-Stage Diagnostic Framework for Tracing Hallucinations in Vision-Language Models - https://arxiv.org/abs/2603.15557 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15557.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lexiang Xiong, Qi Li, Jingwen Ye, Xinchao Wang</p><p><b>Upvotes:</b> 28</p><p><b>Summary:</b> Vision-Language Models (VLMs) frequently "hallucinate" - generate plausible yet factually incorrect statements - posing a critical barrier to their trustworthy deployment. In this work, we propose a new paradigm for diagnosing hallucinations, recasting them from static output errors into dynamic pathologies of a model's computational cognition. Our framework is grounded in a normative principle of computational rationality, allowing us to model a VLM's generation as a dynamic cognitive trajectory. We design a suite of information-theoretic probes that project this trajectory onto an interpretable, low-dimensional Cognitive State Space. Our central discovery is a governing principle we term the geometric-information duality: a cognitive trajectory's geometric abnormality within this space is fundamentally equivalent to its high information-theoretic surprisal. Hallucination detection is counts as a geometric anomaly detection problem. Evaluated across diverse settings - from rigorous binary QA (POPE) and comprehensive reasoning (MME) to unconstrained open-ended captioning (MS-COCO) - our framework achieves state-of-the-art performance. Crucially, it operates with high efficiency under weak supervision and remains highly robust even when calibration data is heavily contaminated. This approach enables a causal attribution of failures, mapping observable errors to distinct pathological states: perceptual instability (measured by Perceptual Entropy), logical-causal failure (measured by Inferential Conflict), and decisional ambiguity (measured by Decision Entropy). Ultimately, this opens a path toward building AI systems whose reasoning is transparent, auditable, and diagnosable by design.</p> - https://arxiv.org/abs/2603.15557 - Mon, 16 Mar 2026 17:20:38 +0000 + F4Splat: Feed-Forward Predictive Densification for Feed-Forward 3D Gaussian Splatting + https://arxiv.org/abs/2603.21304 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.21304.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Injae Kim, Chaehyeon Kim, Minseong Bae, Minseok Joo, Hyunwoo J. Kim</p><p><b>Upvotes:</b> 32</p><p><b>Summary:</b> Feed-forward 3D Gaussian Splatting methods enable single-pass reconstruction and real-time rendering. However, they typically adopt rigid pixel-to-Gaussian or voxel-to-Gaussian pipelines that uniformly allocate Gaussians, leading to redundant Gaussians across views. Moreover, they lack an effective mechanism to control the total number of Gaussians while maintaining reconstruction fidelity. To address these limitations, we present F4Splat, which performs Feed-Forward predictive densification for Feed-Forward 3D Gaussian Splatting, introducing a densification-score-guided allocation strategy that adaptively distributes Gaussians according to spatial complexity and multi-view overlap. Our model predicts per-region densification scores to estimate the required Gaussian density and allows explicit control over the final Gaussian budget without retraining. This spatially adaptive allocation reduces redundancy in simple regions and minimizes duplicate Gaussians across overlapping views, producing compact yet high-quality 3D representations. Extensive experiments demonstrate that our model achieves superior novel-view synthesis performance compared to prior uncalibrated feed-forward methods, while using significantly fewer Gaussians.</p> + https://arxiv.org/abs/2603.21304 + Sun, 22 Mar 2026 16:03:56 +0000 - Panoramic Affordance Prediction - https://arxiv.org/abs/2603.15558 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15558.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zixin Zhang, Chenfei Liao, Hongfei Zhang, Harold Haodong Chen, Kanghao Chen, Zichen Wen, Litao Guo, Bin Ren, Xu Zheng, Yinchuan Li, Xuming Hu, Nicu Sebe, Ying-Cong Chen</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Affordance prediction serves as a critical bridge between perception and action in embodied AI. However, existing research is confined to pinhole camera models, which suffer from narrow Fields of View (FoV) and fragmented observations, often missing critical holistic environmental context. In this paper, we present the first exploration into Panoramic Affordance Prediction, utilizing 360-degree imagery to capture global spatial relationships and holistic scene understanding. To facilitate this novel task, we first introduce PAP-12K, a large-scale benchmark dataset containing over 1,000 ultra-high-resolution (12k, 11904 x 5952) panoramic images with over 12k carefully annotated QA pairs and affordance masks. Furthermore, we propose PAP, a training-free, coarse-to-fine pipeline inspired by the human foveal visual system to tackle the ultra-high resolution and severe distortion inherent in panoramic images. PAP employs recursive visual routing via grid prompting to progressively locate targets, applies an adaptive gaze mechanism to rectify local geometric distortions, and utilizes a cascaded grounding pipeline to extract precise instance-level masks. Experimental results on PAP-12K reveal that existing affordance prediction methods designed for standard perspective images suffer severe performance degradation and fail due to the unique challenges of panoramic vision. In contrast, PAP framework effectively overcomes these obstacles, significantly outperforming state-of-the-art baselines and highlighting the immense potential of panoramic perception for robust embodied intelligence.</p> - https://arxiv.org/abs/2603.15558 - Mon, 16 Mar 2026 17:21:49 +0000 + RoboAlign: Learning Test-Time Reasoning for Language-Action Alignment in Vision-Language-Action Models + https://arxiv.org/abs/2603.21341 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.21341.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dongyoung Kim, Sumin Park, Woomin Song, Seungku Kim, Taeyoung Kim, Huiwon Jang, Jinwoo Shin, Jaehyung Kim, Younggyo Seo</p><p><b>Upvotes:</b> 23</p><p><b>Summary:</b> Improving embodied reasoning in multimodal-large-language models (MLLMs) is essential for building vision-language-action models (VLAs) on top of them to readily translate multimodal understanding into low-level actions. Accordingly, recent work has explored enhancing embodied reasoning in MLLMs through supervision of vision-question-answering type. However, these approaches have been reported to result in unstable VLA performance, often yielding only marginal or even negative gains. In this paper, we propose a more systematic MLLM training framework RoboAlign that reliably improves VLA performance. Our key idea is to sample action tokens via zero-shot natural language reasoning and refines this reasoning using reinforcement learning (RL) to improve action accuracy. As a result, RoboAlign bridges the modality gap between language and low-level actions in MLLMs, and facilitate knowledge transfer from MLLM to VLA. To validate the effectiveness of RoboAlign, we train VLAs by adding a diffusion-based action head on top of an MLLM backbone and evaluate them on major robotics benchmarks. Remarkably, by performing RL-based alignment after SFT using less than 1\% of the data, RoboAlign achieves performance improvements of 17.5\%, 18.9\%, and 106.6\% over SFT baselines on LIBERO, CALVIN, and real-world environments, respectively.</p> + https://arxiv.org/abs/2603.21341 + Sun, 22 Mar 2026 17:57:55 +0000 - The PokeAgent Challenge: Competitive and Long-Context Learning at Scale - https://arxiv.org/abs/2603.15563 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15563.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Seth Karten, Jake Grigsby, Tersoo Upaa, Junik Bae, Seonghun Hong, Hyunyoung Jeong, Jaeyoon Jung, Kun Kerdthaisong, Gyungbo Kim, Hyeokgi Kim, Yujin Kim, Eunju Kwon, Dongyu Liu, Patrick Mariglia, Sangyeon Park, Benedikt Schink, Xianwei Shi, Anthony Sistilli, Joseph Twin, Arian Urdu, Matin Urdu, Qiao Wang, Ling Wu, Wenli Zhang, Kunsheng Zhou, Stephanie Milani, Kiran Vodrahalli, Amy Zhang, Fei Fang, Yuke Zhu, Chi Jin</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> We present the PokeAgent Challenge, a large-scale benchmark for decision-making research built on Pokemon's multi-agent battle system and expansive role-playing game (RPG) environment. Partial observability, game-theoretic reasoning, and long-horizon planning remain open problems for frontier AI, yet few benchmarks stress all three simultaneously under realistic conditions. PokeAgent targets these limitations at scale through two complementary tracks: our Battling Track, which calls for strategic reasoning and generalization under partial observability in competitive Pokemon battles, and our Speedrunning Track, which requires long-horizon planning and sequential decision-making in the Pokemon RPG. Our Battling Track supplies a dataset of 20M+ battle trajectories alongside a suite of heuristic, RL, and LLM-based baselines capable of high-level competitive play. Our Speedrunning Track provides the first standardized evaluation framework for RPG speedrunning, including an open-source multi-agent orchestration system for modular, reproducible comparisons of harness-based LLM approaches. Our NeurIPS 2025 competition validates both the quality of our resources and the research community's interest in Pokemon, with over 100 teams competing across both tracks and winning solutions detailed in our paper. Participant submissions and our baselines reveal considerable gaps between generalist (LLM), specialist (RL), and elite human performance. Analysis against the BenchPress evaluation matrix shows that Pokemon battling is nearly orthogonal to standard LLM benchmarks, measuring capabilities not captured by existing suites and positioning Pokemon as an unsolved benchmark that can drive RL and LLM research forward. We transition to a living benchmark with a live leaderboard for Battling and self-contained evaluation for Speedrunning at https://pokeagentchallenge.com.</p> - https://arxiv.org/abs/2603.15563 - Mon, 16 Mar 2026 17:25:42 +0000 + Generalized Discrete Diffusion from Snapshots + https://arxiv.org/abs/2603.21342 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.21342.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Oussama Zekri, Théo Uscidda, Nicolas Boullé, Anna Korba</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> We introduce Generalized Discrete Diffusion from Snapshots (GDDS), a unified framework for discrete diffusion modeling that supports arbitrary noising processes over large discrete state spaces. Our formulation encompasses all existing discrete diffusion approaches, while allowing significantly greater flexibility in the choice of corruption dynamics. The forward noising process relies on uniformization and enables fast arbitrary corruption. For the reverse process, we derive a simple evidence lower bound (ELBO) based on snapshot latents, instead of the entire noising path, that allows efficient training of standard generative modeling architectures with clear probabilistic interpretation. Our experiments on large-vocabulary discrete generation tasks suggest that the proposed framework outperforms existing discrete diffusion methods in terms of training efficiency and generation quality, and beats autoregressive models for the first time at this scale. We provide the code along with a blog post on the project page : https://oussamazekri.fr/gdds{https://oussamazekri.fr/gdds}.</p> + https://arxiv.org/abs/2603.21342 + Sun, 22 Mar 2026 17:58:01 +0000 - Grounding World Simulation Models in a Real-World Metropolis - https://arxiv.org/abs/2603.15583 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15583.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junyoung Seo, Hyunwook Choi, Minkyung Kwon, Jinhyeok Choi, Siyoon Jin, Gayoung Lee, Junho Kim, JoungBin Lee, Geonmo Gu, Dongyoon Han, Sangdoo Yun, Seungryong Kim, Jin-Hwa Kim</p><p><b>Upvotes:</b> 142</p><p><b>Summary:</b> What if a world simulation model could render not an imagined environment but a city that actually exists? Prior generative world models synthesize visually plausible yet artificial environments by imagining all content. We present Seoul World Model (SWM), a city-scale world model grounded in the real city of Seoul. SWM anchors autoregressive video generation through retrieval-augmented conditioning on nearby street-view images. However, this design introduces several challenges, including temporal misalignment between retrieved references and the dynamic target scene, limited trajectory diversity and data sparsity from vehicle-mounted captures at sparse intervals. We address these challenges through cross-temporal pairing, a large-scale synthetic dataset enabling diverse camera trajectories, and a view interpolation pipeline that synthesizes coherent training videos from sparse street-view images. We further introduce a Virtual Lookahead Sink to stabilize long-horizon generation by continuously re-grounding each chunk to a retrieved image at a future location. We evaluate SWM against recent video world models across three cities: Seoul, Busan, and Ann Arbor. SWM outperforms existing methods in generating spatially faithful, temporally consistent, long-horizon videos grounded in actual urban environments over trajectories reaching hundreds of meters, while supporting diverse camera movements and text-prompted scenario variations.</p> - https://arxiv.org/abs/2603.15583 - Mon, 16 Mar 2026 17:46:04 +0000 + PivotRL: High Accuracy Agentic Post-Training at Low Compute Cost + https://arxiv.org/abs/2603.21383 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.21383.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junkeun Yi, Damon Mosk-Aoyama, Baihe Huang, Ritu Gala, Charles Wang, Sugam Dipak Devare, Khushi Bhardwaj, Abhibha Gupta, Oleksii Kuchaiev, Jiantao Jiao, Jian Zhang, Venkat Srinivasan</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> Post-training for long-horizon agentic tasks has a tension between compute efficiency and generalization. While supervised fine-tuning (SFT) is compute efficient, it often suffers from out-of-domain (OOD) degradation. Conversely, end-to-end reinforcement learning (E2E RL) preserves OOD capabilities, but incurs high compute costs due to many turns of on-policy rollout. We introduce PivotRL, a novel framework that operates on existing SFT trajectories to combine the compute efficiency of SFT with the OOD accuracy of E2E RL. PivotRL relies on two key mechanisms: first, it executes local, on-policy rollouts and filters for pivots: informative intermediate turns where sampled actions exhibit high variance in outcomes; second, it utilizes rewards for functional-equivalent actions rather than demanding strict string matching with the SFT data demonstration. We theoretically show that these mechanisms incentivize strong learning signals with high natural gradient norm, while maximally preserving policy probability ordering on actions unrelated to training tasks. In comparison to standard SFT on identical data, we demonstrate that PivotRL achieves +4.17% higher in-domain accuracy on average across four agentic domains, and +10.04% higher OOD accuracy in non-agentic tasks. Notably, on agentic coding tasks, PivotRL achieves competitive accuracy with E2E RL with 4x fewer rollout turns. PivotRL is adopted by NVIDIA's Nemotron-3-Super-120B-A12B, acting as the workhorse in production-scale agentic post-training.</p> + https://arxiv.org/abs/2603.21383 + Sun, 22 Mar 2026 19:59:48 +0000 - Effective Distillation to Hybrid xLSTM Architectures - https://arxiv.org/abs/2603.15590 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15590.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lukas Hauzenberger, Niklas Schmidinger, Thomas Schmied, Anamaria-Roberta Hartl, David Stap, Pieter-Jan Hoedt, Maximilian Beck, Sebastian Böck, Günter Klambauer, Sepp Hochreiter</p><p><b>Upvotes:</b> 31</p><p><b>Summary:</b> There have been numerous attempts to distill quadratic attention-based large language models (LLMs) into sub-quadratic linearized architectures. However, despite extensive research, such distilled models often fail to match the performance of their teacher LLMs on various downstream tasks. We set out the goal of lossless distillation, which we define in terms of tolerance-corrected Win-and-Tie rates between student and teacher on sets of tasks. To this end, we introduce an effective distillation pipeline for xLSTM-based students. We propose an additional merging stage, where individually linearized experts are combined into a single model. We show the effectiveness of this pipeline by distilling base and instruction-tuned models from the Llama, Qwen, and Olmo families. In many settings, our xLSTM-based students recover most of the teacher's performance, and even exceed it on some downstream tasks. Our contributions are an important step towards more energy-efficient and cost-effective replacements for transformer-based LLMs.</p> - https://arxiv.org/abs/2603.15590 - Mon, 16 Mar 2026 17:49:04 +0000 + Effective Strategies for Asynchronous Software Engineering Agents + https://arxiv.org/abs/2603.21489 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.21489.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiayi Geng, Graham Neubig</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> AI agents have become increasingly capable at isolated software engineering (SWE) tasks such as resolving issues on Github. Yet long-horizon tasks involving multiple interdependent subtasks still pose challenges both with respect to accuracy, and with respect to timely completion. A natural approach to solving these long-horizon tasks in a timely manner is asynchronous multi-agent collaboration, where multiple agents work on different parts of the task at the same time. But effective application of multi-agent systems has proven surprisingly difficult: concurrent edits by multiple agents interfere with each other, dependencies are difficult to synchronize, and combining partial progress into a coherent whole is challenging. On the other hand, human developers have long relied on mature collaboration infrastructure to manage these challenges in large software projects. Inspired by these collaboration primitives, we introduce Centralized Asynchronous Isolated Delegation (CAID), a structured multi-agent coordination paradigm grounded in three core SWE primitives: centralized task delegation, asynchronous execution, and isolated workspaces. CAID constructs dependency-aware task plans through a central manager, executes subtasks concurrently in isolated workspaces, and consolidates progress via structured integration with executable test-based verification. In empirical evaluation, we find that CAID improves accuracy over single-agent baselines by 26.7% absolute on paper reproduction tasks (PaperBench) and 14.3% on Python library development tasks (Commit0). Through systematic analysis, we find that branch-and-merge is a central coordination mechanism for multi-agent collaboration, and that SWE primitives such as git worktree, git commit, and git merge enable it to be realized in a reliable and executable manner.</p> + https://arxiv.org/abs/2603.21489 + Mon, 23 Mar 2026 02:26:35 +0000 - OpenSeeker: Democratizing Frontier Search Agents by Fully Open-Sourcing Training Data - https://arxiv.org/abs/2603.15594 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15594.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuwen Du, Rui Ye, Shuo Tang, Xinyu Zhu, Yijun Lu, Yuzhu Cai, Siheng Chen</p><p><b>Upvotes:</b> 141</p><p><b>Summary:</b> Deep search capabilities have become an indispensable competency for frontier Large Language Model (LLM) agents, yet the development of high-performance search agents remains dominated by industrial giants due to a lack of transparent, high-quality training data. This persistent data scarcity has fundamentally hindered the progress of the broader research community in developing and innovating within this domain. To bridge this gap, we introduce OpenSeeker, the first fully open-source search agent (i.e., model and data) that achieves frontier-level performance through two core technical innovations: (1) Fact-grounded scalable controllable QA synthesis, which reverse-engineers the web graph via topological expansion and entity obfuscation to generate complex, multi-hop reasoning tasks with controllable coverage and complexity. (2) Denoised trajectory synthesis, which employs a retrospective summarization mechanism to denoise the trajectory, therefore promoting the teacher LLMs to generate high-quality actions. Experimental results demonstrate that OpenSeeker, trained (a single training run) on only 11.7k synthesized samples, achieves state-of-the-art performance across multiple benchmarks including BrowseComp, BrowseComp-ZH, xbench-DeepSearch, and WideSearch. Notably, trained with simple SFT, OpenSeeker significantly outperforms the second-best fully open-source agent DeepDive (e.g., 29.5% v.s. 15.3% on BrowseComp), and even surpasses industrial competitors such as Tongyi DeepResearch (trained via extensive continual pre-training, SFT, and RL) on BrowseComp-ZH (48.4% v.s. 46.7%). We fully open-source the complete training dataset and the model weights to democratize frontier search agent research and foster a more transparent, collaborative ecosystem.</p> - https://arxiv.org/abs/2603.15594 - Mon, 16 Mar 2026 17:52:04 +0000 + mSFT: Addressing Dataset Mixtures Overfiting Heterogeneously in Multi-task SFT + https://arxiv.org/abs/2603.21606 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.21606.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Woosung Koh, Jeyoung Jeon, Youngjin Song, Yujin Cheon, Soowon Oh, Jaehyeong Choi, Se-Young Yun</p><p><b>Upvotes:</b> 36</p><p><b>Summary:</b> Current language model training commonly applies multi-task Supervised Fine-Tuning (SFT) using a homogeneous compute budget across all sub-datasets. This approach is fundamentally sub-optimal: heterogeneous learning dynamics cause faster-learning tasks to overfit early while slower ones remain under-fitted. To address this, we introduce mSFT, an iterative, overfitting-aware search algorithm for multi-task data mixtures. mSFT trains the model on an active mixture, identifies and excludes the earliest overfitting sub-dataset, and reverts to that specific optimal checkpoint before continuing. Extensive evaluations demonstrate that mSFT consistently outperforms 4 baselines across 10 benchmarks and 6 base models. Further analysis confirms mSFT maintains robust gains across diverse dataset sizes, task granularities, and is insensitive to its single new hyperparameter (compute budget). Notably, at low compute budget, mSFT can improve performance while lowering training FLOPs. Ultimately, mSFT establishes a practical overfitting-aware algorithm for multi-task SFT that maximizes the potential of models across diverse data mixtures.</p> + https://arxiv.org/abs/2603.21606 + Mon, 23 Mar 2026 06:01:51 +0000 - MiroThinker-1.7 & H1: Towards Heavy-Duty Research Agents via Verification - https://arxiv.org/abs/2603.15726 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15726.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> MiroMind Team, S. Bai, L. Bing, L. Lei, R. Li, X. Li, X. Lin, E. Min, L. Su, B. Wang, L. Wang, L. Wang, S. Wang, X. Wang, Y. Zhang, Z. Zhang, G. Chen, L. Chen, Z. Cheng, Y. Deng, Z. Huang, D. Ng, J. Ni, Q. Ren, X. Tang, B. L. Wang, H. Wang, N. Wang, C. Wei, Q. Wu, J. Xia, Y. Xiao, H. Xu, X. Xu, C. Xue, Z. Yang, Z. Yang, F. Ye, H. Ye, J. Yu, C. Zhang, W. Zhang, H. Zhao, P. Zhu</p><p><b>Upvotes:</b> 175</p><p><b>Summary:</b> We present MiroThinker-1.7, a new research agent designed for complex long-horizon reasoning tasks. Building on this foundation, we further introduce MiroThinker-H1, which extends the agent with heavy-duty reasoning capabilities for more reliable multi-step problem solving. In particular, MiroThinker-1.7 improves the reliability of each interaction step through an agentic mid-training stage that emphasizes structured planning, contextual reasoning, and tool interaction. This enables more effective multi-step interaction and sustained reasoning across complex tasks. MiroThinker-H1 further incorporates verification directly into the reasoning process at both local and global levels. Intermediate reasoning decisions can be evaluated and refined during inference, while the overall reasoning trajectory is audited to ensure that final answers are supported by coherent chains of evidence. Across benchmarks covering open-web research, scientific reasoning, and financial analysis, MiroThinker-H1 achieves state-of-the-art performance on deep research tasks while maintaining strong results on specialized domains. We also release MiroThinker-1.7 and MiroThinker-1.7-mini as open-source models, providing competitive research-agent capabilities with significantly improved efficiency.</p> - https://arxiv.org/abs/2603.15726 - Mon, 16 Mar 2026 17:55:42 +0000 + 4DGS360: 360° Gaussian Reconstruction of Dynamic Objects from a Single Video + https://arxiv.org/abs/2603.21618 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.21618.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jae Won Jang, Yeonjin Chang, Wonsik Shin, Juhwan Cho, Nojun Kwak</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> We introduce 4DGS360, a diffusion-free framework for 360^{circ} dynamic object reconstruction from casual monocular video. Existing methods often fail to reconstruct consistent 360^{circ} geometry, as their heavy reliance on 2D-native priors causes initial points to overfit to visible surface in each training view. 4DGS360 addresses this challenge through a advanced 3D-native initialization that mitigates the geometric ambiguity of occluded regions. Our proposed 3D tracker, AnchorTAP3D, produces reinforced 3D point trajectories by leveraging confident 2D track points as anchors, suppressing drift and providing reliable initialization that preserves geometry in occluded regions. This initialization, combined with optimization, yields coherent 360^{circ} 4D reconstructions. We further present iPhone360, a new benchmark where test cameras are placed up to 135^{circ} apart from training views, enabling 360^{circ} evaluation that existing datasets cannot provide. Experiments show that 4DGS360 achieves state-of-the-art performance on the iPhone360, iPhone, and DAVIS datasets, both qualitatively and quantitatively.</p> + https://arxiv.org/abs/2603.21618 + Mon, 23 Mar 2026 06:30:46 +0000 - Code-A1: Adversarial Evolving of Code LLM and Test LLM via Reinforcement Learning - https://arxiv.org/abs/2603.15611 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15611.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Aozhe Wang, Yuchen Yan, Nan Zhou, Zhengxi Lu, Weiming Lu, Jun Xiao, Yueting Zhuang, Yongliang Shen</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Reinforcement learning for code generation relies on verifiable rewards from unit test pass rates. Yet high-quality test suites are scarce, existing datasets offer limited coverage, and static rewards fail to adapt as models improve. Recent self-play methods unify code and test generation in a single model, but face a inherent dilemma: white-box access leads to self-collusion where the model produces trivial tests for easy rewards, yet black-box restriction yields generic tests that miss implementation-specific bugs. We introduce Code-A1, an adversarial co-evolution framework that jointly optimizes a Code LLM and a Test LLM with opposing objectives. The Code LLM is rewarded for passing more tests, while the Test LLM is rewarded for exposing more defects. This architectural separation eliminates self-collusion risks and safely enables white-box test generation, where the Test LLM can inspect candidate code to craft targeted adversarial tests. We further introduce a Mistake Book mechanism for experience replay and a composite reward balancing test validity with adversarial difficulty. Experiments on Qwen2.5-Coder models demonstrate that Code-A1 achieves code generation performance matching or exceeding models trained on human-annotated tests, while significantly improving test generation capability.</p> - https://arxiv.org/abs/2603.15611 - Mon, 16 Mar 2026 17:58:13 +0000 + The Universal Normal Embedding + https://arxiv.org/abs/2603.21786 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.21786.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chen Tasker, Roy Betser, Eyal Gofer, Meir Yossef Levi, Guy Gilboa</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Generative models and vision encoders have largely advanced on separate tracks, optimized for different goals and grounded in different mathematical principles. Yet, they share a fundamental property: latent space Gaussianity. Generative models map Gaussian noise to images, while encoders map images to semantic embeddings whose coordinates empirically behave as Gaussian. We hypothesize that both are views of a shared latent source, the Universal Normal Embedding (UNE): an approximately Gaussian latent space from which encoder embeddings and DDIM-inverted noise arise as noisy linear projections. To test our hypothesis, we introduce NoiseZoo, a dataset of per-image latents comprising DDIM-inverted diffusion noise and matching encoder representations (CLIP, DINO). On CelebA, linear probes in both spaces yield strong, aligned attribute predictions, indicating that generative noise encodes meaningful semantics along linear directions. These directions further enable faithful, controllable edits (e.g., smile, gender, age) without architectural changes, where simple orthogonalization mitigates spurious entanglements. Taken together, our results provide empirical support for the UNE hypothesis and reveal a shared Gaussian-like latent geometry that concretely links encoding and generation. Code and data are available https://rbetser.github.io/UNE/</p> + https://arxiv.org/abs/2603.21786 + Mon, 23 Mar 2026 10:28:14 +0000 - HSImul3R: Physics-in-the-Loop Reconstruction of Simulation-Ready Human-Scene Interactions - https://arxiv.org/abs/2603.15612 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15612.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yukang Cao, Haozhe Xie, Fangzhou Hong, Long Zhuo, Zhaoxi Chen, Liang Pan, Ziwei Liu</p><p><b>Upvotes:</b> 149</p><p><b>Summary:</b> We present HSImul3R, a unified framework for simulation-ready 3D reconstruction of human-scene interactions (HSI) from casual captures, including sparse-view images and monocular videos. Existing methods suffer from a perception-simulation gap: visually plausible reconstructions often violate physical constraints, leading to instability in physics engines and failure in embodied AI applications. To bridge this gap, we introduce a physically-grounded bi-directional optimization pipeline that treats the physics simulator as an active supervisor to jointly refine human dynamics and scene geometry. In the forward direction, we employ Scene-targeted Reinforcement Learning to optimize human motion under dual supervision of motion fidelity and contact stability. In the reverse direction, we propose Direct Simulation Reward Optimization, which leverages simulation feedback on gravitational stability and interaction success to refine scene geometry. We further present HSIBench, a new benchmark with diverse objects and interaction scenarios. Extensive experiments demonstrate that HSImul3R produces the first stable, simulation-ready HSI reconstructions and can be directly deployed to real-world humanoid robots.</p> - https://arxiv.org/abs/2603.15612 - Mon, 16 Mar 2026 17:58:33 +0000 + Manifold-Aware Exploration for Reinforcement Learning in Video Generation + https://arxiv.org/abs/2603.21872 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.21872.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mingzhe Zheng, Weijie Kong, Yue Wu, Dengyang Jiang, Yue Ma, Xuanhua He, Bin Lin, Kaixiong Gong, Zhao Zhong, Liefeng Bo, Qifeng Chen, Harry Yang</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> Group Relative Policy Optimization (GRPO) methods for video generation like FlowGRPO remain far less reliable than their counterparts for language models and images. This gap arises because video generation has a complex solution space, and the ODE-to-SDE conversion used for exploration can inject excess noise, lowering rollout quality and making reward estimates less reliable, which destabilizes post-training alignment. To address this problem, we view the pre-trained model as defining a valid video data manifold and formulate the core problem as constraining exploration within the vicinity of this manifold, ensuring that rollout quality is preserved and reward estimates remain reliable. We propose SAGE-GRPO (Stable Alignment via Exploration), which applies constraints at both micro and macro levels. At the micro level, we derive a precise manifold-aware SDE with a logarithmic curvature correction and introduce a gradient norm equalizer to stabilize sampling and updates across timesteps. At the macro level, we use a dual trust region with a periodic moving anchor and stepwise constraints so that the trust region tracks checkpoints that are closer to the manifold and limits long-horizon drift. We evaluate SAGE-GRPO on HunyuanVideo1.5 using the original VideoAlign as the reward model and observe consistent gains over previous methods in VQ, MQ, TA, and visual metrics (CLIPScore, PickScore), demonstrating superior performance in both reward maximization and overall video quality. The code and visual gallery are available at https://dungeonmassster.github.io/SAGE-GRPO-Page/.</p> + https://arxiv.org/abs/2603.21872 + Mon, 23 Mar 2026 12:04:38 +0000 - Look Before Acting: Enhancing Vision Foundation Representations for Vision-Language-Action Models - https://arxiv.org/abs/2603.15618 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15618.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yulin Luo, Hao Chen, Zhuangzhe Wu, Bowen Sui, Jiaming Liu, Chenyang Gu, Zhuoyang Liu, Qiuxuan Feng, Jiale Yu, Shuo Gu, Peng Jia, Pheng-Ann Heng, Shanghang Zhang</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> Vision-Language-Action (VLA) models have recently emerged as a promising paradigm for robotic manipulation, in which reliable action prediction critically depends on accurately interpreting and integrating visual observations conditioned on language instructions. Although recent works have sought to enhance the visual capabilities of VLA models, most approaches treat the LLM backbone as a black box, providing limited insight into how visual information is grounded into action generation. Therefore, we perform a systematic analysis of multiple VLA models across different action-generation paradigms and observe that sensitivity to visual tokens progressively decreases in deeper layers during action generation. Motivated by this observation, we propose DeepVision-VLA, built on a Vision-Language Mixture-of-Transformers (VL-MoT) framework. This framework enables shared attention between the vision foundation model and the VLA backbone, injecting multi-level visual features from the vision expert into deeper layers of the VLA backbone to enhance visual representations for precise and complex manipulation. In addition, we introduce Action-Guided Visual Pruning (AGVP), which leverages shallow-layer attention to prune irrelevant visual tokens while preserving task-relevant ones, reinforcing critical visual cues for manipulation with minimal computational overhead. DeepVision-VLA outperforms prior state-of-the-art methods by 9.0\% and 7.5\% on simulated and real-world tasks, respectively, providing new insights for the design of visually enhanced VLA models.</p> - https://arxiv.org/abs/2603.15618 - Mon, 16 Mar 2026 17:59:54 +0000 + Not All Layers Are Created Equal: Adaptive LoRA Ranks for Personalized Image Generation + https://arxiv.org/abs/2603.21884 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.21884.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Donald Shenaj, Federico Errica, Antonio Carta</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Low Rank Adaptation (LoRA) is the de facto fine-tuning strategy to generate personalized images from pre-trained diffusion models. Choosing a good rank is extremely critical, since it trades off performance and memory consumption, but today the decision is often left to the community's consensus, regardless of the personalized subject's complexity. The reason is evident: the cost of selecting a good rank for each LoRA component is combinatorial, so we opt for practical shortcuts such as fixing the same rank for all components. In this paper, we take a first step to overcome this challenge. Inspired by variational methods that learn an adaptive width of neural networks, we let the ranks of each layer freely adapt during fine-tuning on a subject. We achieve it by imposing an ordering of importance on the rank's positions, effectively encouraging the creation of higher ranks when strictly needed. Qualitatively and quantitatively, our approach, LoRA^2, achieves a competitive trade-off between DINO, CLIP-I, and CLIP-T across 29 subjects while requiring much less memory and lower rank than high rank LoRA versions. Code: https://github.com/donaldssh/NotAllLayersAreCreatedEqual.</p> + https://arxiv.org/abs/2603.21884 + Mon, 23 Mar 2026 12:13:47 +0000 - Mixture-of-Depths Attention - https://arxiv.org/abs/2603.15619 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15619.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lianghui Zhu, Yuxin Fang, Bencheng Liao, Shijie Wang, Tianheng Cheng, Zilong Huang, Chen Chen, Lai Wei, Yutao Zeng, Ya Wang, Yi Lin, Yu Li, Xinggang Wang</p><p><b>Upvotes:</b> 73</p><p><b>Summary:</b> Scaling depth is a key driver for large language models (LLMs). Yet, as LLMs become deeper, they often suffer from signal degradation: informative features formed in shallow layers are gradually diluted by repeated residual updates, making them harder to recover in deeper layers. We introduce mixture-of-depths attention (MoDA), a mechanism that allows each attention head to attend to sequence KV pairs at the current layer and depth KV pairs from preceding layers. We further describe a hardware-efficient algorithm for MoDA that resolves non-contiguous memory-access patterns, achieving 97.3% of FlashAttention-2's efficiency at a sequence length of 64K. Experiments on 1.5B-parameter models demonstrate that MoDA consistently outperforms strong baselines. Notably, it improves average perplexity by 0.2 across 10 validation benchmarks and increases average performance by 2.11% on 10 downstream tasks, with a negligible 3.7% FLOPs computational overhead. We also find that combining MoDA with post-norm yields better performance than using it with pre-norm. These results suggest that MoDA is a promising primitive for depth scaling. Code is released at https://github.com/hustvl/MoDA .</p> - https://arxiv.org/abs/2603.15619 - Mon, 16 Mar 2026 17:59:55 +0000 + MultiBind: A Benchmark for Attribute Misbinding in Multi-Subject Generation + https://arxiv.org/abs/2603.21937 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.21937.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wenqing Tian, Hanyi Mao, Zhaocheng Liu, Lihua Zhang, Qiang Liu, Jian Wu, Liang Wang</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Subject-driven image generation is increasingly expected to support fine-grained control over multiple entities within a single image. In multi-reference workflows, users may provide several subject images, a background reference, and long, entity-indexed prompts to control multiple people within one scene. In this setting, a key failure mode is cross-subject attribute misbinding: attributes are preserved, edited, or transferred to the wrong subject. Existing benchmarks and metrics largely emphasize holistic fidelity or per-subject self-similarity, making such failures hard to diagnose. We introduce MultiBind, a benchmark built from real multi-person photographs. Each instance provides slot-ordered subject crops with masks and bounding boxes, canonicalized subject references, an inpainted background reference, and a dense entity-indexed prompt derived from structured annotations. We also propose a dimension-wise confusion evaluation protocol that matches generated subjects to ground-truth slots and measures slot-to-slot similarity using specialists for face identity, appearance, pose, and expression. By subtracting the corresponding ground-truth similarity matrices, our method separates self-degradation from true cross-subject interference and exposes interpretable failure patterns such as drift, swap, dominance, and blending. Experiments on modern multi-reference generators show that MultiBind reveals binding failures that conventional reconstruction metrics miss.</p> + https://arxiv.org/abs/2603.21937 + Mon, 23 Mar 2026 12:54:36 +0000 - Semi-Autonomous Formalization of the Vlasov-Maxwell-Landau Equilibrium - https://arxiv.org/abs/2603.15929 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15929.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Vasily Ilin</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> We present a complete Lean 4 formalization of the equilibrium characterization in the Vlasov-Maxwell-Landau (VML) system, which describes the motion of charged plasma. The project demonstrates the full AI-assisted mathematical research loop: an AI reasoning model (Gemini DeepThink) generated the proof from a conjecture, an agentic coding tool (Claude Code) translated it into Lean from natural-language prompts, a specialized prover (Aristotle) closed 111 lemmas, and the Lean kernel verified the result. A single mathematician supervised the process over 10 days at a cost of \$200, writing zero lines of code. The entire development process is public: all 229 human prompts, and 213 git commits are archived in the repository. We report detailed lessons on AI failure modes -- hypothesis creep, definition-alignment bugs, agent avoidance behaviors -- and on what worked: the abstract/concrete proof split, adversarial self-review, and the critical role of human review of key definitions and theorem statements. Notably, the formalization was completed before the final draft of the corresponding math paper was finished.</p> - https://arxiv.org/abs/2603.15929 - Mon, 16 Mar 2026 21:21:53 +0000 + Group3D: MLLM-Driven Semantic Grouping for Open-Vocabulary 3D Object Detection + https://arxiv.org/abs/2603.21944 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.21944.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Youbin Kim, Jinho Park, Hogun Park, Eunbyung Park</p><p><b>Upvotes:</b> 26</p><p><b>Summary:</b> Open-vocabulary 3D object detection aims to localize and recognize objects beyond a fixed training taxonomy. In multi-view RGB settings, recent approaches often decouple geometry-based instance construction from semantic labeling, generating class-agnostic fragments and assigning open-vocabulary categories post hoc. While flexible, such decoupling leaves instance construction governed primarily by geometric consistency, without semantic constraints during merging. When geometric evidence is view-dependent and incomplete, this geometry-only merging can lead to irreversible association errors, including over-merging of distinct objects or fragmentation of a single instance. We propose Group3D, a multi-view open-vocabulary 3D detection framework that integrates semantic constraints directly into the instance construction process. Group3D maintains a scene-adaptive vocabulary derived from a multimodal large language model (MLLM) and organizes it into semantic compatibility groups that encode plausible cross-view category equivalence. These groups act as merge-time constraints: 3D fragments are associated only when they satisfy both semantic compatibility and geometric consistency. This semantically gated merging mitigates geometry-driven over-merging while absorbing multi-view category variability. Group3D supports both pose-known and pose-free settings, relying only on RGB observations. Experiments on ScanNet and ARKitScenes demonstrate that Group3D achieves state-of-the-art performance in multi-view open-vocabulary 3D detection, while exhibiting strong generalization in zero-shot scenarios. The project page is available at https://ubin108.github.io/Group3D/.</p> + https://arxiv.org/abs/2603.21944 + Mon, 23 Mar 2026 13:01:14 +0000 - Rethinking UMM Visual Generation: Masked Modeling for Efficient Image-Only Pre-training - https://arxiv.org/abs/2603.16139 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16139.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Peng Sun, Jun Xie, Tao Lin</p><p><b>Upvotes:</b> 30</p><p><b>Summary:</b> Unified Multimodal Models (UMMs) are often constrained by the pre-training of their visual generation components, which typically relies on inefficient paradigms and scarce, high-quality text-image paired data. In this paper, we systematically analyze pre-training recipes for UMM visual generation and identify these two issues as the major bottlenecks. To address them, we propose Image-Only Training for UMMs (IOMM), a data-efficient two-stage training framework. The first stage pre-trains the visual generative component exclusively using abundant unlabeled image-only data, thereby removing the dependency on paired data for this costly phase. The second stage fine-tunes the model using a mixture of unlabeled images and a small curated set of text-image pairs, leading to improved instruction alignment and generative quality. Extensive experiments show that IOMM not only improves training efficiency but also achieves state-of-the-art (SOTA) performance. For example, our IOMM-B (3.6B) model was trained from scratch using only sim 1050 H800 GPU hours (with the vast majority, 1000 hours, dedicated to the efficient image-only pre-training stage). It achieves 0.89 on GenEval and 0.55 on WISE--surpassing strong baselines such as BAGEL-7B (0.82 & 0.55) and BLIP3-o-4B (0.84 & 0.50). Code is available https://github.com/LINs-lab/IOMM{https://github.com/LINs-lab/IOMM}.</p> - https://arxiv.org/abs/2603.16139 - Tue, 17 Mar 2026 05:41:48 +0000 + Speed by Simplicity: A Single-Stream Architecture for Fast Audio-Video Generative Foundation Model + https://arxiv.org/abs/2603.21986 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.21986.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> SII-GAIR, Sand. ai, Ethan Chern, Hansi Teng, Hanwen Sun, Hao Wang, Hong Pan, Hongyu Jia, Jiadi Su, Jin Li, Junjie Yu, Lijie Liu, Lingzhi Li, Lyumanshan Ye, Min Hu, Qiangang Wang, Quanwei Qi, Steffi Chern, Tao Bu, Taoran Wang, Teren Xu, Tianning Zhang, Tiantian Mi, Weixian Xu, Wenqiang Zhang, Wentai Zhang, Xianping Yi, Xiaojie Cai, Xiaoyang Kang, Yan Ma, Yixiu Liu, Yunbo Zhang, Yunpeng Huang, Yutong Lin, Zewei Tao, Zhaoliang Liu, Zheng Zhang, Zhiyao Cen, Zhixuan Yu, Zhongshu Wang, Zhulin Hu, Zijin Zhou, Zinan Guo, Yue Cao, Pengfei Liu</p><p><b>Upvotes:</b> 117</p><p><b>Summary:</b> We present daVinci-MagiHuman, an open-source audio-video generative foundation model for human-centric generation. daVinci-MagiHuman jointly generates synchronized video and audio using a single-stream Transformer that processes text, video, and audio within a unified token sequence via self-attention only. This single-stream design avoids the complexity of multi-stream or cross-attention architectures while remaining easy to optimize with standard training and inference infrastructure. The model is particularly strong in human-centric scenarios, producing expressive facial performance, natural speech-expression coordination, realistic body motion, and precise audio-video synchronization. It supports multilingual spoken generation across Chinese (Mandarin and Cantonese), English, Japanese, Korean, German, and French. For efficient inference, we combine the single-stream backbone with model distillation, latent-space super-resolution, and a Turbo VAE decoder, enabling generation of a 5-second 256p video in 2 seconds on a single H100 GPU. In automatic evaluation, daVinci-MagiHuman achieves the highest visual quality and text alignment among leading open models, along with the lowest word error rate (14.60%) for speech intelligibility. In pairwise human evaluation, it achieves win rates of 80.0% against Ovi 1.1 and 60.9% against LTX 2.3 over 2000 comparisons. We open-source the complete model stack, including the base model, the distilled model, the super-resolution model, and the inference codebase.</p> + https://arxiv.org/abs/2603.21986 + Mon, 23 Mar 2026 13:49:06 +0000 - Reliable Reasoning in SVG-LLMs via Multi-Task Multi-Reward Reinforcement Learning - https://arxiv.org/abs/2603.16189 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16189.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haomin Wang, Qi Wei, Qianli Ma, Shengyuan Ding, Jinhui Yin, Kai Chen, Hongjie Zhang</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> With the rapid advancement of vision-language models, an increasing number of studies have explored their potential for SVG generation tasks. Although existing approaches improve performance by constructing large-scale SVG datasets and introducing SVG-specific tokens, they still suffer from limited generalization, redundant paths in code outputs, and a lack of explicit reasoning. In this work, we present CTRL-S (Chain-of-Thought Reinforcement Learning for SVG), a unified framework that introduces a chain-of-thought mechanism to explicitly expose the model's reasoning process during SVG generation. To support this structured reasoning, we construct SVG-Sophia, a high-quality dataset containing 145K samples across SVG code refinement, Text-to-SVG, and Image-to-SVG tasks. By training the model to generate group-level structured SVG code, CTRL-S significantly improves structural coherence and visual fidelity. Furthermore, we adopt the GRPO algorithm and design a multi-reward optimization framework, incorporating DINO, image-text similarity, format, and code efficiency rewards. Through joint multi-reward optimization and multi-task training, our approach systematically enhances overall generation capabilities. Extensive experiments show that CTRL-S outperforms existing methods, achieving higher task success rates, superior SVG code quality, and exceptional visual fidelity.</p> - https://arxiv.org/abs/2603.16189 - Tue, 17 Mar 2026 07:16:30 +0000 + VP-VLA: Visual Prompting as an Interface for Vision-Language-Action Models + https://arxiv.org/abs/2603.22003 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22003.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zixuan Wang, Yuxin Chen, Yuqi Liu, Jinhui Ye, Pengguang Chen, Changsheng Lu, Shu Liu, Jiaya Jia</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Vision-Language-Action (VLA) models typically map visual observations and linguistic instructions directly to robotic control signals. This "black-box" mapping forces a single forward pass to simultaneously handle instruction interpretation, spatial grounding, and low-level control, often leading to poor spatial precision and limited robustness in out-of-distribution scenarios. To address these limitations, we propose VP-VLA, a dual-system framework that decouples high-level reasoning and low-level execution via a structured visual prompting interface. Specifically, a "System 2 Planner" decomposes complex instructions into sub-tasks and identifies relevant target objects and goal locations. These spatial anchors are then overlaid directly onto visual observations as structured visual prompts, such as crosshairs and bounding boxes. Guided by these prompts and enhanced by a novel auxiliary visual grounding objective during training, a "System 1 Controller" reliably generates precise low-level execution motions. Experiments on the Robocasa-GR1-Tabletop benchmark and SimplerEnv simulation demonstrate that VP-VLA improves success rates by 5% and 8.3%, surpassing competitive baselines including QwenOFT and GR00T-N1.6.</p> + https://arxiv.org/abs/2603.22003 + Mon, 23 Mar 2026 14:08:58 +0000 - Omnilingual MT: Machine Translation for 1,600 Languages - https://arxiv.org/abs/2603.16309 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16309.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Omnilingual MT Team, Belen Alastruey, Niyati Bafna, Andrea Caciolai, Kevin Heffernan, Artyom Kozhevnikov, Christophe Ropers, Eduardo Sánchez, Charles-Eric Saint-James, Ioannis Tsiamas, Chierh Cheng, Joe Chuang, Paul-Ambroise Duquenne, Mark Duppenthaler, Nate Ekberg, Cynthia Gao, Pere Lluís Huguet Cabot, João Maria Janeiro, Jean Maillard, Gabriel Mejia Gonzalez, Holger Schwenk, Edan Toledo, Arina Turkatenko, Albert Ventayol-Boada, Rashel Moritz, Alexandre Mourachko, Surya Parimi, Mary Williamson, Shireen Yates, David Dale, Marta R. Costa-jussà</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> High-quality machine translation (MT) can scale to hundreds of languages, setting a high bar for multilingual systems. However, compared to the world's 7,000 languages, current systems still offer only limited coverage: about 200 languages on the target side, and maybe a few hundreds more on the source side, supported due to cross-lingual transfer. And even these numbers have been hard to evaluate due to the lack of reliable benchmarks and metrics. We present Omnilingual Machine Translation (OMT), the first MT system supporting more than 1,600 languages. This scale is enabled by a comprehensive data strategy that integrates large public multilingual corpora with newly created datasets, including manually curated MeDLEY bitext. We explore two ways of specializing a Large Language model (LLM) for machine translation: as a decoder-only model (OMT-LLaMA) or as a module in an encoder-decoder architecture (OMT-NLLB). Notably, all our 1B to 8B parameter models match or exceed the MT performance of a 70B LLM baseline, revealing a clear specialization advantage and enabling strong translation quality in low-compute settings. Moreover, our evaluation of English-to-1,600 translations further shows that while baseline models can interpret undersupported languages, they frequently fail to generate them with meaningful fidelity; OMT-LLaMA models substantially expand the set of languages for which coherent generation is feasible. Additionally, OMT models improve in cross-lingual transfer, being close to solving the "understanding" part of the puzzle in MT for the 1,600 evaluated. Our leaderboard and main human-created evaluation datasets (BOUQuET and Met-BOUQuET) are dynamically evolving towards Omnilinguality and freely available.</p> - https://arxiv.org/abs/2603.16309 - Tue, 17 Mar 2026 09:43:42 +0000 + SpatialBoost: Enhancing Visual Representation through Language-Guided Reasoning + https://arxiv.org/abs/2603.22057 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22057.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Byungwoo Jeon, Dongyoung Kim, Huiwon Jang, Insoo Kim, Jinwoo Shin</p><p><b>Upvotes:</b> 44</p><p><b>Summary:</b> Despite the remarkable success of large-scale pre-trained image representation models (i.e., vision encoders) across various vision tasks, they are predominantly trained on 2D image data and therefore often fail to capture 3D spatial relationships between objects and backgrounds in the real world, constraining their effectiveness in many downstream applications. To address this, we propose SpatialBoost, a scalable framework that enhances the spatial awareness of existing pre-trained vision encoders by injecting 3D spatial knowledge expressed in linguistic descriptions. The core idea involves converting dense 3D spatial information from 2D images into linguistic expressions, which is then used to inject such spatial knowledge into vision encoders through a Large Language Model (LLM). To this end, we adopt a multi-turn Chain-of-Thought (CoT) reasoning process that progressively incorporates dense spatial knowledge and builds hierarchical spatial understanding. To validate effectiveness, we adapt SpatialBoost to state-of-the-art vision encoders such as DINOv3, and evaluate its performance gains on a wide range of benchmarks requiring both 3D perception and general vision abilities. For instance, SpatialBoost improves DINOv3 performance from 55.9 to 59.7 mIoU on ADE20K, achieving state-of-the-art performance with 3.8% gain over the pre-trained DINOv3.</p> + https://arxiv.org/abs/2603.22057 + Mon, 23 Mar 2026 14:54:34 +0000 - TRUST-SQL: Tool-Integrated Multi-Turn Reinforcement Learning for Text-to-SQL over Unknown Schemas - https://arxiv.org/abs/2603.16448 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16448.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ai Jian, Xiaoyun Zhang, Wanrou Du, Jingqing Ruan, Jiangbo Pei, Weipeng Zhang, Ke Zeng, Xunliang Cai</p><p><b>Upvotes:</b> 54</p><p><b>Summary:</b> Text-to-SQL parsing has achieved remarkable progress under the Full Schema Assumption. However, this premise fails in real-world enterprise environments where databases contain hundreds of tables with massive noisy metadata. Rather than injecting the full schema upfront, an agent must actively identify and verify only the relevant subset, giving rise to the Unknown Schema scenario we study in this work. To address this, we propose TRUST-SQL (Truthful Reasoning with Unknown Schema via Tools). We formulate the task as a Partially Observable Markov Decision Process where our autonomous agent employs a structured four-phase protocol to ground reasoning in verified metadata. Crucially, this protocol provides a structural boundary for our novel Dual-Track GRPO strategy. By applying token-level masked advantages, this strategy isolates exploration rewards from execution outcomes to resolve credit assignment, yielding a 9.9% relative improvement over standard GRPO. Extensive experiments across five benchmarks demonstrate that TRUST-SQL achieves an average absolute improvement of 30.6% and 16.6% for the 4B and 8B variants respectively over their base models. Remarkably, despite operating entirely without pre-loaded metadata, our framework consistently matches or surpasses strong baselines that rely on schema prefilling.</p> - https://arxiv.org/abs/2603.16448 - Tue, 17 Mar 2026 12:30:42 +0000 + On the Direction of RLVR Updates for LLM Reasoning: Identification and Exploitation + https://arxiv.org/abs/2603.22117 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22117.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kexin Huang, Haoming Meng, Junkang Wu, Jinda Lu, Chiyu Ma, Ziqian Chen, Xue Wang, Bolin Ding, Jiancan Wu, Xiang Wang, Xiangnan He, Guoyin Wang, Jingren Zhou</p><p><b>Upvotes:</b> 26</p><p><b>Summary:</b> Reinforcement learning with verifiable rewards (RLVR) has substantially improved the reasoning capabilities of large language models. While existing analyses identify that RLVR-induced changes are sparse, they primarily focus on the magnitude of these updates, largely overlooking their direction. In this work, we argue that the direction of updates is a more critical lens for understanding RLVR's effects, which can be captured by the signed, token-level log probability difference Δlog p between the base and final RLVR models. Through statistical analysis and token-replacement interventions, we demonstrate that Δlog p more effectively identifies sparse, yet reasoning-critical updates than magnitude-based metrics (\eg divergence or entropy). Building on this insight, we propose two practical applications: (1) a test-time extrapolation method that amplifies the policy along the learned Δlog p direction to improve reasoning accuracy without further training; (2) a training-time reweighting method that focuses learning on low-probability (corresponding to higher Δlog p) tokens, which improves reasoning performance across models and benchmarks. Our work establishes the direction of change as a key principle for analyzing and improving RLVR.</p> + https://arxiv.org/abs/2603.22117 + Mon, 23 Mar 2026 15:42:24 +0000 - AdaMem: Adaptive User-Centric Memory for Long-Horizon Dialogue Agents - https://arxiv.org/abs/2603.16496 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16496.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shannan Yan, Jingchen Ni, Leqi Zheng, Jiajun Zhang, Peixi Wu, Dacheng Yin, Jing Lyu, Chun Yuan, Fengyun Rao</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Large language model (LLM) agents increasingly rely on external memory to support long-horizon interaction, personalized assistance, and multi-step reasoning. However, existing memory systems still face three core challenges: they often rely too heavily on semantic similarity, which can miss evidence crucial for user-centric understanding; they frequently store related experiences as isolated fragments, weakening temporal and causal coherence; and they typically use static memory granularities that do not adapt well to the requirements of different questions. We propose AdaMem, an adaptive user-centric memory framework for long-horizon dialogue agents. AdaMem organizes dialogue history into working, episodic, persona, and graph memories, enabling the system to preserve recent context, structured long-term experiences, stable user traits, and relation-aware connections within a unified framework. At inference time, AdaMem first resolves the target participant, then builds a question-conditioned retrieval route that combines semantic retrieval with relation-aware graph expansion only when needed, and finally produces the answer through a role-specialized pipeline for evidence synthesis and response generation. We evaluate AdaMem on the LoCoMo and PERSONAMEM benchmarks for long-horizon reasoning and user modeling. Experimental results show that AdaMem achieves state-of-the-art performance on both benchmarks. The code will be released upon acceptance.</p> - https://arxiv.org/abs/2603.16496 - Tue, 17 Mar 2026 13:22:54 +0000 + StreamingClaw Technical Report + https://arxiv.org/abs/2603.22120 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22120.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiawei Chen, Zhe Chen, Chaoqun Du, Maokui He, Wei He, Hengtao Li, Qizhen Li, Zide Liu, Hao Ma, Xuhao Pan, Chang Ren, Xudong Rao, Xintian Shen, Chenfeng Wang, Tao Wei, Chengjun Yu, Pengfei Yu, Shengyu Yao, Chunpeng Zhou, Kun Zhan, Lihao Zheng, Pan Zhou, Xuhan Zhu, Yufei Zheng</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Applications such as embodied intelligence rely on a real-time perception-decision-action closed loop, posing stringent challenges for streaming video understanding. However, current agents suffer from fragmented capabilities, such as supporting only offline video understanding, lacking long-term multimodal memory mechanisms, or struggling to achieve real-time reasoning and proactive interaction under streaming inputs. These shortcomings have become a key bottleneck for preventing them from sustaining perception, making real-time decisions, and executing actions in real-world environments. To alleviate these issues, we propose StreamingClaw, a unified agent framework for streaming video understanding and embodied intelligence. It is also an OpenClaw-compatible framework that supports real-time, multimodal streaming interaction. StreamingClaw integrates five core capabilities: (1) It supports real-time streaming reasoning. (2) It supports reasoning about future events and proactive interaction under the online evolution of interaction objectives. (3) It supports multimodal long-term storage, hierarchical evolution, and efficient retrieval of shared memory across multiple agents. (4) It supports a closed-loop of perception-decision-action. In addition to conventional tools and skills, it also provides streaming tools and action-centric skills tailored for real-world physical environments. (5) It is compatible with the OpenClaw framework, allowing it to fully leverage the resources and support of the open-source community. With these designs, StreamingClaw integrates online real-time reasoning, multimodal long-term memory, and proactive interaction within a unified framework. Moreover, by translating decisions into executable actions, it enables direct control of the physical world, supporting practical deployment of embodied interaction.</p> + https://arxiv.org/abs/2603.22120 + Mon, 23 Mar 2026 15:43:52 +0000 - Conservative Offline Robot Policy Learning via Posterior-Transition Reweighting - https://arxiv.org/abs/2603.16542 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16542.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wanpeng Zhang, Hao Luo, Sipeng Zheng, Yicheng Feng, Haiweng Xu, Ziheng Xi, Chaoyi Xu, Haoqi Yuan, Zongqing Lu</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Offline post-training adapts a pretrained robot policy to a target dataset by supervised regression on recorded actions. In practice, robot datasets are heterogeneous: they mix embodiments, camera setups, and demonstrations of varying quality, so many trajectories reflect recovery behavior, inconsistent operator skill, or weakly informative supervision. Uniform post-training gives equal credit to all samples and can therefore average over conflicting or low-attribution data. We propose Posterior-Transition Reweighting (PTR), a reward-free and conservative post-training method that decides how much each training sample should influence the supervised update. For each sample, PTR encodes the observed post-action consequence as a latent target, inserts it into a candidate pool of mismatched targets, and uses a separate transition scorer to estimate a softmax identification posterior over target indices. The posterior-to-uniform ratio defines the PTR score, which is converted into a clipped-and-mixed weight and applied to the original action objective through self-normalized weighted regression. This construction requires no tractable policy likelihood and is compatible with both diffusion and flow-matching action heads. Rather than uniformly trusting all recorded supervision, PTR reallocates credit according to how attributable each sample's post-action consequence is under the current representation, improving conservative offline adaptation to heterogeneous robot data.</p> - https://arxiv.org/abs/2603.16542 - Tue, 17 Mar 2026 14:05:35 +0000 + Omni-WorldBench: Towards a Comprehensive Interaction-Centric Evaluation for World Models + https://arxiv.org/abs/2603.22212 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22212.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Meiqi Wu, Zhixin Cai, Fufangchen Zhao, Xiaokun Feng, Rujing Dang, Bingze Song, Ruitian Tian, Jiashu Zhu, Jiachen Lei, Hao Dou, Jing Tang, Lei Sun, Jiahong Wu, Xiangxiang Chu, Zeming Liu, Kaiqi Huang</p><p><b>Upvotes:</b> 122</p><p><b>Summary:</b> Video--based world models have emerged along two dominant paradigms: video generation and 3D reconstruction. However, existing evaluation benchmarks either focus narrowly on visual fidelity and text--video alignment for generative models, or rely on static 3D reconstruction metrics that fundamentally neglect temporal dynamics. We argue that the future of world modeling lies in 4D generation, which jointly models spatial structure and temporal evolution. In this paradigm, the core capability is interactive response: the ability to faithfully reflect how interaction actions drive state transitions across space and time. Yet no existing benchmark systematically evaluates this critical dimension. To address this gap, we propose Omni--WorldBench, a comprehensive benchmark specifically designed to evaluate the interactive response capabilities of world models in 4D settings. Omni--WorldBench comprises two key components: Omni--WorldSuite, a systematic prompt suite spanning diverse interaction levels and scene types; and Omni--Metrics, an agent-based evaluation framework that quantifies world modeling capabilities by measuring the causal impact of interaction actions on both final outcomes and intermediate state evolution trajectories. We conduct extensive evaluations of 18 representative world models across multiple paradigms. Our analysis reveals critical limitations of current world models in interactive response, providing actionable insights for future research. Omni-WorldBench will be publicly released to foster progress in interactive 4D world modeling.</p> + https://arxiv.org/abs/2603.22212 + Mon, 23 Mar 2026 17:10:29 +0000 - BenchPreS: A Benchmark for Context-Aware Personalized Preference Selectivity of Persistent-Memory LLMs - https://arxiv.org/abs/2603.16557 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16557.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sangyeon Yoon, Sunkyoung Kim, Hyesoo Hong, Wonje Jeung, Yongil Kim, Wooseok Seo, Heuiyeen Yeen, Albert No</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> Large language models (LLMs) increasingly store user preferences in persistent memory to support personalization across interactions. However, in third-party communication settings governed by social and institutional norms, some user preferences may be inappropriate to apply. We introduce BenchPreS, which evaluates whether memory-based user preferences are appropriately applied or suppressed across communication contexts. Using two complementary metrics, Misapplication Rate (MR) and Appropriate Application Rate (AAR), we find even frontier LLMs struggle to apply preferences in a context-sensitive manner. Models with stronger preference adherence exhibit higher rates of over-application, and neither reasoning capability nor prompt-based defenses fully resolve this issue. These results suggest current LLMs treat personalized preferences as globally enforceable rules rather than as context-dependent normative signals.</p> - https://arxiv.org/abs/2603.16557 - Tue, 17 Mar 2026 14:19:05 +0000 + From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agents + https://arxiv.org/abs/2603.22386 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22386.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ling Yue, Kushal Raj Bhandari, Ching-Yun Ko, Dhaval Patel, Shuxin Lin, Nianjun Zhou, Jianxi Gao, Pin-Yu Chen, Shaowu Pan</p><p><b>Upvotes:</b> 53</p><p><b>Summary:</b> Large language model (LLM)-based systems are becoming increasingly popular for solving tasks by constructing executable workflows that interleave LLM calls, information retrieval, tool use, code execution, memory updates, and verification. This survey reviews recent methods for designing and optimizing such workflows, which we treat as agentic computation graphs (ACGs). We organize the literature based on when workflow structure is determined, where structure refers to which components or agents are present, how they depend on each other, and how information flows between them. This lens distinguishes static methods, which fix a reusable workflow scaffold before deployment, from dynamic methods, which select, generate, or revise the workflow for a particular run before or during execution. We further organize prior work along three dimensions: when structure is determined, what part of the workflow is optimized, and which evaluation signals guide optimization (e.g., task metrics, verifier signals, preferences, or trace-derived feedback). We also distinguish reusable workflow templates, run-specific realized graphs, and execution traces, separating reusable design choices from the structures actually deployed in a given run and from realized runtime behavior. Finally, we outline a structure-aware evaluation perspective that complements downstream task metrics with graph-level properties, execution cost, robustness, and structural variation across inputs. Our goal is to provide a clear vocabulary, a unified framework for positioning new methods, a more comparable view of existing body of literature, and a more reproducible evaluation standard for future work in workflow optimizations for LLM agents.</p> + https://arxiv.org/abs/2603.22386 + Mon, 23 Mar 2026 17:42:59 +0000 - When AI Navigates the Fog of War - https://arxiv.org/abs/2603.16642 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16642.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ming Li, Xirui Li, Tianyi Zhou</p><p><b>Upvotes:</b> 28</p><p><b>Summary:</b> Can AI reason about a war before its trajectory becomes historically obvious? Analyzing this capability is difficult because retrospective geopolitical prediction is heavily confounded by training-data leakage. We address this challenge through a temporally grounded case study of the early stages of the 2026 Middle East conflict, which unfolded after the training cutoff of current frontier models. We construct 11 critical temporal nodes, 42 node-specific verifiable questions, and 5 general exploratory questions, requiring models to reason only from information that would have been publicly available at each moment. This design substantially mitigates training-data leakage concerns, creating a setting well-suited for studying how models analyze an unfolding crisis under the fog of war, and provides, to our knowledge, the first temporally grounded analysis of LLM reasoning in an ongoing geopolitical conflict. Our analysis reveals three main findings. First, current state-of-the-art large language models often display a striking degree of strategic realism, reasoning beyond surface rhetoric toward deeper structural incentives. Second, this capability is uneven across domains: models are more reliable in economically and logistically structured settings than in politically ambiguous multi-actor environments. Finally, model narratives evolve over time, shifting from early expectations of rapid containment toward more systemic accounts of regional entrenchment and attritional de-escalation. Since the conflict remains ongoing at the time of writing, this work can serve as an archival snapshot of model reasoning during an unfolding geopolitical crisis, enabling future studies without the hindsight bias of retrospective analysis.</p> - https://arxiv.org/abs/2603.16642 - Tue, 17 Mar 2026 15:13:10 +0000 + Repurposing Geometric Foundation Models for Multi-view Diffusion + https://arxiv.org/abs/2603.22275 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22275.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wooseok Jang, Seonghu Jeon, Jisang Han, Jinhyeok Choi, Minkyung Kwon, Seungryong Kim, Saining Xie, Sainan Liu</p><p><b>Upvotes:</b> 43</p><p><b>Summary:</b> While recent advances in generative latent spaces have driven substantial progress in single-image generation, the optimal latent space for novel view synthesis (NVS) remains largely unexplored. In particular, NVS requires geometrically consistent generation across viewpoints, but existing approaches typically operate in a view-independent VAE latent space. In this paper, we propose Geometric Latent Diffusion (GLD), a framework that repurposes the geometrically consistent feature space of geometric foundation models as the latent space for multi-view diffusion. We show that these features not only support high-fidelity RGB reconstruction but also encode strong cross-view geometric correspondences, providing a well-suited latent space for NVS. Our experiments demonstrate that GLD outperforms both VAE and RAE on 2D image quality and 3D consistency metrics, while accelerating training by more than 4.4x compared to the VAE latent space. Notably, GLD remains competitive with state-of-the-art methods that leverage large-scale text-to-image pretraining, despite training its diffusion model from scratch without such generative pretraining.</p> + https://arxiv.org/abs/2603.22275 + Mon, 23 Mar 2026 17:57:05 +0000 - Kinema4D: Kinematic 4D World Modeling for Spatiotemporal Embodied Simulation - https://arxiv.org/abs/2603.16669 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16669.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mutian Xu, Tianbao Zhang, Tianqi Liu, Zhaoxi Chen, Xiaoguang Han, Ziwei Liu</p><p><b>Upvotes:</b> 68</p><p><b>Summary:</b> Simulating robot-world interactions is a cornerstone of Embodied AI. Recently, a few works have shown promise in leveraging video generations to transcend the rigid visual/physical constraints of traditional simulators. However, they primarily operate in 2D space or are guided by static environmental cues, ignoring the fundamental reality that robot-world interactions are inherently 4D spatiotemporal events that require precise interactive modeling. To restore this 4D essence while ensuring the precise robot control, we introduce Kinema4D, a new action-conditioned 4D generative robotic simulator that disentangles the robot-world interaction into: i) Precise 4D representation of robot controls: we drive a URDF-based 3D robot via kinematics, producing a precise 4D robot control trajectory. ii) Generative 4D modeling of environmental reactions: we project the 4D robot trajectory into a pointmap as a spatiotemporal visual signal, controlling the generative model to synthesize complex environments' reactive dynamics into synchronized RGB/pointmap sequences. To facilitate training, we curated a large-scale dataset called Robo4D-200k, comprising 201,426 robot interaction episodes with high-quality 4D annotations. Extensive experiments demonstrate that our method effectively simulates physically-plausible, geometry-consistent, and embodiment-agnostic interactions that faithfully mirror diverse real-world dynamics. For the first time, it shows potential zero-shot transfer capability, providing a high-fidelity foundation for advancing next-generation embodied simulation.</p> - https://arxiv.org/abs/2603.16669 - Tue, 17 Mar 2026 15:36:38 +0000 + Scaling DoRA: High-Rank Adaptation via Factored Norms and Fused Kernels + https://arxiv.org/abs/2603.22276 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22276.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Alexandra Zelenin, Alexandra Zhuravlyova</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Weight-Decomposed Low-Rank Adaptation (DoRA) extends LoRA by decoupling weight magnitude from direction, but its forward pass requires the row-wise norm of W + sBA, a computation that every major framework we surveyed implements by materializing the dense [d_out, d_in] product BA. At d_in = 8192 and rank r = 384, a single module's norm requires about 512 MB of transient working memory in bf16, making high-rank DoRA costly and often infeasible on common single-GPU setups once hundreds of adapted modules and checkpointing are involved. We present two systems contributions. A factored norm decomposes the squared norm into base, cross, and Gram terms computable through O(d_out r + r^2) intermediates, eliminating the dense product. Fused Triton kernels collapse the four-kernel DoRA composition into a single pass, reducing memory traffic by about 4x and using a numerically stable form that avoids catastrophic cancellation in the near-unity rescaling regime where magnitude scales concentrate in practice. Across six 8-32B vision-language models (VLMs) on three NVIDIA GPUs (RTX 6000 PRO, H200, B200) at r = 384 in bf16, the fused implementation is 1.5-2.0x faster than Hugging Face PEFT's DoRA implementation for inference and 1.5-1.9x faster for gradient computation (optimizer step excluded), with up to 7 GB lower peak VRAM. Microbenchmarks on six GPUs spanning four architecture generations (L40S, A100, RTX 6000 PRO, H200, B200, B300) confirm 1.5-2.7x compose-kernel speedup. Final-logit cosine similarity exceeds 0.9999 across all model/GPU pairs, and multi-seed training curves match within 7.1 x 10^-4 mean per-step loss delta over 2000 steps.</p> + https://arxiv.org/abs/2603.22276 + Mon, 23 Mar 2026 17:57:24 +0000 - InCoder-32B: Code Foundation Model for Industrial Scenarios - https://arxiv.org/abs/2603.16790 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16790.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jian Yang, Wei Zhang, Jiajun Wu, Junhang Cheng, Shawn Guo, Haowen Wang, Weicheng Gu, Yaxin Du, Joseph Li, Fanglin Xu, Yizhi Li, Lin Jing, Yuanbo Wang, Yuhan Gao, Ruihao Gong, Chuan Hao, Ran Tao, Aishan Liu, Tuney Zheng, Ganqu Cui, Zhoujun Li, Mingjie Tang, Chenghua Lin, Wayne Xin Zhao, Xianglong Liu, Ming Zhou, Bryan Dai, Weifeng Lv</p><p><b>Upvotes:</b> 291</p><p><b>Summary:</b> Recent code large language models have achieved remarkable progress on general programming tasks. Nevertheless, their performance degrades significantly in industrial scenarios that require reasoning about hardware semantics, specialized language constructs, and strict resource constraints. To address these challenges, we introduce InCoder-32B (Industrial-Coder-32B), the first 32B-parameter code foundation model unifying code intelligence across chip design, GPU kernel optimization, embedded systems, compiler optimization, and 3D modeling. By adopting an efficient architecture, we train InCoder-32B from scratch with general code pre-training, curated industrial code annealing, mid-training that progressively extends context from 8K to 128K tokens with synthetic industrial reasoning data, and post-training with execution-grounded verification. We conduct extensive evaluation on 14 mainstream general code benchmarks and 9 industrial benchmarks spanning 4 specialized domains. Results show InCoder-32B achieves highly competitive performance on general tasks while establishing strong open-source baselines across industrial domains.</p> - https://arxiv.org/abs/2603.16790 - Tue, 17 Mar 2026 17:01:35 +0000 + ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Model + https://arxiv.org/abs/2603.22281 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22281.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haichao Zhang, Yijiang Li, Shwai He, Tushar Nagarajan, Mingfei Chen, Jianglin Lu, Ang Li, Yun Fu</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Recent progress in latent world models (e.g., V-JEPA2) has shown promising capability in forecasting future world states from video observations. Nevertheless, dense prediction from a short observation window limits temporal context and can bias predictors toward local, low-level extrapolation, making it difficult to capture long-horizon semantics and reducing downstream utility. Vision--language models (VLMs), in contrast, provide strong semantic grounding and general knowledge by reasoning over uniformly sampled frames, but they are not ideal as standalone dense predictors due to compute-driven sparse sampling, a language-output bottleneck that compresses fine-grained interaction states into text-oriented representations, and a data-regime mismatch when adapting to small action-conditioned datasets. We propose a VLM-guided JEPA-style latent world modeling framework that combines dense-frame dynamics modeling with long-horizon semantic guidance via a dual-temporal pathway: a dense JEPA branch for fine-grained motion and interaction cues, and a uniformly sampled VLM thinker branch with a larger temporal stride for knowledge-rich guidance. To transfer the VLM's progressive reasoning signals effectively, we introduce a hierarchical pyramid representation extraction module that aggregates multi-layer VLM representations into guidance features compatible with latent prediction. Experiments on hand-manipulation trajectory prediction show that our method outperforms both a strong VLM-only baseline and a JEPA-predictor baseline, and yields more robust long-horizon rollout behavior.</p> + https://arxiv.org/abs/2603.22281 + Mon, 23 Mar 2026 17:59:42 +0000 - M^3: Dense Matching Meets Multi-View Foundation Models for Monocular Gaussian Splatting SLAM - https://arxiv.org/abs/2603.16844 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16844.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kerui Ren, Guanghao Li, Changjian Jiang, Yingxiang Xu, Tao Lu, Linning Xu, Junting Dong, Jiangmiao Pang, Mulin Yu, Bo Dai</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Streaming reconstruction from uncalibrated monocular video remains challenging, as it requires both high-precision pose estimation and computationally efficient online refinement in dynamic environments. While coupling 3D foundation models with SLAM frameworks is a promising paradigm, a critical bottleneck persists: most multi-view foundation models estimate poses in a feed-forward manner, yielding pixel-level correspondences that lack the requisite precision for rigorous geometric optimization. To address this, we present M^3, which augments the Multi-view foundation model with a dedicated Matching head to facilitate fine-grained dense correspondences and integrates it into a robust Monocular Gaussian Splatting SLAM. M^3 further enhances tracking stability by incorporating dynamic area suppression and cross-inference intrinsic alignment. Extensive experiments on diverse indoor and outdoor benchmarks demonstrate state-of-the-art accuracy in both pose estimation and scene reconstruction. Notably, M^3 reduces ATE RMSE by 64.3% compared to VGGT-SLAM 2.0 and outperforms ARTDECO by 2.11 dB in PSNR on the ScanNet++ dataset.</p> - https://arxiv.org/abs/2603.16844 - Tue, 17 Mar 2026 17:52:37 +0000 + VideoDetective: Clue Hunting via both Extrinsic Query and Intrinsic Relevance for Long Video Understanding + https://arxiv.org/abs/2603.22285 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22285.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ruoliu Yang, Chu Wu, Caifeng Shan, Ran He, Chaoyou Fu</p><p><b>Upvotes:</b> 50</p><p><b>Summary:</b> Long video understanding remains challenging for multimodal large language models (MLLMs) due to limited context windows, which necessitate identifying sparse query-relevant video segments. However, existing methods predominantly localize clues based solely on the query, overlooking the video's intrinsic structure and varying relevance across segments. To address this, we propose VideoDetective, a framework that integrates query-to-segment relevance and inter-segment affinity for effective clue hunting in long-video question answering. Specifically, we divide a video into various segments and represent them as a visual-temporal affinity graph built from visual similarity and temporal proximity. We then perform a Hypothesis-Verification-Refinement loop to estimate relevance scores of observed segments to the query and propagate them to unseen segments, yielding a global relevance distribution that guides the localization of the most critical segments for final answering with sparse observation. Experiments show our method consistently achieves substantial gains across a wide range of mainstream MLLMs on representative benchmarks, with accuracy improvements of up to 7.5% on VideoMME-long. Our code is available at https://videodetective.github.io/</p> + https://arxiv.org/abs/2603.22285 + Mon, 23 Mar 2026 17:59:51 +0000 - Online Experiential Learning for Language Models - https://arxiv.org/abs/2603.16856 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16856.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tianzhu Ye, Li Dong, Qingxiu Dong, Xun Wu, Shaohan Huang, Furu Wei</p><p><b>Upvotes:</b> 52</p><p><b>Summary:</b> The prevailing paradigm for improving large language models relies on offline training with human annotations or simulated environments, leaving the rich experience accumulated during real-world deployment entirely unexploited. We propose Online Experiential Learning (OEL), a framework that enables language models to continuously improve from their own deployment experience. OEL operates in two stages: first, transferable experiential knowledge is extracted and accumulated from interaction trajectories collected on the user side; second, this knowledge is consolidated into model parameters via on-policy context distillation, requiring no access to the user-side environment. The two stages are iterated to form an online learning loop, where the improved model collects higher-quality trajectories that yield richer experiential knowledge for subsequent rounds. We evaluate OEL on text-based game environments across multiple model scales and both thinking and non-thinking variants. OEL achieves consistent improvements over successive iterations, enhancing both task accuracy and token efficiency while preserving out-of-distribution performance. Our analysis further shows that extracted experiential knowledge is significantly more effective than raw trajectories, and that on-policy consistency between the knowledge source and the policy model is critical for effective learning.</p> - https://arxiv.org/abs/2603.16856 - Tue, 17 Mar 2026 17:57:49 +0000 + Sparse but Critical: A Token-Level Analysis of Distributional Shifts in RLVR Fine-Tuning of LLMs + https://arxiv.org/abs/2603.22446 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22446.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haoming Meng, Kexin Huang, Shaohang Wei, Chiyu Ma, Shuo Yang, Xue Wang, Guoyin Wang, Bolin Ding, Jingren Zhou</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Reinforcement learning with verifiable rewards (RLVR) has significantly improved reasoning in large language models (LLMs), yet the token-level mechanisms underlying these improvements remain unclear. We present a systematic empirical study of RLVR's distributional effects organized around three main analyses: (1) token-level characterization of distributional shifts between base and RL models, (2) the impact of token-level distributional shifts on sequence-level reasoning performance through cross-sampling interventions, and (3) fine-grained mechanics of these shifts at the token level. We find that RL fine-tuning induces highly sparse and targeted changes, with only a small fraction of token distributions exhibiting meaningful divergence between the base and RL policies. We further characterize the structure and evolution of these shifts through analyses of token entropy, positional concentration, and reallocation of probability mass. To assess the functional importance of these sparse changes, we conduct cross-sampling experiments that selectively swap token choices between the base and RL models with varying intervention budgets. We show that inserting only a small fraction of RL-sampled tokens into base generations progressively recovers RL performance gains, while injecting a similarly small number of base token choices into otherwise RL-generated sequences collapses performance to base levels, isolating a small set of token-level decisions directly responsible for RLVR's performance gains. Finally, we explore divergence-weighted variants of the advantage signal as a diagnostic intervention, finding that they can yield improvements over baselines. Together, our results shed light on the distributional changes induced by RLVR and provide a fine-grained, token-level lens for understanding RLVR fine-tuning as a targeted refinement process.</p> + https://arxiv.org/abs/2603.22446 + Mon, 23 Mar 2026 18:17:15 +0000 - SocialOmni: Benchmarking Audio-Visual Social Interactivity in Omni Models - https://arxiv.org/abs/2603.16859 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16859.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tianyu Xie, Jinfa Huang, Yuexiao Ma, Rongfang Luo, Yan Yang, Wang Chen, Yuhui Zeng, Ruize Fang, Yixuan Zou, Xiawu Zheng, Jiebo Luo, Rongrong Ji</p><p><b>Upvotes:</b> 240</p><p><b>Summary:</b> Omni-modal large language models (OLMs) redefine human-machine interaction by natively integrating audio, vision, and text. However, existing OLM benchmarks remain anchored to static, accuracy-centric tasks, leaving a critical gap in assessing social interactivity, the fundamental capacity to navigate dynamic cues in natural dialogues. To this end, we propose SocialOmni, a comprehensive benchmark that operationalizes the evaluation of this conversational interactivity across three core dimensions: (i) speaker separation and identification (who is speaking), (ii) interruption timing control (when to interject), and (iii) natural interruption generation (how to phrase the interruption). SocialOmni features 2,000 perception samples and a quality-controlled diagnostic set of 209 interaction-generation instances with strict temporal and contextual constraints, complemented by controlled audio-visual inconsistency scenarios to test model robustness. We benchmarked 12 leading OLMs, which uncovers significant variance in their social-interaction capabilities across models. Furthermore, our analysis reveals a pronounced decoupling between a model's perceptual accuracy and its ability to generate contextually appropriate interruptions, indicating that understanding-centric metrics alone are insufficient to characterize conversational social competence. More encouragingly, these diagnostics from SocialOmni yield actionable signals for bridging the perception-interaction divide in future OLMs.</p> - https://arxiv.org/abs/2603.16859 - Tue, 17 Mar 2026 17:58:44 +0000 + MinerU-Diffusion: Rethinking Document OCR as Inverse Rendering via Diffusion Decoding + https://arxiv.org/abs/2603.22458 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22458.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hejun Dong, Junbo Niu, Bin Wang, Weijun Zeng, Wentao Zhang, Conghui He</p><p><b>Upvotes:</b> 130</p><p><b>Summary:</b> Optical character recognition (OCR) has evolved from line-level transcription to structured document parsing, requiring models to recover long-form sequences containing layout, tables, and formulas. Despite recent advances in vision-language models, most existing systems rely on autoregressive decoding, which introduces sequential latency and amplifies error propagation in long documents. In this work, we revisit document OCR from an inverse rendering perspective, arguing that left-to-right causal generation is an artifact of serialization rather than an intrinsic property of the task. Motivated by this insight, we propose MinerU-Diffusion, a unified diffusion-based framework that replaces autoregressive sequential decoding with parallel diffusion denoising under visual conditioning. MinerU-Diffusion employs a block-wise diffusion decoder and an uncertainty-driven curriculum learning strategy to enable stable training and efficient long-sequence inference. Extensive experiments demonstrate that MinerU-Diffusion consistently improves robustness while achieving up to 3.2x faster decoding compared to autoregressive baselines. Evaluations on the proposed Semantic Shuffle benchmark further confirm its reduced dependence on linguistic priors and stronger visual OCR capability.</p> + https://arxiv.org/abs/2603.22458 + Mon, 23 Mar 2026 18:25:17 +0000 - SparkVSR: Interactive Video Super-Resolution via Sparse Keyframe Propagation - https://arxiv.org/abs/2603.16864 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16864.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiongze Yu, Xiangbo Gao, Pooja Verlani, Akshay Gadde, Yilin Wang, Balu Adsumilli, Zhengzhong Tu</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Video Super-Resolution (VSR) aims to restore high-quality video frames from low-resolution (LR) estimates, yet most existing VSR approaches behave like black boxes at inference time: users cannot reliably correct unexpected artifacts, but instead can only accept whatever the model produces. In this paper, we propose a novel interactive VSR framework dubbed SparkVSR that makes sparse keyframes a simple and expressive control signal. Specifically, users can first super-resolve or optionally a small set of keyframes using any off-the-shelf image super-resolution (ISR) model, then SparkVSR propagates the keyframe priors to the entire video sequence while remaining grounded by the original LR video motion. Concretely, we introduce a keyframe-conditioned latent-pixel two-stage training pipeline that fuses LR video latents with sparsely encoded HR keyframe latents to learn robust cross-space propagation and refine perceptual details. At inference time, SparkVSR supports flexible keyframe selection (manual specification, codec I-frame extraction, or random sampling) and a reference-free guidance mechanism that continuously balances keyframe adherence and blind restoration, ensuring robust performance even when reference keyframes are absent or imperfect. Experiments on multiple VSR benchmarks demonstrate improved temporal consistency and strong restoration quality, surpassing baselines by up to 24.6%, 21.8%, and 5.6% on CLIP-IQA, DOVER, and MUSIQ, respectively, enabling controllable, keyframe-driven video super-resolution. Moreover, we demonstrate that SparkVSR is a generic interactive, keyframe-conditioned video processing framework as it can be applied out of the box to unseen tasks such as old-film restoration and video style transfer. Our project page is available at: https://sparkvsr.github.io/</p> - https://arxiv.org/abs/2603.16864 - Tue, 17 Mar 2026 17:59:30 +0000 + Ego2Web: A Web Agent Benchmark Grounded in Egocentric Videos + https://arxiv.org/abs/2603.22529 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22529.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shoubin Yu, Lei Shu, Antoine Yang, Yao Fu, Srinivas Sunkara, Maria Wang, Jindong Chen, Mohit Bansal, Boqing Gong</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Multimodal AI agents are increasingly automating complex real-world workflows that involve online web execution. However, current web-agent benchmarks suffer from a critical limitation: they focus entirely on web-based interaction and perception, lacking grounding in the user's real-world physical surroundings. This limitation prevents evaluation in crucial scenarios, such as when an agent must use egocentric visual perception (e.g., via AR glasses) to recognize an object in the user's surroundings and then complete a related task online. To address this gap, we introduce Ego2Web, the first benchmark designed to bridge egocentric video perception and web agent execution. Ego2Web pairs real-world first-person video recordings with web tasks that require visual understanding, web task planning, and interaction in an online environment for successful completion. We utilize an automatic data-generation pipeline combined with human verification and refinement to curate well-constructed, high-quality video-task pairs across diverse web task types, including e-commerce, media retrieval, knowledge lookup, etc. To facilitate accurate and scalable evaluation for our benchmark, we also develop a novel LLM-as-a-Judge automatic evaluation method, Ego2WebJudge, which achieves approximately 84% agreement with human judgment, substantially higher than existing evaluation methods. Experiments with diverse SoTA agents on our Ego2Web show that their performance is weak, with substantial headroom across all task categories. We also conduct a comprehensive ablation study on task design, highlighting the necessity of accurate video understanding in the proposed task and the limitations of current agents. We hope Ego2Web can be a critical new resource for developing truly capable AI assistants that can seamlessly see, understand, and act across the physical and digital worlds.</p> + https://arxiv.org/abs/2603.22529 + Mon, 23 Mar 2026 19:47:58 +0000 - SegviGen: Repurposing 3D Generative Model for Part Segmentation - https://arxiv.org/abs/2603.16869 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16869.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lin Li, Haoran Feng, Zehuan Huang, Haohua Chen, Wenbo Nie, Shaohua Hou, Keqing Fan, Pan Hu, Sheng Wang, Buyu Li, Lu Sheng</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> We introduce SegviGen, a framework that repurposes native 3D generative models for 3D part segmentation. Existing pipelines either lift strong 2D priors into 3D via distillation or multi-view mask aggregation, often suffering from cross-view inconsistency and blurred boundaries, or explore native 3D discriminative segmentation, which typically requires large-scale annotated 3D data and substantial training resources. In contrast, SegviGen leverages the structured priors encoded in pretrained 3D generative model to induce segmentation through distinctive part colorization, establishing a novel and efficient framework for part segmentation. Specifically, SegviGen encodes a 3D asset and predicts part-indicative colors on active voxels of a geometry-aligned reconstruction. It supports interactive part segmentation, full segmentation, and full segmentation with 2D guidance in a unified framework. Extensive experiments show that SegviGen improves over the prior state of the art by 40% on interactive part segmentation and by 15% on full segmentation, while using only 0.32% of the labeled training data. It demonstrates that pretrained 3D generative priors transfer effectively to 3D part segmentation, enabling strong performance with limited supervision. See our project page at https://fenghora.github.io/SegviGen-Page/.</p> - https://arxiv.org/abs/2603.16869 - Tue, 17 Mar 2026 17:59:51 +0000 + CanViT: Toward Active-Vision Foundation Models + https://arxiv.org/abs/2603.22570 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22570.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yohaï-Eliel Berreby, Sabrina Du, Audrey Durand, B. Suresh Krishna</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Active computer vision promises efficient, biologically plausible perception through sequential, localized glimpses, but lacks scalable general-purpose architectures and pretraining pipelines. As a result, Active-Vision Foundation Models (AVFMs) have remained unexplored. We introduce CanViT, the first task- and policy-agnostic AVFM. CanViT uses scene-relative RoPE to bind a retinotopic Vision Transformer backbone and a spatiotopic scene-wide latent workspace, the canvas. Efficient interaction with this high-capacity working memory is supported by Canvas Attention, a novel asymmetric cross-attention mechanism. We decouple thinking (backbone-level) and memory (canvas-level), eliminating canvas-side self-attention and fully-connected layers to achieve low-latency sequential inference and scalability to large scenes. We propose a label-free active vision pretraining scheme, policy-agnostic passive-to-active dense latent distillation: reconstructing scene-wide DINOv3 embeddings from sequences of low-resolution glimpses with randomized locations, zoom levels, and lengths. We pretrain CanViT-B from a random initialization on 13.2 million ImageNet-21k scenes -- an order of magnitude more than previous active models -- and 1 billion random glimpses, in 166 hours on a single H100. On ADE20K segmentation, a frozen CanViT-B achieves 38.5% mIoU in a single low-resolution glimpse, outperforming the best active model's 27.6% with 19.5x fewer inference FLOPs and no fine-tuning, as well as its FLOP- or input-matched DINOv3 teacher. Given additional glimpses, CanViT-B reaches 45.9% ADE20K mIoU. On ImageNet-1k classification, CanViT-B reaches 81.2% top-1 accuracy with frozen teacher probes. CanViT generalizes to longer rollouts, larger scenes, and new policies. Our work closes the wide gap between passive and active vision on semantic segmentation and demonstrates the potential of AVFMs as a new research axis.</p> + https://arxiv.org/abs/2603.22570 + Mon, 23 Mar 2026 21:05:21 +0000 - Efficient Reasoning on the Edge - https://arxiv.org/abs/2603.16867 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16867.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yelysei Bondarenko, Thomas Hehn, Rob Hesselink, Romain Lepert, Fabio Valerio Massoli, Evgeny Mironov, Leyla Mirvakhabova, Tribhuvanesh Orekondy, Spyridon Stasis, Andrey Kuzmin, Anna Kuzina, Markus Nagel, Ankita Nayak, Corrado Rainone, Ork de Rooij, Paul N Whatmough, Arash Behboodi, Babak Ehteshami Bejnordi</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Large language models (LLMs) with chain-of-thought reasoning achieve state-of-the-art performance across complex problem-solving tasks, but their verbose reasoning traces and large context requirements make them impractical for edge deployment. These challenges include high token generation costs, large KV-cache footprints, and inefficiencies when distilling reasoning capabilities into smaller models for mobile devices. Existing approaches often rely on distilling reasoning traces from larger models into smaller models, which are verbose and stylistically redundant, undesirable for on-device inference. In this work, we propose a lightweight approach to enable reasoning in small LLMs using LoRA adapters combined with supervised fine-tuning. We further introduce budget forcing via reinforcement learning on these adapters, significantly reducing response length with minimal accuracy loss. To address memory-bound decoding, we exploit parallel test-time scaling, improving accuracy at minor latency increase. Finally, we present a dynamic adapter-switching mechanism that activates reasoning only when needed and a KV-cache sharing strategy during prompt encoding, reducing time-to-first-token for on-device inference. Experiments on Qwen2.5-7B demonstrate that our method achieves efficient, accurate reasoning under strict resource constraints, making LLM reasoning practical for mobile scenarios. Videos demonstrating our solution running on mobile devices are available on our project page.</p> - https://arxiv.org/abs/2603.16867 - Tue, 17 Mar 2026 17:59:51 +0000 + TrajLoom: Dense Future Trajectory Generation from Video + https://arxiv.org/abs/2603.22606 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22606.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zewei Zhang, Jia Jun Cheng Xian, Kaiwen Liu, Ming Liang, Hang Chu, Jun Chen, Renjie Liao</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Predicting future motion is crucial in video understanding and controllable video generation. Dense point trajectories are a compact, expressive motion representation, but modeling their future evolution from observed video remains challenging. We propose a framework that predicts future trajectories and visibility from past trajectories and video context. Our method has three components: (1) Grid-Anchor Offset Encoding, which reduces location-dependent bias by representing each point as an offset from its pixel-center anchor; (2) TrajLoom-VAE, which learns a compact spatiotemporal latent space for dense trajectories with masked reconstruction and a spatiotemporal consistency regularizer; and (3) TrajLoom-Flow, which generates future trajectories in latent space via flow matching, with boundary cues and on-policy K-step fine-tuning for stable sampling. We also introduce TrajLoomBench, a unified benchmark spanning real and synthetic videos with a standardized setup aligned with video-generation benchmarks. Compared with state-of-the-art methods, our approach extends the prediction horizon from 24 to 81 frames while improving motion realism and stability across datasets. The predicted trajectories directly support downstream video generation and editing. Code, model checkpoints, and datasets are available at https://trajloom.github.io/.</p> + https://arxiv.org/abs/2603.22606 + Mon, 23 Mar 2026 22:10:58 +0000 - Demystifing Video Reasoning - https://arxiv.org/abs/2603.16870 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16870.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ruisi Wang, Zhongang Cai, Fanyi Pu, Junxiang Xu, Wanqi Yin, Maijunxian Wang, Ran Ji, Chenyang Gu, Bo Li, Ziqi Huang, Hokin Deng, Dahua Lin, Ziwei Liu, Lei Yang</p><p><b>Upvotes:</b> 348</p><p><b>Summary:</b> Recent advances in video generation have revealed an unexpected phenomenon: diffusion-based video models exhibit non-trivial reasoning capabilities. Prior work attributes this to a Chain-of-Frames (CoF) mechanism, where reasoning is assumed to unfold sequentially across video frames. In this work, we challenge this assumption and uncover a fundamentally different mechanism. We show that reasoning in video models instead primarily emerges along the diffusion denoising steps. Through qualitative analysis and targeted probing experiments, we find that models explore multiple candidate solutions in early denoising steps and progressively converge to a final answer, a process we term Chain-of-Steps (CoS). Beyond this core mechanism, we identify several emergent reasoning behaviors critical to model performance: (1) working memory, enabling persistent reference; (2) self-correction and enhancement, allowing recovery from incorrect intermediate solutions; and (3) perception before action, where early steps establish semantic grounding and later steps perform structured manipulation. During a diffusion step, we further uncover self-evolved functional specialization within Diffusion Transformers, where early layers encode dense perceptual structure, middle layers execute reasoning, and later layers consolidate latent representations. Motivated by these insights, we present a simple training-free strategy as a proof-of-concept, demonstrating how reasoning can be improved by ensembling latent trajectories from identical models with different random seeds. Overall, our work provides a systematic understanding of how reasoning emerges in video generation models, offering a foundation to guide future research in better exploiting the inherent reasoning dynamics of video models as a new substrate for intelligence.</p> - https://arxiv.org/abs/2603.16870 - Tue, 17 Mar 2026 17:59:55 +0000 + Rethinking Token-Level Policy Optimization for Multimodal Chain-of-Thought + https://arxiv.org/abs/2603.22847 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22847.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yunheng Li, Hangyi Kuang, Hengrui Zhang, Jiangxia Cao, Zhaojie Liu, Qibin Hou, Ming-Ming Cheng</p><p><b>Upvotes:</b> 24</p><p><b>Summary:</b> Multimodal Chain-of-Thought (CoT) reasoning requires large vision-language models to construct reasoning trajectories that interleave perceptual grounding with multi-step inference. However, existing Reinforcement Learning with Verifiable Rewards (RLVR) methods typically optimize reasoning at a coarse granularity, treating CoT uniformly without distinguishing their varying degrees of visual grounding. In this work, we conduct a token-level analysis of multimodal reasoning trajectories and show that successful reasoning is characterized by structured token dynamics reflecting both perceptual grounding and exploratory inference. Building upon this analysis, we propose Perception-Exploration Policy Optimization (PEPO), which derives a perception prior from hidden state similarity and integrates it with token entropy through a smooth gating mechanism to produce token-level advantages. PEPO integrates seamlessly with existing RLVR frameworks such as GRPO and DAPO, requiring neither additional supervision nor auxiliary branches. Extensive experiments across diverse multimodal benchmarks demonstrate consistent and robust improvements over strong RL baselines, spanning geometry reasoning, visual grounding, visual puzzle solving, and few-shot classification, while maintaining stable training dynamics. Code: https://github.com/xzxxntxdy/PEPO</p> + https://arxiv.org/abs/2603.22847 + Tue, 24 Mar 2026 06:38:00 +0000 - WorldCam: Interactive Autoregressive 3D Gaming Worlds with Camera Pose as a Unifying Geometric Representation - https://arxiv.org/abs/2603.16871 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16871.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jisu Nam, Yicong Hong, Chun-Hao Paul Huang, Feng Liu, JoungBin Lee, Jiyoung Kim, Siyoon Jin, Yunsung Lee, Jaeyoon Jung, Suhwan Choi, Seungryong Kim, Yang Zhou</p><p><b>Upvotes:</b> 58</p><p><b>Summary:</b> Recent advances in video diffusion transformers have enabled interactive gaming world models that allow users to explore generated environments over extended horizons. However, existing approaches struggle with precise action control and long-horizon 3D consistency. Most prior works treat user actions as abstract conditioning signals, overlooking the fundamental geometric coupling between actions and the 3D world, whereby actions induce relative camera motions that accumulate into a global camera pose within a 3D world. In this paper, we establish camera pose as a unifying geometric representation to jointly ground immediate action control and long-term 3D consistency. First, we define a physics-based continuous action space and represent user inputs in the Lie algebra to derive precise 6-DoF camera poses, which are injected into the generative model via a camera embedder to ensure accurate action alignment. Second, we use global camera poses as spatial indices to retrieve relevant past observations, enabling geometrically consistent revisiting of locations during long-horizon navigation. To support this research, we introduce a large-scale dataset comprising 3,000 minutes of authentic human gameplay annotated with camera trajectories and textual descriptions. Extensive experiments show that our approach substantially outperforms state-of-the-art interactive gaming world models in action controllability, long-horizon visual quality, and 3D spatial consistency.</p> - https://arxiv.org/abs/2603.16871 - Tue, 17 Mar 2026 17:59:56 +0000 + EVA: Efficient Reinforcement Learning for End-to-End Video Agent + https://arxiv.org/abs/2603.22918 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22918.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yaolun Zhang, Ruohui Wang, Jiahao Wang, Yepeng Tang, Xuanyu Zheng, Haonan Duan, Hao Lu, Hanming Deng, Lewei Lu</p><p><b>Upvotes:</b> 39</p><p><b>Summary:</b> Video understanding with multimodal large language models (MLLMs) remains challenging due to the long token sequences of videos, which contain extensive temporal dependencies and redundant frames. Existing approaches typically treat MLLMs as passive recognizers, processing entire videos or uniformly sampled frames without adaptive reasoning. Recent agent-based methods introduce external tools, yet still depend on manually designed workflows and perception-first strategies, resulting in inefficiency on long videos. We present EVA, an Efficient Reinforcement Learning framework for End-to-End Video Agent, which enables planning-before-perception through iterative summary-plan-action-reflection reasoning. EVA autonomously decides what to watch, when to watch, and how to watch, achieving query-driven and efficient video understanding. To train such agents, we design a simple yet effective three-stage learning pipeline - comprising supervised fine-tuning (SFT), Kahneman-Tversky Optimization (KTO), and Generalized Reward Policy Optimization (GRPO) - that bridges supervised imitation and reinforcement learning. We further construct high-quality datasets for each stage, supporting stable and reproducible training. We evaluate EVA on six video understanding benchmarks, demonstrating its comprehensive capabilities. Compared with existing baselines, EVA achieves a substantial improvement of 6-12% over general MLLM baselines and a further 1-3% gain over prior adaptive agent methods. Our code and model are available at https://github.com/wangruohui/EfficientVideoAgent.</p> + https://arxiv.org/abs/2603.22918 + Tue, 24 Mar 2026 08:06:29 +0000 - MosaicMem: Hybrid Spatial Memory for Controllable Video World Models - https://arxiv.org/abs/2603.17117 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.17117.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wei Yu, Runjia Qian, Yumeng Li, Liquan Wang, Songheng Yin, Sri Siddarth Chakaravarthy P, Dennis Anthony, Yang Ye, Yidi Li, Weiwei Wan, Animesh Garg</p><p><b>Upvotes:</b> 82</p><p><b>Summary:</b> Video diffusion models are moving beyond short, plausible clips toward world simulators that must remain consistent under camera motion, revisits, and intervention. Yet spatial memory remains a key bottleneck: explicit 3D structures can improve reprojection-based consistency but struggle to depict moving objects, while implicit memory often produces inaccurate camera motion even with correct poses. We propose Mosaic Memory (MosaicMem), a hybrid spatial memory that lifts patches into 3D for reliable localization and targeted retrieval, while exploiting the model's native conditioning to preserve prompt-following generation. MosaicMem composes spatially aligned patches in the queried view via a patch-and-compose interface, preserving what should persist while allowing the model to inpaint what should evolve. With PRoPE camera conditioning and two new memory alignment methods, experiments show improved pose adherence compared to implicit memory and stronger dynamic modeling than explicit baselines. MosaicMem further enables minute-level navigation, memory-based scene editing, and autoregressive rollout.</p> - https://arxiv.org/abs/2603.17117 - Tue, 17 Mar 2026 20:19:44 +0000 + SIMART: Decomposing Monolithic Meshes into Sim-ready Articulated Assets via MLLM + https://arxiv.org/abs/2603.23386 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.23386.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chuanrui Zhang, Minghan Qin, Yuang Wang, Baifeng Xie, Hang Li, Ziwei Wang</p><p><b>Upvotes:</b> 41</p><p><b>Summary:</b> High-quality articulated 3D assets are indispensable for embodied AI and physical simulation, yet 3D generation still focuses on static meshes, leaving a gap in "sim-ready" interactive objects. Most recent articulated object creation methods rely on multi-stage pipelines that accumulate errors across decoupled modules. Alternatively, unified MLLMs offer a single-stage path to joint static asset understanding and sim-ready asset generation. However dense voxel-based 3D tokenization yields long 3D token sequences and high memory overhead, limiting scalability to complex articulated objects. To address this, we propose SIMART, a unified MLLM framework that jointly performs part-level decomposition and kinematic prediction. By introducing a Sparse 3D VQ-VAE, SIMART reduces token counts by 70% vs. dense voxel tokens, enabling high-fidelity multi-part assemblies. SIMART achieves state-of-the-art performance on PartNet-Mobility and in-the-wild AIGC datasets, and enables physics-based robotic simulation.</p> + https://arxiv.org/abs/2603.23386 + Tue, 24 Mar 2026 16:16:52 +0000 - MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild - https://arxiv.org/abs/2603.17187 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.17187.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Peng Xia, Jianwen Chen, Xinyu Yang, Haoqin Tu, Jiaqi Liu, Kaiwen Xiong, Siwei Han, Shi Qiu, Haonian Ji, Yuyin Zhou, Zeyu Zheng, Cihang Xie, Huaxiu Yao</p><p><b>Upvotes:</b> 117</p><p><b>Summary:</b> Large language model (LLM) agents are increasingly used for complex tasks, yet deployed agents often remain static, failing to adapt as user needs evolve. This creates a tension between the need for continuous service and the necessity of updating capabilities to match shifting task distributions. On platforms like OpenClaw, which handle diverse workloads across 20+ channels, existing methods either store raw trajectories without distilling knowledge, maintain static skill libraries, or require disruptive downtime for retraining. We present MetaClaw, a continual meta-learning framework that jointly evolves a base LLM policy and a library of reusable behavioral skills. MetaClaw employs two complementary mechanisms. Skill-driven fast adaptation analyzes failure trajectories via an LLM evolver to synthesize new skills, enabling immediate improvement with zero downtime. Opportunistic policy optimization performs gradient-based updates via cloud LoRA fine-tuning and Reinforcement Learning with a Process Reward Model (RL-PRM). This is triggered during user-inactive windows by the Opportunistic Meta-Learning Scheduler (OMLS), which monitors system inactivity and calendar data. These mechanisms are mutually reinforcing: a refined policy generates better trajectories for skill synthesis, while richer skills provide higher-quality data for policy optimization. To prevent data contamination, a versioning mechanism separates support and query data. Built on a proxy-based architecture, MetaClaw scales to production-size LLMs without local GPUs. Experiments on MetaClaw-Bench and AutoResearchClaw show that skill-driven adaptation improves accuracy by up to 32% relative. The full pipeline advances Kimi-K2.5 accuracy from 21.4% to 40.6% and increases composite robustness by 18.3%. Code is available at https://github.com/aiming-lab/MetaClaw.</p> - https://arxiv.org/abs/2603.17187 - Tue, 17 Mar 2026 22:30:30 +0000 + RealMaster: Lifting Rendered Scenes into Photorealistic Video + https://arxiv.org/abs/2603.23462 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.23462.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dana Cohen-Bar, Ido Sobol, Raphael Bensadoun, Shelly Sheynin, Oran Gafni, Or Patashnik, Daniel Cohen-Or, Amit Zohar</p><p><b>Upvotes:</b> 29</p><p><b>Summary:</b> State-of-the-art video generation models produce remarkable photorealism, but they lack the precise control required to align generated content with specific scene requirements. Furthermore, without an underlying explicit geometry, these models cannot guarantee 3D consistency. Conversely, 3D engines offer granular control over every scene element and provide native 3D consistency by design, yet their output often remains trapped in the "uncanny valley". Bridging this sim-to-real gap requires both structural precision, where the output must exactly preserve the geometry and dynamics of the input, and global semantic transformation, where materials, lighting, and textures must be holistically transformed to achieve photorealism. We present RealMaster, a method that leverages video diffusion models to lift rendered video into photorealistic video while maintaining full alignment with the output of the 3D engine. To train this model, we generate a paired dataset via an anchor-based propagation strategy, where the first and last frames are enhanced for realism and propagated across the intermediate frames using geometric conditioning cues. We then train an IC-LoRA on these paired videos to distill the high-quality outputs of the pipeline into a model that generalizes beyond the pipeline's constraints, handling objects and characters that appear mid-sequence and enabling inference without requiring anchor frames. Evaluated on complex GTA-V sequences, RealMaster significantly outperforms existing video editing baselines, improving photorealism while preserving the geometry, dynamics, and identity specified by the original 3D control.</p> + https://arxiv.org/abs/2603.23462 + Tue, 24 Mar 2026 17:32:42 +0000 - Alignment Makes Language Models Normative, Not Descriptive - https://arxiv.org/abs/2603.17218 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.17218.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Eilam Shapira, Moshe Tennenholtz, Roi Reichart</p><p><b>Upvotes:</b> 45</p><p><b>Summary:</b> Post-training alignment optimizes language models to match human preference signals, but this objective is not equivalent to modeling observed human behavior. We compare 120 base-aligned model pairs on more than 10,000 real human decisions in multi-round strategic games - bargaining, persuasion, negotiation, and repeated matrix games. In these settings, base models outperform their aligned counterparts in predicting human choices by nearly 10:1, robustly across model families, prompt formulations, and game configurations. This pattern reverses, however, in settings where human behavior is more likely to follow normative predictions: aligned models dominate on one-shot textbook games across all 12 types tested and on non-strategic lottery choices - and even within the multi-round games themselves, at round one, before interaction history develops. This boundary-condition pattern suggests that alignment induces a normative bias: it improves prediction when human behavior is relatively well captured by normative solutions, but hurts prediction in multi-round strategic settings, where behavior is shaped by descriptive dynamics such as reciprocity, retaliation, and history-dependent adaptation. These results reveal a fundamental trade-off between optimizing models for human use and using them as proxies for human behavior.</p> - https://arxiv.org/abs/2603.17218 - Tue, 17 Mar 2026 23:47:08 +0000 + VTAM: Video-Tactile-Action Models for Complex Physical Interaction Beyond VLAs + https://arxiv.org/abs/2603.23481 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.23481.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haoran Yuan, Weigang Yi, Zhenyu Zhang, Wendi Chen, Yuchen Mo, Jiashi Yin, Xinzhuo Li, Xiangyu Zeng, Chuan Wen, Cewu Lu, Katherine Driggs-Campbell, Ismini Lourentzou</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Video-Action Models (VAMs) have emerged as a promising framework for embodied intelligence, learning implicit world dynamics from raw video streams to produce temporally consistent action predictions. Although such models demonstrate strong performance on long-horizon tasks through visual reasoning, they remain limited in contact-rich scenarios where critical interaction states are only partially observable from vision alone. In particular, fine-grained force modulation and contact transitions are not reliably encoded in visual tokens, leading to unstable or imprecise behaviors. To bridge this gap, we introduce the Video-Tactile Action Model (VTAM), a multimodal world modeling framework that incorporates tactile perception as a complementary grounding signal. VTAM augments a pretrained video transformer with tactile streams via a lightweight modality transfer finetuning, enabling efficient cross-modal representation learning without tactile-language paired data or independent tactile pretraining. To stabilize multimodal fusion, we introduce a tactile regularization loss that enforces balanced cross-modal attention, preventing visual latent dominance in the action model. VTAM demonstrates superior performance in contact-rich manipulation, maintaining a robust success rate of 90 percent on average. In challenging scenarios such as potato chip pick-and-place requiring high-fidelity force awareness, VTAM outperforms the pi 0.5 baseline by 80 percent. Our findings demonstrate that integrating tactile feedback is essential for correcting visual estimation errors in world action models, providing a scalable approach to physically grounded embodied foundation models.</p> + https://arxiv.org/abs/2603.23481 + Tue, 24 Mar 2026 17:45:06 +0000 - GigaWorld-Policy: An Efficient Action-Centered World--Action Model - https://arxiv.org/abs/2603.17240 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.17240.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Angen Ye, Boyuan Wang, Chaojun Ni, Guan Huang, Guosheng Zhao, Hao Li, Hengtao Li, Jie Li, Jindi Lv, Jingyu Liu, Min Cao, Peng Li, Qiuping Deng, Wenjun Mei, Xiaofeng Wang, Xinze Chen, Xinyu Zhou, Yang Wang, Yifan Chang, Yifan Li, Yukun Zhou, Yun Ye, Zhichao Liu, Zheng Zhu</p><p><b>Upvotes:</b> 23</p><p><b>Summary:</b> World-Action Models (WAM) initialized from pre-trained video generation backbones have demonstrated remarkable potential for robot policy learning. However, existing approaches face two critical bottlenecks that hinder performance and deployment. First, jointly reasoning over future visual dynamics and corresponding actions incurs substantial inference overhead. Second, joint modeling often entangles visual and motion representations, making motion prediction accuracy heavily dependent on the quality of future video forecasts. To address these issues, we introduce GigaWorld-Policy, an action-centered WAM that learns 2D pixel-action dynamics while enabling efficient action decoding, with optional video generation. Specifically, we formulate policy training into two coupled components: the model predicts future action sequences conditioned on the current observation, and simultaneously generates future videos conditioned on the predicted actions and the same observation. The policy is supervised by both action prediction and video generation, providing richer learning signals and encouraging physically plausible actions through visual-dynamics constraints. With a causal design that prevents future-video tokens from influencing action tokens, explicit future-video generation is optional at inference time, allowing faster action prediction during deployment. To support this paradigm, we curate a diverse, large-scale robot dataset to pre-train an action-centered video generation model, which is then adapted as the backbone for robot policy learning. Experimental results on real-world robotic platforms show that GigaWorld-Policy runs 9x faster than the leading WAM baseline, Motus, while improving task success rates by 7%. Moreover, compared with pi-0.5, GigaWorld-Policy improves performance by 95% on RoboTwin 2.0.</p> - https://arxiv.org/abs/2603.17240 - Wed, 18 Mar 2026 00:52:02 +0000 + SpecEyes: Accelerating Agentic Multimodal LLMs via Speculative Perception and Planning + https://arxiv.org/abs/2603.23483 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.23483.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haoyu Huang, Jinfa Huang, Zhongwei Wan, Xiawu Zheng, Rongrong Ji, Jiebo Luo</p><p><b>Upvotes:</b> 58</p><p><b>Summary:</b> Agentic multimodal large language models (MLLMs) (e.g., OpenAI o3 and Gemini Agentic Vision) achieve remarkable reasoning capabilities through iterative visual tool invocation. However, the cascaded perception, reasoning, and tool-calling loops introduce significant sequential overhead. This overhead, termed agentic depth, incurs prohibitive latency and seriously limits system-level concurrency. To this end, we propose SpecEyes, an agentic-level speculative acceleration framework that breaks this sequential bottleneck. Our key insight is that a lightweight, tool-free MLLM can serve as a speculative planner to predict the execution trajectory, enabling early termination of expensive tool chains without sacrificing accuracy. To regulate this speculative planning, we introduce a cognitive gating mechanism based on answer separability, which quantifies the model's confidence for self-verification without requiring oracle labels. Furthermore, we design a heterogeneous parallel funnel that exploits the stateless concurrency of the small model to mask the stateful serial execution of the large model, maximizing system throughput. Extensive experiments on V* Bench, HR-Bench, and POPE demonstrate that SpecEyes achieves 1.1-3.35x speedup over the agentic baseline while preserving or even improving accuracy (up to +6.7%), thereby boosting serving throughput under concurrent workloads.</p> + https://arxiv.org/abs/2603.23483 + Tue, 24 Mar 2026 17:45:47 +0000 - Stereo World Model: Camera-Guided Stereo Video Generation - https://arxiv.org/abs/2603.17375 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.17375.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yang-Tian Sun, Zehuan Huang, Yifan Niu, Lin Ma, Yan-Pei Cao, Yuewen Ma, Xiaojuan Qi</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> We present StereoWorld, a camera-conditioned stereo world model that jointly learns appearance and binocular geometry for end-to-end stereo video generation.Unlike monocular RGB or RGBD approaches, StereoWorld operates exclusively within the RGB modality, while simultaneously grounding geometry directly from disparity. To efficiently achieve consistent stereo generation, our approach introduces two key designs: (1) a unified camera-frame RoPE that augments latent tokens with camera-aware rotary positional encoding, enabling relative, view- and time-consistent conditioning while preserving pretrained video priors via a stable attention initialization; and (2) a stereo-aware attention decomposition that factors full 4D attention into 3D intra-view attention plus horizontal row attention, leveraging the epipolar prior to capture disparity-aligned correspondences with substantially lower compute. Across benchmarks, StereoWorld improves stereo consistency, disparity accuracy, and camera-motion fidelity over strong monocular-then-convert pipelines, achieving more than 3x faster generation with an additional 5% gain in viewpoint consistency. Beyond benchmarks, StereoWorld enables end-to-end binocular VR rendering without depth estimation or inpainting, enhances embodied policy learning through metric-scale depth grounding, and is compatible with long-video distillation for extended interactive stereo synthesis.</p> - https://arxiv.org/abs/2603.17375 - Wed, 18 Mar 2026 05:42:22 +0000 + WildWorld: A Large-Scale Dataset for Dynamic World Modeling with Actions and Explicit State toward Generative ARPG + https://arxiv.org/abs/2603.23497 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.23497.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhen Li, Zian Meng, Shuwei Shi, Wenshuo Peng, Yuwei Wu, Bo Zheng, Chuanhao Li, Kaipeng Zhang</p><p><b>Upvotes:</b> 85</p><p><b>Summary:</b> Dynamical systems theory and reinforcement learning view world evolution as latent-state dynamics driven by actions, with visual observations providing partial information about the state. Recent video world models attempt to learn this action-conditioned dynamics from data. However, existing datasets rarely match the requirement: they typically lack diverse and semantically meaningful action spaces, and actions are directly tied to visual observations rather than mediated by underlying states. As a result, actions are often entangled with pixel-level changes, making it difficult for models to learn structured world dynamics and maintain consistent evolution over long horizons. In this paper, we propose WildWorld, a large-scale action-conditioned world modeling dataset with explicit state annotations, automatically collected from a photorealistic AAA action role-playing game (Monster Hunter: Wilds). WildWorld contains over 108 million frames and features more than 450 actions, including movement, attacks, and skill casting, together with synchronized per-frame annotations of character skeletons, world states, camera poses, and depth maps. We further derive WildBench to evaluate models through Action Following and State Alignment. Extensive experiments reveal persistent challenges in modeling semantically rich actions and maintaining long-horizon state consistency, highlighting the need for state-aware video generation. The project page is https://shandaai.github.io/wildworld-project/.</p> + https://arxiv.org/abs/2603.23497 + Tue, 24 Mar 2026 17:58:25 +0000 - Efficient Exploration at Scale - https://arxiv.org/abs/2603.17378 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.17378.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Seyed Mohammad Asghari, Chris Chute, Vikranth Dwaracherla, Xiuyuan Lu, Mehdi Jafarnia, Victor Minden, Zheng Wen, Benjamin Van Roy</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> We develop an online learning algorithm that dramatically improves the data efficiency of reinforcement learning from human feedback (RLHF). Our algorithm incrementally updates reward and language models as choice data is received. The reward model is fit to the choice data, while the language model is updated by a variation of reinforce, with reinforcement signals provided by the reward model. Several features enable the efficiency gains: a small affirmative nudge added to each reinforcement signal, an epistemic neural network that models reward uncertainty, and information-directed exploration. With Gemma large language models (LLMs), our algorithm matches the performance of offline RLHF trained on 200K labels using fewer than 20K labels, representing more than a 10x gain in data efficiency. Extrapolating from our results, we expect our algorithm trained on 1M labels to match offline RLHF trained on 1B labels. This represents a 1,000x gain. To our knowledge, these are the first results to demonstrate that such large improvements are possible.</p> - https://arxiv.org/abs/2603.17378 - Wed, 18 Mar 2026 05:47:59 +0000 + DA-Flow: Degradation-Aware Optical Flow Estimation with Diffusion Models + https://arxiv.org/abs/2603.23499 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.23499.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jaewon Min, Jaeeun Lee, Yeji Choi, Paul Hyunbin Cho, Jin Hyeon Kim, Tae-Young Lee, Jongsik Ahn, Hwayeong Lee, Seonghyun Park, Seungryong Kim</p><p><b>Upvotes:</b> 48</p><p><b>Summary:</b> Optical flow models trained on high-quality data often degrade severely when confronted with real-world corruptions such as blur, noise, and compression artifacts. To overcome this limitation, we formulate Degradation-Aware Optical Flow, a new task targeting accurate dense correspondence estimation from real-world corrupted videos. Our key insight is that the intermediate representations of image restoration diffusion models are inherently corruption-aware but lack temporal awareness. To address this limitation, we lift the model to attend across adjacent frames via full spatio-temporal attention, and empirically demonstrate that the resulting features exhibit zero-shot correspondence capabilities. Based on this finding, we present DA-Flow, a hybrid architecture that fuses these diffusion features with convolutional features within an iterative refinement framework. DA-Flow substantially outperforms existing optical flow methods under severe degradation across multiple benchmarks.</p> + https://arxiv.org/abs/2603.23499 + Tue, 24 Mar 2026 17:59:13 +0000 - MOSS-TTS Technical Report - https://arxiv.org/abs/2603.18090 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.18090.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yitian Gong, Botian Jiang, Yiwei Zhao, Yucheng Yuan, Kuangwei Chen, Yaozhou Jiang, Cheng Chang, Dong Hong, Mingshu Chen, Ruixiao Li, Yiyang Zhang, Yang Gao, Hanfu Chen, Ke Chen, Songlin Wang, Xiaogui Yang, Yuqian Zhang, Kexin Huang, ZhengYuan Lin, Kang Yu, Ziqi Chen, Jin Wang, Zhaoye Fei, Qinyuan Cheng, Shimin Li, Xipeng Qiu</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> This technical report presents MOSS-TTS, a speech generation foundation model built on a scalable recipe: discrete audio tokens, autoregressive modeling, and large-scale pretraining. Built on MOSS-Audio-Tokenizer, a causal Transformer tokenizer that compresses 24 kHz audio to 12.5 fps with variable-bitrate RVQ and unified semantic-acoustic representations, we release two complementary generators: MOSS-TTS, which emphasizes structural simplicity, scalability, and long-context/control-oriented deployment, and MOSS-TTS-Local-Transformer, which introduces a frame-local autoregressive module for higher modeling efficiency, stronger speaker preservation, and a shorter time to first audio. Across multilingual and open-domain settings, MOSS-TTS supports zero-shot voice cloning, token-level duration control, phoneme-/pinyin-level pronunciation control, smooth code-switching, and stable long-form generation. This report summarizes the design, training recipe, and empirical characteristics of the released models.</p> - https://arxiv.org/abs/2603.18090 - Wed, 18 Mar 2026 09:08:06 +0000 + UniGRPO: Unified Policy Optimization for Reasoning-Driven Visual Generation + https://arxiv.org/abs/2603.23500 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.23500.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jie Liu, Zilyu Ye, Linxiao Yuan, Shenhan Zhu, Yu Gao, Jie Wu, Kunchang Li, Xionghui Wang, Xiaonan Nie, Weilin Huang, Wanli Ouyang</p><p><b>Upvotes:</b> 35</p><p><b>Summary:</b> Unified models capable of interleaved generation have emerged as a promising paradigm, with the community increasingly converging on autoregressive modeling for text and flow matching for image generation. To advance this direction, we propose a unified reinforcement learning framework tailored for interleaved generation. We validate our approach on its fundamental unit: a single round of reasoning-driven image generation, where the model first expands the user prompt through reasoning, followed by image synthesis. Formulating this multimodal generation process as a Markov Decision Process with sparse terminal rewards, we introduce UniGRPO to jointly optimize text and image generation policies using GRPO. Adopting a minimalist methodology to avoid over-design, we leverage established training recipes for both modalities by seamlessly integrating standard GRPO for reasoning and FlowGRPO for visual synthesis. To ensure scalability to multi-round interleaved generation, we introduce two critical modifications to the original FlowGRPO: (1) eliminating classifier-free guidance to maintain linear, unbranched rollouts, which is essential for scaling to complex scenarios involving multi-turn interactions and multi-condition generation (e.g., editing); and (2) replacing the standard latent KL penalty with an MSE penalty directly on the velocity fields, providing a more robust and direct regularization signal to mitigate reward hacking effectively. Our experiments demonstrate that this unified training recipe significantly enhances image generation quality through reasoning, providing a robust and scalable baseline for the future post-training of fully interleaved models.</p> + https://arxiv.org/abs/2603.23500 + Tue, 24 Mar 2026 17:59:17 +0000 - Temporal Gains, Spatial Costs: Revisiting Video Fine-Tuning in Multimodal Large Language Models - https://arxiv.org/abs/2603.17541 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.17541.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Linghao Zhang, Jungang Li, Yonghua Hei, Sicheng Tao, Song Dai, Yibo Yan, Zihao Dongfang, Weiting Liu, Chenxi Qin, Hanqian Li, Xin Zou, Jiahao Zhang, Shuhang Xun, Haiyun Jiang, Xuming Hu</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> Multimodal large language models (MLLMs) are typically trained in multiple stages, with video-based supervised fine-tuning (Video-SFT) serving as a key step for improving visual understanding. Yet its effect on the fine-grained evolution of visual capabilities, particularly the balance between spatial and temporal understanding, remains poorly understood. In this paper, we systematically study how Video-SFT reshapes visual capabilities in MLLMs. Across architectures, parameter scales, and frame sampling settings, we observe a consistent pattern: Video-SFT reliably improves video performance, but often yields limited gains or even degradation on static image benchmarks. We further show that this trade-off is closely tied to temporal budget: increasing the number of sampled frames generally improves video performance, but does not reliably improve static image performance. Motivated by this finding, we study an instruction-aware Hybrid-Frame strategy that adaptively allocates frame counts and partially mitigates the image-video trade-off. Our results indicate that Video-SFT is not a free lunch for MLLMs, and preserving spatial understanding remains a central challenge in joint image-video training.</p> - https://arxiv.org/abs/2603.17541 - Wed, 18 Mar 2026 09:46:44 +0000 + Can LLM Agents Be CFOs? A Benchmark for Resource Allocation in Dynamic Enterprise Environments + https://arxiv.org/abs/2603.23638 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.23638.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yi Han, Lingfei Qian, Yan Wang, Yueru He, Xueqing Peng, Dongji Feng, Yankai Chen, Haohang Li, Yupeng Cao, Jimin Huang, Xue Liu, Jian-Yun Nie, Sophia Ananiadou</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Large language models (LLMs) have enabled agentic systems that can reason, plan, and act across complex tasks, but it remains unclear whether they can allocate resources effectively under uncertainty. Unlike short-horizon reactive decisions, allocation requires committing scarce resources over time while balancing competing objectives and preserving flexibility for future needs. We introduce EnterpriseArena, the first benchmark for evaluating agents on long-horizon enterprise resource allocation. It instantiates CFO-style decision-making in a 132-month enterprise simulator combining firm-level financial data, anonymized business documents, macroeconomic and industry signals, and expert-validated operating rules. The environment is partially observable and reveals the state only through budgeted organizational tools, forcing agents to trade off information acquisition against conserving scarce resources. Experiments on eleven advanced LLMs show that this setting remains highly challenging: only 16% of runs survive the full horizon, and larger models do not reliably outperform smaller ones. These results identify long-horizon resource allocation under uncertainty as a distinct capability gap for current LLM agents.</p> + https://arxiv.org/abs/2603.23638 + Tue, 24 Mar 2026 18:25:00 +0000 - Complementary Reinforcement Learning - https://arxiv.org/abs/2603.17621 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.17621.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dilxat Muhtar, Jiashun Liu, Wei Gao, Weixun Wang, Shaopan Xiong, Ju Huang, Siran Yang, Wenbo Su, Jiamang Wang, Ling Pan, Bo Zheng</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> Reinforcement Learning (RL) has emerged as a powerful paradigm for training LLM-based agents, yet remains limited by low sample efficiency, stemming not only from sparse outcome feedback but also from the agent's inability to leverage prior experience across episodes. While augmenting agents with historical experience offers a promising remedy, existing approaches suffer from a critical weakness: the experience distilled from history is either stored statically or fail to coevolve with the improving actor, causing a progressive misalignment between the experience and the actor's evolving capability that diminishes its utility over the course of training. Inspired by complementary learning systems in neuroscience, we present Complementary RL to achieve seamless co-evolution of an experience extractor and a policy actor within the RL optimization loop. Specifically, the actor is optimized via sparse outcome-based rewards, while the experience extractor is optimized according to whether its distilled experiences demonstrably contribute to the actor's success, thereby evolving its experience management strategy in lockstep with the actor's growing capabilities. Empirically, Complementary RL outperforms outcome-based agentic RL baselines that do not learn from experience, achieving 10% performance improvement in single-task scenarios and exhibits robust scalability in multi-task settings. These results establish Complementary RL as a paradigm for efficient experience-driven agent learning.</p> - https://arxiv.org/abs/2603.17621 - Wed, 18 Mar 2026 11:38:01 +0000 + Understanding the Challenges in Iterative Generative Optimization with LLMs + https://arxiv.org/abs/2603.23994 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.23994.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Allen Nie, Xavier Daull, Zhiyi Kuang, Abhinav Akkiraju, Anish Chaudhuri, Max Piasevoli, Ryan Rong, YuCheng Yuan, Prerit Choudhary, Shannon Xiao, Rasool Fakoor, Adith Swaminathan, Ching-An Cheng</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> Generative optimization uses large language models (LLMs) to iteratively improve artifacts (such as code, workflows or prompts) using execution feedback. It is a promising approach to building self-improving agents, yet in practice remains brittle: despite active research, only 9% of surveyed agents used any automated optimization. We argue that this brittleness arises because, to set up a learning loop, an engineer must make ``hidden'' design choices: What can the optimizer edit and what is the "right" learning evidence to provide at each update? We investigate three factors that affect most applications: the starting artifact, the credit horizon for execution traces, and batching trials and errors into learning evidence. Through case studies in MLAgentBench, Atari, and BigBench Extra Hard, we find that these design decisions can determine whether generative optimization succeeds, yet they are rarely made explicit in prior work. Different starting artifacts determine which solutions are reachable in MLAgentBench, truncated traces can still improve Atari agents, and larger minibatches do not monotonically improve generalization on BBEH. We conclude that the lack of a simple, universal way to set up learning loops across domains is a major hurdle for productionization and adoption. We provide practical guidance for making these choices.</p> + https://arxiv.org/abs/2603.23994 + Wed, 25 Mar 2026 06:49:24 +0000 - LoST: Level of Semantics Tokenization for 3D Shapes - https://arxiv.org/abs/2603.17995 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.17995.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Niladri Shekhar Dutt, Zifan Shi, Paul Guerrero, Chun-Hao Paul Huang, Duygu Ceylan, Niloy J. Mitra, Xuelin Chen</p><p><b>Upvotes:</b> 27</p><p><b>Summary:</b> Tokenization is a fundamental technique in the generative modeling of various modalities. In particular, it plays a critical role in autoregressive (AR) models, which have recently emerged as a compelling option for 3D generation. However, optimal tokenization of 3D shapes remains an open question. State-of-the-art (SOTA) methods primarily rely on geometric level-of-detail (LoD) hierarchies, originally designed for rendering and compression. These spatial hierarchies are often token-inefficient and lack semantic coherence for AR modeling. We propose Level-of-Semantics Tokenization (LoST), which orders tokens by semantic salience, such that early prefixes decode into complete, plausible shapes that possess principal semantics, while subsequent tokens refine instance-specific geometric and semantic details. To train LoST, we introduce Relational Inter-Distance Alignment (RIDA), a novel 3D semantic alignment loss that aligns the relational structure of the 3D shape latent space with that of the semantic DINO feature space. Experiments show that LoST achieves SOTA reconstruction, surpassing previous LoD-based 3D shape tokenizers by large margins on both geometric and semantic reconstruction metrics. Moreover, LoST achieves efficient, high-quality AR 3D generation and enables downstream tasks like semantic retrieval, while using only 0.1%-10% of the tokens needed by prior AR models.</p> - https://arxiv.org/abs/2603.17995 - Wed, 18 Mar 2026 17:56:06 +0000 + CarePilot: A Multi-Agent Framework for Long-Horizon Computer Task Automation in Healthcare + https://arxiv.org/abs/2603.24157 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.24157.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Akash Ghosh, Tajamul Ashraf, Rishu Kumar Singh, Numan Saeed, Sriparna Saha, Xiuying Chen, Salman Khan</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Multimodal agentic pipelines are transforming human-computer interaction by enabling efficient and accessible automation of complex, real-world tasks. However, recent efforts have focused on short-horizon or general-purpose applications (e.g., mobile or desktop interfaces), leaving long-horizon automation for domain-specific systems, particularly in healthcare, largely unexplored. To address this, we introduce CareFlow, a high-quality human-annotated benchmark comprising complex, long-horizon software workflows across medical annotation tools, DICOM viewers, EHR systems, and laboratory information systems. On this benchmark, existing vision-language models (VLMs) perform poorly, struggling with long-horizon reasoning and multi-step interactions in medical contexts. To overcome this, we propose CarePilot, a multi-agent framework based on the actor-critic paradigm. The Actor integrates tool grounding with dual-memory mechanisms (long-term and short-term experience) to predict the next semantic action from the visual interface and system state. The Critic evaluates each action, updates memory based on observed effects, and either executes or provides corrective feedback to refine the workflow. Through iterative agentic simulation, the Actor learns to perform more robust and reasoning-aware predictions during inference. Our experiments show that CarePilot achieves state-of-the-art performance, outperforming strong closed-source and open-source multimodal baselines by approximately 15.26% and 3.38%, respectively, on our benchmark and out-of-distribution dataset.</p> + https://arxiv.org/abs/2603.24157 + Wed, 25 Mar 2026 10:25:48 +0000 - Loc3R-VLM: Language-based Localization and 3D Reasoning with Vision-Language Models - https://arxiv.org/abs/2603.18002 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.18002.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kevin Qu, Haozhe Qi, Mihai Dusmanu, Mahdi Rad, Rui Wang, Marc Pollefeys</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Multimodal Large Language Models (MLLMs) have made impressive progress in connecting vision and language, but they still struggle with spatial understanding and viewpoint-aware reasoning. Recent efforts aim to augment the input representations with geometric cues rather than explicitly teaching models to reason in 3D space. We introduce Loc3R-VLM, a framework that equips 2D Vision-Language Models with advanced 3D understanding capabilities from monocular video input. Inspired by human spatial cognition, Loc3R-VLM relies on two joint objectives: global layout reconstruction to build a holistic representation of the scene structure, and explicit situation modeling to anchor egocentric perspective. These objectives provide direct spatial supervision that grounds both perception and language in a 3D context. To ensure geometric consistency and metric-scale alignment, we leverage lightweight camera pose priors extracted from a pre-trained 3D foundation model. Loc3R-VLM achieves state-of-the-art performance in language-based localization and outperforms existing 2D- and video-based approaches on situated and general 3D question-answering benchmarks, demonstrating that our spatial supervision framework enables strong 3D understanding. Project page: https://kevinqu7.github.io/loc3r-vlm</p> - https://arxiv.org/abs/2603.18002 - Wed, 18 Mar 2026 17:59:10 +0000 + GameplayQA: A Benchmarking Framework for Decision-Dense POV-Synced Multi-Video Understanding of 3D Virtual Agents + https://arxiv.org/abs/2603.24329 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.24329.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yunzhe Wang, Runhui Xu, Kexin Zheng, Tianyi Zhang, Jayavibhav Niranjan Kogundi, Soham Hans, Volkan Ustun</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> Multimodal LLMs are increasingly deployed as perceptual backbones for autonomous agents in 3D environments, from robotics to virtual worlds. These applications require agents to perceive rapid state changes, attribute actions to the correct entities, and reason about concurrent multi-agent behaviors from a first-person perspective, capabilities that existing benchmarks do not adequately evaluate. We introduce GameplayQA, a framework for evaluating agentic-centric perception and reasoning through video understanding. Specifically, we densely annotate multiplayer 3D gameplay videos at 1.22 labels/second, with time-synced, concurrent captions of states, actions, and events structured around a triadic system of Self, Other Agents, and the World, a natural decomposition for multi-agent environments. From these annotations, we refined 2.4K diagnostic QA pairs organized into three levels of cognitive complexity, accompanied by a structured distractor taxonomy that enables fine-grained analysis of where models hallucinate. Evaluation of frontier MLLMs reveals a substantial gap from human performance, with common failures in temporal and cross-video grounding, agent-role attribution, and handling the decision density of the game. We hope GameplayQA stimulates future research at the intersection of embodied AI, agentic perception, and world modeling.</p> + https://arxiv.org/abs/2603.24329 + Wed, 25 Mar 2026 14:10:45 +0000 - Unified Spatio-Temporal Token Scoring for Efficient Video VLMs - https://arxiv.org/abs/2603.18004 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.18004.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jianrui Zhang, Yue Yang, Rohun Tripathi, Winson Han, Ranjay Krishna, Christopher Clark, Yong Jae Lee, Sangho Lee</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Token pruning is essential for enhancing the computational efficiency of vision-language models (VLMs), particularly for video-based tasks where temporal redundancy is prevalent. Prior approaches typically prune tokens either (1) within the vision transformer (ViT) exclusively for unimodal perception tasks such as action recognition and object segmentation, without adapting to downstream vision-language tasks; or (2) only within the LLM while leaving the ViT output intact, often requiring complex text-conditioned token selection mechanisms. In this paper, we introduce Spatio-Temporal Token Scoring (STTS), a simple and lightweight module that prunes vision tokens across both the ViT and the LLM without text conditioning or token merging, and is fully compatible with end-to-end training. By learning how to score temporally via an auxiliary loss and spatially via LLM downstream gradients, aided by our efficient packing algorithm, STTS prunes 50% of vision tokens throughout the entire architecture, resulting in a 62% improvement in efficiency during both training and inference with only a 0.7% drop in average performance across 13 short and long video QA tasks. Efficiency gains increase with more sampled frames per video. Applying test-time scaling for long-video QA further yields performance gains of 0.5-1% compared to the baseline. Overall, STTS represents a novel, simple yet effective technique for unified, architecture-wide vision token pruning.</p> - https://arxiv.org/abs/2603.18004 - Wed, 18 Mar 2026 17:59:56 +0000 + CUA-Suite: Massive Human-annotated Video Demonstrations for Computer-Use Agents + https://arxiv.org/abs/2603.24440 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.24440.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiangru Jian, Shravan Nayak, Kevin Qinghong Lin, Aarash Feizi, Kaixin Li, Patrice Bechard, Spandana Gella, Sai Rajeswar</p><p><b>Upvotes:</b> 87</p><p><b>Summary:</b> Computer-use agents (CUAs) hold great promise for automating complex desktop workflows, yet progress toward general-purpose agents is bottlenecked by the scarcity of continuous, high-quality human demonstration videos. Recent work emphasizes that continuous video, not sparse screenshots, is the critical missing ingredient for scaling these agents. However, the largest existing open dataset, ScaleCUA, contains only 2 million screenshots, equating to less than 20 hours of video. To address this bottleneck, we introduce CUA-Suite, a large-scale ecosystem of expert video demonstrations and dense annotations for professional desktop computer-use agents. At its core is VideoCUA, which provides approximately 10,000 human-demonstrated tasks across 87 diverse applications with continuous 30 fps screen recordings, kinematic cursor traces, and multi-layerfed reasoning annotations, totaling approximately 55 hours and 6 million frames of expert video. Unlike sparse datasets that capture only final click coordinates, these continuous video streams preserve the full temporal dynamics of human interaction, forming a superset of information that can be losslessly transformed into the formats required by existing agent frameworks. CUA-Suite further provides two complementary resources: UI-Vision, a rigorous benchmark for evaluating grounding and planning capabilities in CUAs, and GroundCUA, a large-scale grounding dataset with 56K annotated screenshots and over 3.6 million UI element annotations. Preliminary evaluation reveals that current foundation action models struggle substantially with professional desktop applications (~60% task failure rate). Beyond evaluation, CUA-Suite's rich multimodal corpus supports emerging research directions including generalist screen parsing, continuous spatial control, video-based reward modeling, and visual world models. All data and models are publicly released.</p> + https://arxiv.org/abs/2603.24440 + Wed, 25 Mar 2026 15:52:56 +0000 - AndroTMem: From Interaction Trajectories to Anchored Memory in Long-Horizon GUI Agents - https://arxiv.org/abs/2603.18429 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.18429.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yibo Shi, Jungang Li, Linghao Zhang, Zihao Dongfang, Biao Wu, Sicheng Tao, Yibo Yan, Chenxi Qin, Weiting Liu, Zhixin Lin, Hanqian Li, Yu Huang, Song Dai, Yonghua Hei, Yue Ding, Xiang Li, Shikang Wang, Chengdong Xu, Jingqi Liu, Xueying Ma, Zhiwen Zheng, Xiaofei Zhang, Bincheng Wang, Nichen Yang, Jie Wu, Lihua Tian, Chen Li, Xuming Hu</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> Long-horizon GUI agents are a key step toward real-world deployment, yet effective interaction memory under prevailing paradigms remains under-explored. Replaying full interaction sequences is redundant and amplifies noise, while summaries often erase dependency-critical information and traceability. We present AndroTMem, a diagnostic framework for anchored memory in long-horizon Android GUI agents. Its core benchmark, AndroTMem-Bench, comprises 1,069 tasks with 34,473 interaction steps (avg. 32.1 per task, max. 65). We evaluate agents with TCR (Task Complete Rate), focusing on tasks whose completion requires carrying forward critical intermediate state; AndroTMem-Bench is designed to enforce strong step-to-step causal dependencies, making sparse yet essential intermediate states decisive for downstream actions and centering interaction memory in evaluation. Across open- and closed-source GUI agents, we observe a consistent pattern: as interaction sequences grow longer, performance drops are driven mainly by within-task memory failures, not isolated perception errors or local action mistakes. Guided by this diagnosis, we propose Anchored State Memory (ASM), which represents interaction sequences as a compact set of causally linked intermediate-state anchors to enable subgoal-targeted retrieval and attribution-aware decision making. Across multiple settings and 12 evaluated GUI agents, ASM consistently outperforms full-sequence replay and summary-based baselines, improving TCR by 5%-30.16% and AMS by 4.93%-24.66%, indicating that anchored, structured memory effectively mitigates the interaction-memory bottleneck in long-horizon GUI tasks. The code, benchmark, and related resources are publicly available at [https://github.com/CVC2233/AndroTMem](https://github.com/CVC2233/AndroTMem).</p> - https://arxiv.org/abs/2603.18429 - Thu, 19 Mar 2026 02:45:21 +0000 + Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs? + https://arxiv.org/abs/2603.24472 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.24472.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jeonghye Kim, Xufang Luo, Minbeom Kim, Sangmook Lee, Dohyung Kim, Jiwon Jeon, Dongsheng Li, Yuqing Yang</p><p><b>Upvotes:</b> 40</p><p><b>Summary:</b> Self-distillation has emerged as an effective post-training paradigm for LLMs, often improving performance while shortening reasoning traces. However, in mathematical reasoning, we find that it can reduce response length while degrading performance. We trace this degradation to the suppression of epistemic verbalization - the model's expression of uncertainty during reasoning. Through controlled experiments varying conditioning context richness and task coverage, we show that conditioning the teacher on rich information suppresses uncertainty expression, enabling rapid in-domain optimization with limited task coverage but harming OOD performance, where unseen problems benefit from expressing uncertainty and adjusting accordingly. Across Qwen3-8B, DeepSeek-Distill-Qwen-7B, and Olmo3-7B-Instruct, we observe performance drops of up to 40%. Our findings highlight that exposing appropriate levels of uncertainty is crucial for robust reasoning and underscore the importance of optimizing reasoning behavior beyond merely reinforcing correct answer traces.</p> + https://arxiv.org/abs/2603.24472 + Wed, 25 Mar 2026 16:14:52 +0000 - Cognitive Mismatch in Multimodal Large Language Models for Discrete Symbol Understanding - https://arxiv.org/abs/2603.18472 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.18472.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yinghui Li, Jiayi Kuang, Peng Xing, Daixian Liu, Junnan Dong, Shu-Yu Guo, Yangning Li, Qingyu Zhou, Wenhao Jiang, Hai-Tao Zheng, Ying Shen, Liang Lin, Philip S. Yu</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> While Multimodal Large Language Models (MLLMs) have achieved remarkable success in interpreting natural scenes, their ability to process discrete symbols -- the fundamental building blocks of human cognition -- remains a critical open question. Unlike continuous visual data, symbols such as mathematical formulas, chemical structures, and linguistic characters require precise, deeper interpretation. This paper introduces a comprehensive benchmark to evaluate how top-tier MLLMs navigate these "discrete semantic spaces" across five domains: language, culture, mathematics, physics, and chemistry. Our investigation uncovers a counterintuitive phenomenon: models often fail at basic symbol recognition yet succeed in complex reasoning tasks, suggesting they rely on linguistic probability rather than true visual perception. By exposing this "cognitive mismatch", we highlight a significant gap in current AI capabilities: the struggle to truly perceive and understand the symbolic languages that underpin scientific discovery and abstract thought. This work offers a roadmap for developing more rigorous, human-aligned intelligent systems.</p> - https://arxiv.org/abs/2603.18472 - Thu, 19 Mar 2026 04:08:20 +0000 + AVO: Agentic Variation Operators for Autonomous Evolutionary Search + https://arxiv.org/abs/2603.24517 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.24517.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Terry Chen, Zhifan Ye, Bing Xu, Zihao Ye, Timmy Liu, Ali Hassani, Tianqi Chen, Andrew Kerr, Haicheng Wu, Yang Xu, Yu-Jung Chen, Hanfeng Chen, Aditya Kane, Ronny Krashinsky, Ming-Yu Liu, Vinod Grover, Luis Ceze, Roger Bringmann, John Tran, Wei Liu, Fung Xie, Michael Lightstone, Humphrey Shi</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Agentic Variation Operators (AVO) are a new family of evolutionary variation operators that replace the fixed mutation, crossover, and hand-designed heuristics of classical evolutionary search with autonomous coding agents. Rather than confining a language model to candidate generation within a prescribed pipeline, AVO instantiates variation as a self-directed agent loop that can consult the current lineage, a domain-specific knowledge base, and execution feedback to propose, repair, critique, and verify implementation edits. We evaluate AVO on attention, among the most aggressively optimized kernel targets in AI, on NVIDIA Blackwell (B200) GPUs. Over 7 days of continuous autonomous evolution on multi-head attention, AVO discovers kernels that outperform cuDNN by up to 3.5% and FlashAttention-4 by up to 10.5% across the evaluated configurations. The discovered optimizations transfer readily to grouped-query attention, requiring only 30 minutes of additional autonomous adaptation and yielding gains of up to 7.0% over cuDNN and 9.3% over FlashAttention-4. Together, these results show that agentic variation operators move beyond prior LLM-in-the-loop evolutionary pipelines by elevating the agent from candidate generator to variation operator, and can discover performance-critical micro-architectural optimizations that produce kernels surpassing state-of-the-art expert-engineered attention implementations on today's most advanced GPU hardware.</p> + https://arxiv.org/abs/2603.24517 + Wed, 25 Mar 2026 16:55:04 +0000 - 3DreamBooth: High-Fidelity 3D Subject-Driven Video Generation Model - https://arxiv.org/abs/2603.18524 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.18524.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hyun-kyu Ko, Jihyeon Park, Younghyun Kim, Dongheok Park, Eunbyung Park</p><p><b>Upvotes:</b> 51</p><p><b>Summary:</b> Creating dynamic, view-consistent videos of customized subjects is highly sought after for a wide range of emerging applications, including immersive VR/AR, virtual production, and next-generation e-commerce. However, despite rapid progress in subject-driven video generation, existing methods predominantly treat subjects as 2D entities, focusing on transferring identity through single-view visual features or textual prompts. Because real-world subjects are inherently 3D, applying these 2D-centric approaches to 3D object customization reveals a fundamental limitation: they lack the comprehensive spatial priors necessary to reconstruct the 3D geometry. Consequently, when synthesizing novel views, they must rely on generating plausible but arbitrary details for unseen regions, rather than preserving the true 3D identity. Achieving genuine 3D-aware customization remains challenging due to the scarcity of multi-view video datasets. While one might attempt to fine-tune models on limited video sequences, this often leads to temporal overfitting. To resolve these issues, we introduce a novel framework for 3D-aware video customization, comprising 3DreamBooth and 3Dapter. 3DreamBooth decouples spatial geometry from temporal motion through a 1-frame optimization paradigm. By restricting updates to spatial representations, it effectively bakes a robust 3D prior into the model without the need for exhaustive video-based training. To enhance fine-grained textures and accelerate convergence, we incorporate 3Dapter, a visual conditioning module. Following single-view pre-training, 3Dapter undergoes multi-view joint optimization with the main generation branch via an asymmetrical conditioning strategy. This design allows the module to act as a dynamic selective router, querying view-specific geometric hints from a minimal reference set. Project page: https://ko-lani.github.io/3DreamBooth/</p> - https://arxiv.org/abs/2603.18524 - Thu, 19 Mar 2026 06:14:05 +0000 + UI-Voyager: A Self-Evolving GUI Agent Learning via Failed Experience + https://arxiv.org/abs/2603.24533 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.24533.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zichuan Lin, Feiyu Liu, Yijun Yang, Jiafei Lyu, Yiming Gao, Yicheng Liu, Zhicong Lu, Yangbin Yu, Mingyu Yang, Junyou Li, Deheng Ye, Jie Jiang</p><p><b>Upvotes:</b> 40</p><p><b>Summary:</b> Autonomous mobile GUI agents have attracted increasing attention along with the advancement of Multimodal Large Language Models (MLLMs). However, existing methods still suffer from inefficient learning from failed trajectories and ambiguous credit assignment under sparse rewards for long-horizon GUI tasks. To that end, we propose UI-Voyager, a novel two-stage self-evolving mobile GUI agent. In the first stage, we employ Rejection Fine-Tuning (RFT), which enables the continuous co-evolution of data and models in a fully autonomous loop. The second stage introduces Group Relative Self-Distillation (GRSD), which identifies critical fork points in group rollouts and constructs dense step-level supervision from successful trajectories to correct failed ones. Extensive experiments on AndroidWorld show that our 4B model achieves an 81.0% Pass@1 success rate, outperforming numerous recent baselines and exceeding human-level performance. Ablation and case studies further verify the effectiveness of GRSD. Our method represents a significant leap toward efficient, self-evolving, and high-performance mobile GUI automation without expensive manual data annotation.</p> + https://arxiv.org/abs/2603.24533 + Wed, 25 Mar 2026 17:10:29 +0000 - Memento-Skills: Let Agents Design Agents - https://arxiv.org/abs/2603.18743 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.18743.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Huichi Zhou, Siyuan Guo, Anjie Liu, Zhongwei Yu, Ziqin Gong, Bowen Zhao, Zhixun Chen, Menglong Zhang, Yihang Chen, Jinsong Li, Runyu Yang, Qiangbin Liu, Xinlei Yu, Jianmin Zhou, Na Wang, Chunyang Sun, Jun Wang</p><p><b>Upvotes:</b> 37</p><p><b>Summary:</b> We introduce Memento-Skills, a generalist, continually-learnable LLM agent system that functions as an agent-designing agent: it autonomously constructs, adapts, and improves task-specific agents through experience. The system is built on a memory-based reinforcement learning framework with stateful prompts, where reusable skills (stored as structured markdown files) serve as persistent, evolving memory. These skills encode both behaviour and context, enabling the agent to carry forward knowledge across interactions. Starting from simple elementary skills (like Web search and terminal operations), the agent continually improves via the Read--Write Reflective Learning mechanism introduced in Memento~2~wang2025memento2. In the read phase, a behaviour-trainable skill router selects the most relevant skill conditioned on the current stateful prompt; in the write phase, the agent updates and expands its skill library based on new experience. This closed-loop design enables continual learning without updating LLM parameters, as all adaptation is realised through the evolution of externalised skills and prompts. Unlike prior approaches that rely on human-designed agents, Memento-Skills enables a generalist agent to design agents end-to-end for new tasks. Through iterative skill generation and refinement, the system progressively improves its own capabilities. Experiments on the General AI Assistants benchmark and Humanity's Last Exam demonstrate sustained gains, achieving 26.2\% and 116.2\% relative improvements in overall accuracy, respectively. Code is available at https://github.com/Memento-Teams/Memento-Skills.</p> - https://arxiv.org/abs/2603.18743 - Thu, 19 Mar 2026 10:45:22 +0000 + VFIG: Vectorizing Complex Figures in SVG with Vision-Language Models + https://arxiv.org/abs/2603.24575 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.24575.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qijia He, Xunmei Liu, Hammaad Memon, Ziang Li, Zixian Ma, Jaemin Cho, Jason Ren, Daniel S Weld, Ranjay Krishna</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Scalable Vector Graphics (SVG) are an essential format for technical illustration and digital design, offering precise resolution independence and flexible semantic editability. In practice, however, original vector source files are frequently lost or inaccessible, leaving only "flat" rasterized versions (e.g., PNG or JPEG) that are difficult to modify or scale. Manually reconstructing these figures is a prohibitively labor-intensive process, requiring specialized expertise to recover the original geometric intent. To bridge this gap, we propose VFIG, a family of Vision-Language Models trained for complex and high-fidelity figure-to-SVG conversion. While this task is inherently data-driven, existing datasets are typically small-scale and lack the complexity of professional diagrams. We address this by introducing VFIG-DATA, a large-scale dataset of 66K high-quality figure-SVG pairs, curated from a diverse mix of real-world paper figures and procedurally generated diagrams. Recognizing that SVGs are composed of recurring primitives and hierarchical local structures, we introduce a coarse-to-fine training curriculum that begins with supervised fine-tuning (SFT) to learn atomic primitives and transitions to reinforcement learning (RL) refinement to optimize global diagram fidelity, layout consistency, and topological edge cases. Finally, we introduce VFIG-BENCH, a comprehensive evaluation suite with novel metrics designed to measure the structural integrity of complex figures. VFIG achieves state-of-the-art performance among open-source models and performs on par with GPT-5.2, achieving a VLM-Judge score of 0.829 on VFIG-BENCH.</p> + https://arxiv.org/abs/2603.24575 + Wed, 25 Mar 2026 17:52:23 +0000 - ProRL Agent: Rollout-as-a-Service for RL Training of Multi-Turn LLM Agents - https://arxiv.org/abs/2603.18815 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.18815.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hao Zhang, Mingjie Liu, Shaokun Zhang, Songyang Han, Jian Hu, Zhenghui Jin, Yuchi Zhang, Shizhe Diao, Ximing Lu, Binfeng Xu, Zhiding Yu, Jan Kautz, Yi Dong</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Multi-turn LLM agents are increasingly important for solving complex, interactive tasks, and reinforcement learning (RL) is a key ingredient for improving their long-horizon behavior. However, RL training requires generating large numbers of sandboxed rollout trajectories, and existing infrastructures often couple rollout orchestration with the training loop, making systems hard to migrate and maintain. Under the rollout-as-a-service philosophy, we present ProRL Agent , a scalable infrastructure that serves the full agentic rollout lifecycle through an API service. ProRL Agent also provides standardized and extensible sandbox environments that support diverse agentic tasks in rootless HPC settings. We validate ProRL Agent through RL training on software engineering, math, STEM, and coding tasks. ProRL Agent is open-sourced and integrated as part of NVIDIA NeMo Gym.</p> - https://arxiv.org/abs/2603.18815 - Thu, 19 Mar 2026 12:08:51 +0000 + SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative Tasks + https://arxiv.org/abs/2603.24755 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.24755.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Gabriel Orlanski, Devjeet Roy, Alexander Yun, Changho Shin, Alex Gu, Albert Ge, Dyah Adila, Frederic Sala, Aws Albarghouthi</p><p><b>Upvotes:</b> 24</p><p><b>Summary:</b> Software development is iterative, yet agentic coding benchmarks overwhelmingly evaluate single-shot solutions against complete specifications. Code can pass the test suite but become progressively harder to extend. Recent iterative benchmarks attempt to close this gap, but constrain the agent's design decisions too tightly to faithfully measure how code quality shapes future extensions. We introduce SlopCodeBench, a language-agnostic benchmark comprising 20 problems and 93 checkpoints, in which agents repeatedly extend their own prior solutions under evolving specifications that force architectural decisions without prescribing internal structure. We track two trajectory-level quality signals: verbosity, the fraction of redundant or duplicated code, and structural erosion, the share of complexity mass concentrated in high-complexity functions. No agent solves any problem end-to-end across 11 models; the highest checkpoint solve rate is 17.2%. Quality degrades steadily: erosion rises in 80% of trajectories and verbosity in 89.8%. Against 48 open-source Python repositories, agent code is 2.2x more verbose and markedly more eroded. Tracking 20 of those repositories over time shows that human code stays flat, while agent code deteriorates with each iteration. A prompt-intervention study shows that initial quality can be improved, but it does not halt degradation. These results demonstrate that pass-rate benchmarks systematically undermeasure extension robustness, and that current agents lack the design discipline iterative software development demands.</p> + https://arxiv.org/abs/2603.24755 + Wed, 25 Mar 2026 19:26:44 +0000 - FASTER: Rethinking Real-Time Flow VLAs - https://arxiv.org/abs/2603.19199 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19199.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuxiang Lu, Zhe Liu, Xianzhe Fan, Zhenya Yang, Jinghua Hou, Junyi Li, Kaixin Ding, Hengshuang Zhao</p><p><b>Upvotes:</b> 49</p><p><b>Summary:</b> Real-time execution is crucial for deploying Vision-Language-Action (VLA) models in the physical world. Existing asynchronous inference methods primarily optimize trajectory smoothness, but neglect the critical latency in reacting to environmental changes. By rethinking the notion of reaction in action chunking policies, this paper presents a systematic analysis of the factors governing reaction time. We show that reaction time follows a uniform distribution determined jointly by the Time to First Action (TTFA) and the execution horizon. Moreover, we reveal that the standard practice of applying a constant schedule in flow-based VLAs can be inefficient and forces the system to complete all sampling steps before any movement can start, forming the bottleneck in reaction latency. To overcome this issue, we propose Fast Action Sampling for ImmediaTE Reaction (FASTER). By introducing a Horizon-Aware Schedule, FASTER adaptively prioritizes near-term actions during flow sampling, compressing the denoising of the immediate reaction by tenfold (e.g., in π_{0.5} and X-VLA) into a single step, while preserving the quality of long-horizon trajectory. Coupled with a streaming client-server pipeline, FASTER substantially reduces the effective reaction latency on real robots, especially when deployed on consumer-grade GPUs. Real-world experiments, including a highly dynamic table tennis task, prove that FASTER unlocks unprecedented real-time responsiveness for generalist policies, enabling rapid generation of accurate and smooth trajectories.</p> - https://arxiv.org/abs/2603.19199 - Thu, 19 Mar 2026 17:51:37 +0000 + AVControl: Efficient Framework for Training Audio-Visual Controls + https://arxiv.org/abs/2603.24793 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.24793.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Matan Ben-Yosef, Tavi Halperin, Naomi Ken Korem, Mohammad Salama, Harel Cain, Asaf Joseph, Anthony Chen, Urska Jelercic, Ofir Bibi</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> Controlling video and audio generation requires diverse modalities, from depth and pose to camera trajectories and audio transformations, yet existing approaches either train a single monolithic model for a fixed set of controls or introduce costly architectural changes for each new modality. We introduce AVControl, a lightweight, extendable framework built on LTX-2, a joint audio-visual foundation model, where each control modality is trained as a separate LoRA on a parallel canvas that provides the reference signal as additional tokens in the attention layers, requiring no architectural changes beyond the LoRA adapters themselves. We show that simply extending image-based in-context methods to video fails for structural control, and that our parallel canvas approach resolves this. On the VACE Benchmark, we outperform all evaluated baselines on depth- and pose-guided generation, inpainting, and outpainting, and show competitive results on camera control and audio-visual benchmarks. Our framework supports a diverse set of independently trained modalities: spatially-aligned controls such as depth, pose, and edges, camera trajectory with intrinsics, sparse motion control, video editing, and, to our knowledge, the first modular audio-visual controls for a joint generation model. Our method is both compute- and data-efficient: each modality requires only a small dataset and converges within a few hundred to a few thousand training steps, a fraction of the budget of monolithic alternatives. We publicly release our code and trained LoRA checkpoints.</p> + https://arxiv.org/abs/2603.24793 + Wed, 25 Mar 2026 20:06:43 +0000 - Tinted Frames: Question Framing Blinds Vision-Language Models - https://arxiv.org/abs/2603.19203 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19203.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wan-Cyuan Fan, Jiayun Luo, Declan Kutscher, Leonid Sigal, Ritwik Gupta</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Vision-Language Models (VLMs) have been shown to be blind, often underutilizing their visual inputs even on tasks that require visual reasoning. In this work, we demonstrate that VLMs are selectively blind. They modulate the amount of attention applied to visual inputs based on linguistic framing even when alternative framings demand identical visual reasoning. Using visual attention as a probe, we quantify how framing alters both the amount and distribution of attention over the image. Constrained framings, such as multiple choice and yes/no, induce substantially lower attention to image context compared to open-ended, reduce focus on task-relevant regions, and shift attention towards uninformative tokens. We further demonstrate that this attention misallocation is the principal cause of degraded accuracy and cross-framing inconsistency. Building on this mechanistic insight, we introduce a lightweight prompt-tuning method using learnable tokens that encourages the robust, visually grounded attention patterns observed in open-ended settings, improving visual grounding and improving performance across framings.</p> - https://arxiv.org/abs/2603.19203 - Thu, 19 Mar 2026 17:53:09 +0000 + Calibri: Enhancing Diffusion Transformers via Parameter-Efficient Calibration + https://arxiv.org/abs/2603.24800 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.24800.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Danil Tokhchukov, Aysel Mirzoeva, Andrey Kuznetsov, Konstantin Sobolev</p><p><b>Upvotes:</b> 53</p><p><b>Summary:</b> In this paper, we uncover the hidden potential of Diffusion Transformers (DiTs) to significantly enhance generative tasks. Through an in-depth analysis of the denoising process, we demonstrate that introducing a single learned scaling parameter can significantly improve the performance of DiT blocks. Building on this insight, we propose Calibri, a parameter-efficient approach that optimally calibrates DiT components to elevate generative quality. Calibri frames DiT calibration as a black-box reward optimization problem, which is efficiently solved using an evolutionary algorithm and modifies just ~100 parameters. Experimental results reveal that despite its lightweight design, Calibri consistently improves performance across various text-to-image models. Notably, Calibri also reduces the inference steps required for image generation, all while maintaining high-quality outputs.</p> + https://arxiv.org/abs/2603.24800 + Wed, 25 Mar 2026 20:19:50 +0000 - LVOmniBench: Pioneering Long Audio-Video Understanding Evaluation for Omnimodal LLMs - https://arxiv.org/abs/2603.19217 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19217.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Keda Tao, Yuhua Zheng, Jia Xu, Wenjie Du, Kele Shao, Hesong Wang, Xueyi Chen, Xin Jin, Junhan Zhu, Bohan Yu, Weiqiang Wang, Jian Liu, Can Qin, Yulun Zhang, Ming-Hsuan Yang, Huan Wang</p><p><b>Upvotes:</b> 27</p><p><b>Summary:</b> Recent advancements in omnimodal large language models (OmniLLMs) have significantly improved the comprehension of audio and video inputs. However, current evaluations primarily focus on short audio and video clips ranging from 10 seconds to 5 minutes, failing to reflect the demands of real-world applications, where videos typically run for tens of minutes. To address this critical gap, we introduce LVOmniBench, a new benchmark designed specifically for the cross-modal comprehension of long-form audio and video. This dataset comprises high-quality videos sourced from open platforms that feature rich audio-visual dynamics. Through rigorous manual selection and annotation, LVOmniBench comprises 275 videos, ranging in duration from 10 to 90 minutes, and 1,014 question-answer (QA) pairs. LVOmniBench aims to rigorously evaluate the capabilities of OmniLLMs across domains, including long-term memory, temporal localization, fine-grained understanding, and multimodal perception. Our extensive evaluation reveals that current OmniLLMs encounter significant challenges when processing extended audio-visual inputs. Open-source models generally achieve accuracies below 35%, whereas the Gemini 3 Pro reaches a peak accuracy of approximately 65%. We anticipate that this dataset, along with our empirical findings, will stimulate further research and the development of advanced models capable of resolving complex cross-modal understanding problems within long-form audio-visual contexts.</p> - https://arxiv.org/abs/2603.19217 - Thu, 19 Mar 2026 17:58:13 +0000 + FinMCP-Bench: Benchmarking LLM Agents for Real-World Financial Tool Use under the Model Context Protocol + https://arxiv.org/abs/2603.24943 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.24943.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jie Zhu, Yimin Tian, Boyang Li, Kehao Wu, Zhongzhi Liang, Junhui Li, Xianyin Zhang, Lifan Guo, Feng Chen, Yong Liu, Chi Zhang</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> This paper introduces FinMCP-Bench, a novel benchmark for evaluating large language models (LLMs) in solving real-world financial problems through tool invocation of financial model context protocols. FinMCP-Bench contains 613 samples spanning 10 main scenarios and 33 sub-scenarios, featuring both real and synthetic user queries to ensure diversity and authenticity. It incorporates 65 real financial MCPs and three types of samples, single tool, multi-tool, and multi-turn, allowing evaluation of models across different levels of task complexity. Using this benchmark, we systematically assess a range of mainstream LLMs and propose metrics that explicitly measure tool invocation accuracy and reasoning capabilities. FinMCP-Bench provides a standardized, practical, and challenging testbed for advancing research on financial LLM agents.</p> + https://arxiv.org/abs/2603.24943 + Thu, 26 Mar 2026 02:20:04 +0000 - Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation - https://arxiv.org/abs/2603.19220 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19220.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhuolin Yang, Zihan Liu, Yang Chen, Wenliang Dai, Boxin Wang, Sheng-Chieh Lin, Chankyu Lee, Yangyi Chen, Dongfu Jiang, Jiafan He, Renjie Pi, Grace Lam, Nayeon Lee, Alexander Bukharin, Mohammad Shoeybi, Bryan Catanzaro, Wei Ping</p><p><b>Upvotes:</b> 47</p><p><b>Summary:</b> We introduce Nemotron-Cascade 2, an open 30B MoE model with 3B activated parameters that delivers best-in-class reasoning and strong agentic capabilities. Despite its compact size, its mathematical and coding reasoning performance approaches that of frontier open models. It is the second open-weight LLM, after DeepSeekV3.2-Speciale-671B-A37B, to achieve Gold Medal-level performance in the 2025 International Mathematical Olympiad (IMO), the International Olympiad in Informatics (IOI), and the ICPC World Finals, demonstrating remarkably high intelligence density with 20x fewer parameters. In contrast to Nemotron-Cascade 1, the key technical advancements are as follows. After SFT on a meticulously curated dataset, we substantially expand Cascade RL to cover a much broader spectrum of reasoning and agentic domains. Furthermore, we introduce multi-domain on-policy distillation from the strongest intermediate teacher models for each domain throughout the Cascade RL process, allowing us to efficiently recover benchmark regressions and sustain strong performance gains along the way. We release the collection of model checkpoint and training data.</p> - https://arxiv.org/abs/2603.19220 - Thu, 19 Mar 2026 17:58:52 +0000 + Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale + https://arxiv.org/abs/2603.25040 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.25040.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yicheng Zou, Dongsheng Zhu, Lin Zhu, Tong Zhu, Yunhua Zhou, Peiheng Zhou, Xinyu Zhou, Dongzhan Zhou, Zhiwang Zhou, Yuhao Zhou, Bowen Zhou, Zhanping Zhong, Zhijie Zhong, Haiteng Zhao, Penghao Zhao, Xiaomeng Zhao, Zhiyuan Zhao, Yechen Zhang, Jin Zhang, Wenwei Zhang, Hongjie Zhang, Zhuo Zhang, Wenlong Zhang, Bo Zhang, Chao Zhang, Chen Zhang, Yuhang Zang, Fei Yuan, Jiakang Yuan, Jiashuo Yu, Jinhui Yin, Haochen Ye, Qian Yao, Bowen Yang, Danni Yang, Kaichen Yang, Ziang Yan, Jun Xu, Yicheng Xu, Wanghan Xu, Xuenan Xu, Chao Xu, Ruiliang Xu, Shuhao Xing, Long Xing, Xinchen Xie, Ling-I Wu, Zijian Wu, Zhenyu Wu, Lijun Wu, Yue Wu, Jianyu Wu, Wen Wu, Fan Wu, Xilin Wei, Qi Wei, Bingli Wang, Rui Wang, Ziyi Wang, Zun Wang, Yi Wang, Haomin Wang, Yizhou Wang, Lintao Wang, Yiheng Wang, Longjiang Wang, Bin Wang, Jian Tong, Zhongbo Tian, Huanze Tang, Chen Tang, Shixiang Tang, Yu Sun, Qiushi Sun, Xuerui Su, Qisheng Su, Chenlin Su, Demin Song, Jin Shi, Fukai Shang, Yuchen Ren, Pengli Ren, Xiaoye Qu, Yuan Qu, Jiantao Qiu, Yu Qiao, Runyu Peng, Tianshuo Peng, Jiahui Peng, Qizhi Pei, Zhuoshi Pan, Linke Ouyang, Wenchang Ning, Yichuan Ma, Zerun Ma, Ningsheng Ma, Runyuan Ma, Chengqi Lyu, Haijun Lv, Han Lv, Lindong Lu, Kuikun Liu, Jiangning Liu, Yuhong Liu, Kai Liu, Hongwei Liu, Zhoumianze Liu, Mengjie Liu, Ziyu Liu, Wenran Liu, Yang Liu, Liwei Liu, Kaiwen Liu, Junyao Lin, Junming Lin, Tianyang Lin, Dahua Lin, Jianze Liang, Linyang Li, Peiji Li, Zonglin Li, Zehao Li, Pengze Li, Guoyan Li, Lingkai Kong, Linglin Jing, Zhenjiang Jin, Feifei Jiang, Qian Jiang, Junhao Huang, Zixian Huang, Haian Huang, Zhouqi Hua, Han Hu, Linfeng Hou, Yinan He, Conghui He, Tianyao He, Xu Guo, Qipeng Guo, Aijia Guo, Yuzhe Gu, Lixin Gu, Jingyang Gong, Qiming Ge, Jiaye Ge, Songyang Gao, Jianfei Gao, Xinyu Fang, Caihua fan, Yue Fan, Yanhui Duan, Zichen Ding, Shengyuan Ding, Xuanlang Dai, Erfei Cui, Ganqu Cui, Pei Chu, Tao Chu, Guangran Cheng, Yu Cheng, Kai Chen, Yongkang Chen, Chiyu Chen, Guanzhou Chen, Qiaosheng Chen, Sitao Chen, Xin Chen, Haojiong Chen, Yicheng Chen, Weihan Cao, Yuhang Cao, Qinglong Cao, Lei Bai</p><p><b>Upvotes:</b> 109</p><p><b>Summary:</b> We introduce Intern-S1-Pro, the first one-trillion-parameter scientific multimodal foundation model. Scaling to this unprecedented size, the model delivers a comprehensive enhancement across both general and scientific domains. Beyond stronger reasoning and image-text understanding capabilities, its intelligence is augmented with advanced agent capabilities. Simultaneously, its scientific expertise has been vastly expanded to master over 100 specialized tasks across critical science fields, including chemistry, materials, life sciences, and earth sciences. Achieving this massive scale is made possible by the robust infrastructure support of XTuner and LMDeploy, which facilitates highly efficient Reinforcement Learning (RL) training at the 1-trillion parameter level while ensuring strict precision consistency between training and inference. By seamlessly integrating these advancements, Intern-S1-Pro further fortifies the fusion of general and specialized intelligence, working as a Specializable Generalist, demonstrating its position in the top tier of open-source models for general capabilities, while outperforming proprietary models in the depth of specialized scientific tasks.</p> + https://arxiv.org/abs/2603.25040 + Thu, 26 Mar 2026 05:21:45 +0000 - F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World - https://arxiv.org/abs/2603.19223 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19223.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ziyin Zhang, Zihan Liao, Hang Yu, Peng Di, Rui Wang</p><p><b>Upvotes:</b> 24</p><p><b>Summary:</b> We present F2LLM-v2, a new family of general-purpose, multilingual embedding models in 8 distinct sizes ranging from 80M to 14B. Trained on a newly curated composite of 60 million publicly available high-quality data samples, F2LLM-v2 supports more than 200 languages, with a particular emphasis on previously underserved mid- and low-resource languages. By integrating a two-stage LLM-based embedding training pipeline with matryoshka learning, model pruning, and knowledge distillation techniques, we present models that are far more efficient than previous LLM-based embedding models while retaining competitive performances. Extensive evaluations confirm that F2LLM-v2-14B ranks first on 11 MTEB benchmarks, while the smaller models in the family also set a new state of the art for resource-constrained applications. To facilitate open-source embedding model research, we release all models, data, code, and intermediate checkpoints.</p> - https://arxiv.org/abs/2603.19223 - Thu, 19 Mar 2026 17:59:21 +0000 + MACRO: Advancing Multi-Reference Image Generation with Structured Long-Context Data + https://arxiv.org/abs/2603.25319 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.25319.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhekai Chen, Yuqing Wang, Manyuan Zhang, Xihui Liu</p><p><b>Upvotes:</b> 27</p><p><b>Summary:</b> Generating images conditioned on multiple visual references is critical for real-world applications such as multi-subject composition, narrative illustration, and novel view synthesis, yet current models suffer from severe performance degradation as the number of input references grows. We identify the root cause as a fundamental data bottleneck: existing datasets are dominated by single- or few-reference pairs and lack the structured, long-context supervision needed to learn dense inter-reference dependencies. To address this, we introduce MacroData, a large-scale dataset of 400K samples, each containing up to 10 reference images, systematically organized across four complementary dimensions -- Customization, Illustration, Spatial reasoning, and Temporal dynamics -- to provide comprehensive coverage of the multi-reference generation space. Recognizing the concurrent absence of standardized evaluation protocols, we further propose MacroBench, a benchmark of 4,000 samples that assesses generative coherence across graded task dimensions and input scales. Extensive experiments show that fine-tuning on MacroData yields substantial improvements in multi-reference generation, and ablation studies further reveal synergistic benefits of cross-task co-training and effective strategies for handling long-context complexity. The dataset and benchmark will be publicly released.</p> + https://arxiv.org/abs/2603.25319 + Thu, 26 Mar 2026 11:09:14 +0000 - EffectErase: Joint Video Object Removal and Insertion for High-Quality Effect Erasing - https://arxiv.org/abs/2603.19224 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19224.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yang Fu, Yike Zheng, Ziyun Dai, Henghui Ding</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Video object removal aims to eliminate dynamic target objects and their visual effects, such as deformation, shadows, and reflections, while restoring seamless backgrounds. Recent diffusion-based video inpainting and object removal methods can remove the objects but often struggle to erase these effects and to synthesize coherent backgrounds. Beyond method limitations, progress is further hampered by the lack of a comprehensive dataset that systematically captures common object effects across varied environments for training and evaluation. To address this, we introduce VOR (Video Object Removal), a large-scale dataset that provides diverse paired videos, each consisting of one video where the target object is present with its effects and a counterpart where the object and effects are absent, with corresponding object masks. VOR contains 60K high-quality video pairs from captured and synthetic sources, covers five effects types, and spans a wide range of object categories as well as complex, dynamic multi-object scenes. Building on VOR, we propose EffectErase, an effect-aware video object removal method that treats video object insertion as the inverse auxiliary task within a reciprocal learning scheme. The model includes task-aware region guidance that focuses learning on affected areas and enables flexible task switching. Then, an insertion-removal consistency objective that encourages complementary behaviors and shared localization of effect regions and structural cues. Trained on VOR, EffectErase achieves superior performance in extensive experiments, delivering high-quality video object effect erasing across diverse scenarios.</p> - https://arxiv.org/abs/2603.19224 - Thu, 19 Mar 2026 17:59:22 +0000 + RealRestorer: Towards Generalizable Real-World Image Restoration with Large-Scale Image Editing Models + https://arxiv.org/abs/2603.25502 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.25502.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yufeng Yang, Xianfang Zeng, Zhangqi Jiang, Fukun Yin, Jianzhuang Liu, Wei Cheng, jinghong lan, Shiyu Liu, Yuqi Peng, Gang YU, Shifeng Chen</p><p><b>Upvotes:</b> 47</p><p><b>Summary:</b> Image restoration under real-world degradations is critical for downstream tasks such as autonomous driving and object detection. However, existing restoration models are often limited by the scale and distribution of their training data, resulting in poor generalization to real-world scenarios. Recently, large-scale image editing models have shown strong generalization ability in restoration tasks, especially for closed-source models like Nano Banana Pro, which can restore images while preserving consistency. Nevertheless, achieving such performance with those large universal models requires substantial data and computational costs. To address this issue, we construct a large-scale dataset covering nine common real-world degradation types and train a state-of-the-art open-source model to narrow the gap with closed-source alternatives. Furthermore, we introduce RealIR-Bench, which contains 464 real-world degraded images and tailored evaluation metrics focusing on degradation removal and consistency preservation. Extensive experiments demonstrate our model ranks first among open-source methods, achieving state-of-the-art performance.</p> + https://arxiv.org/abs/2603.25502 + Thu, 26 Mar 2026 14:39:39 +0000 - Bridging Semantic and Kinematic Conditions with Diffusion-based Discrete Motion Tokenizer - https://arxiv.org/abs/2603.19227 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19227.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chenyang Gu, Mingyuan Zhang, Haozhe Xie, Zhongang Cai, Lei Yang, Ziwei Liu</p><p><b>Upvotes:</b> 39</p><p><b>Summary:</b> Prior motion generation largely follows two paradigms: continuous diffusion models that excel at kinematic control, and discrete token-based generators that are effective for semantic conditioning. To combine their strengths, we propose a three-stage framework comprising condition feature extraction (Perception), discrete token generation (Planning), and diffusion-based motion synthesis (Control). Central to this framework is MoTok, a diffusion-based discrete motion tokenizer that decouples semantic abstraction from fine-grained reconstruction by delegating motion recovery to a diffusion decoder, enabling compact single-layer tokens while preserving motion fidelity. For kinematic conditions, coarse constraints guide token generation during planning, while fine-grained constraints are enforced during control through diffusion-based optimization. This design prevents kinematic details from disrupting semantic token planning. On HumanML3D, our method significantly improves controllability and fidelity over MaskControl while using only one-sixth of the tokens, reducing trajectory error from 0.72 cm to 0.08 cm and FID from 0.083 to 0.029. Unlike prior methods that degrade under stronger kinematic constraints, ours improves fidelity, reducing FID from 0.033 to 0.014.</p> - https://arxiv.org/abs/2603.19227 - Thu, 19 Mar 2026 17:59:51 +0000 + Voxtral TTS + https://arxiv.org/abs/2603.25551 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.25551.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Alexander H. Liu, Alexis Tacnet, Andy Ehrenberg, Andy Lo, Chen-Yo Sun, Guillaume Lample, Henry Lagarde, Jean-Malo Delignon, Jaeyoung Kim, John Harvill, Khyathi Raghavi Chandu, Lorenzo Signoretti, Margaret Jennings, Patrick von Platen, Pavankumar Reddy Muddireddy, Rohin Arora, Sanchit Gandhi, Samuel Humeau, Soham Ghosh, Srijan Mishra, Van Phung, Abdelaziz Bounhar, Abhinav Rastogi, Adrien Sadé, Alan Jeffares, Albert Jiang, Alexandre Cahill, Alexandre Gavaudan, Alexandre Sablayrolles, Amélie Héliou, Amos You, Andrew Bai, Andrew Zhao, Angele Lenglemetz, Anmol Agarwal, Anton Eliseev, Antonia Calvi, Arjun Majumdar, Arthur Fournier, Artjom Joosen, Avi Sooriyarachchi, Aysenur Karaduman Utkur, Baptiste Bout, Baptiste Rozière, Baudouin De Monicault, Benjamin Tibi, Bowen Yang, Charlotte Cronjäger, Clémence Lanfranchi, Connor Chen, Corentin Barreau, Corentin Sautier, Cyprien Courtot, Darius Dabert, Diego de las Casas, Elizaveta Demyanenko, Elliot Chane-Sane, Emmanuel Gottlob, Enguerrand Paquin, Etienne Goffinet, Fabien Niel, Faruk Ahmed, Federico Baldassarre, Gabrielle Berrada, Gaëtan Ecrepont, Gauthier Guinet, Genevieve Hayes, Georgii Novikov, Giada Pistilli, Guillaume Kunsch, Guillaume Martin, Guillaume Raille, Gunjan Dhanuka, Gunshi Gupta, Han Zhou, Harshil Shah, Hope McGovern, Hugo Thimonier, Indraneel Mukherjee, Irene Zhang, Jacques Sun, Jan Ludziejewski, Jason Rute, Jérémie Dentan, Joachim Studnia, Jonas Amar, Joséphine Delas, Josselin Somerville Roberts, Julien Tauran, Karmesh Yadav, Kartik Khandelwal, Kilian Tep, Kush Jain, Laurence Aitchison, Laurent Fainsin, Léonard Blier, Lingxiao Zhao, Louis Martin, Lucile Saulnier, Luyu Gao, Maarten Buyl, Manan Sharma, Marie Pellat, Mark Prins, Martin Alexandre, Mathieu Poirée, Mathieu Schmitt, Mathilde Guillaumin, Matthieu Dinot, Matthieu Futeral, Maxime Darrin, Maximilian Augustin, Mert Unsal, Mia Chiquier, Mikhail Biriuchinskii, Minh-Quang Pham, Mircea Lica, Morgane Rivière, Nathan Grinsztajn, Neha Gupta, Olivier Bousquet, Olivier Duchenne, Patricia Wang, Paul Jacob, Paul Wambergue, Paula Kurylowicz, Philippe Pinel, Philomène Chagniot, Pierre Stock, Piotr Miłoś, Prateek Gupta, Pravesh Agrawal, Quentin Torroba, Ram Ramrakhya, Randall Isenhour, Rishi Shah, Romain Sauvestre, Roman Soletskyi, Rosalie Millner, Rupert Menneer, Sagar Vaze, Samuel Barry, Samuel Belkadi, Sandeep Subramanian, Sean Cha, Shashwat Verma, Siddhant Waghjale, Siddharth Gandhi, Simon Lepage, Sumukh Aithal, Szymon Antoniak, Tarun Kumar Vangani, Teven Le Scao, Théo Cachet, Theo Simon Sorg, Thibaut Lavril, Thomas Chabal, Thomas Foubert, Thomas Robert, Thomas Wang, Tim Lawson, Tom Bewley, Tom Edwards, Tyler Wang, Umar Jamil, Umberto Tomasini, Valeriia Nemychnikova, Vedant Nanda, Victor Jouault, Vincent Maladière, Vincent Pfister, Virgile Richard, Vladislav Bataev, Wassim Bouaziz, Wen-Ding Li, William Havard, William Marshall, Xinghui Li, Xingran Guo, Xinyu Yang, Yannic Neuhaus, Yassine El Ouahidi, Yassir Bendou, Yihan Wang, Yimu Pan, Zaccharie Ramzi, Zhenlin Xu</p><p><b>Upvotes:</b> 42</p><p><b>Summary:</b> We introduce Voxtral TTS, an expressive multilingual text-to-speech model that generates natural speech from as little as 3 seconds of reference audio. Voxtral TTS adopts a hybrid architecture that combines auto-regressive generation of semantic speech tokens with flow-matching for acoustic tokens. These tokens are encoded and decoded with Voxtral Codec, a speech tokenizer trained from scratch with a hybrid VQ-FSQ quantization scheme. In human evaluations conducted by native speakers, Voxtral TTS is preferred for multilingual voice cloning due to its naturalness and expressivity, achieving a 68.4\% win rate over ElevenLabs Flash v2.5. We release the model weights under a CC BY-NC license.</p> + https://arxiv.org/abs/2603.25551 + Thu, 26 Mar 2026 15:23:34 +0000 - SAMA: Factorized Semantic Anchoring and Motion Alignment for Instruction-Guided Video Editing - https://arxiv.org/abs/2603.19228 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19228.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xinyao Zhang, Wenkai Dong, Yuxin Song, Bo Fang, Qi Zhang, Jing Wang, Fan Chen, Hui Zhang, Haocheng Feng, Yu Lu, Hang Zhou, Chun Yuan, Jingdong Wang</p><p><b>Upvotes:</b> 61</p><p><b>Summary:</b> Current instruction-guided video editing models struggle to simultaneously balance precise semantic modifications with faithful motion preservation. While existing approaches rely on injecting explicit external priors (e.g., VLM features or structural conditions) to mitigate these issues, this reliance severely bottlenecks model robustness and generalization. To overcome this limitation, we present SAMA (factorized Semantic Anchoring and Motion Alignment), a framework that factorizes video editing into semantic anchoring and motion modeling. First, we introduce Semantic Anchoring, which establishes a reliable visual anchor by jointly predicting semantic tokens and video latents at sparse anchor frames, enabling purely instruction-aware structural planning. Second, Motion Alignment pre-trains the same backbone on motion-centric video restoration pretext tasks (cube inpainting, speed perturbation, and tube shuffle), enabling the model to internalize temporal dynamics directly from raw videos. SAMA is optimized with a two-stage pipeline: a factorized pre-training stage that learns inherent semantic-motion representations without paired video-instruction editing data, followed by supervised fine-tuning on paired editing data. Remarkably, the factorized pre-training alone already yields strong zero-shot video editing ability, validating the proposed factorization. SAMA achieves state-of-the-art performance among open-source models and is competitive with leading commercial systems (e.g., Kling-Omni). Code, models, and datasets will be released.</p> - https://arxiv.org/abs/2603.19228 - Thu, 19 Mar 2026 17:59:51 +0000 + Revisiting On-Policy Distillation: Empirical Failure Modes and Simple Fixes + https://arxiv.org/abs/2603.25562 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.25562.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuqian Fu, Haohuan Huang, Kaiwen Jiang, Yuanheng Zhu, Dongbin Zhao</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> On-policy distillation (OPD) is appealing for large language model (LLM) post-training because it evaluates teacher feedback on student-generated rollouts rather than fixed teacher traces. In long-horizon settings, however, the common sampled-token variant is fragile: it reduces distribution matching to a one-token signal and becomes increasingly unreliable as rollouts drift away from prefixes the teacher commonly visits. We revisit OPD from the estimator and implementation sides. Theoretically, token-level OPD is biased relative to sequence-level reverse-KL, but it has a much tighter worst-case variance bound; our toy study shows the same tradeoff empirically, with stronger future-reward coupling producing higher gradient variance and less stable learning. Empirically, we identify three failure modes of sampled-token OPD: an imbalanced one-token signal, unreliable teacher guidance on student-generated prefixes, and distortions caused by tokenizer or special-token mismatch. We address these issues with teacher top-K local support matching, implemented as truncated reverse-KL with top-p rollout sampling and special-token masking. Across single-task math reasoning and multi-task agentic-plus-math training, this objective yields more stable optimization and better downstream performance than sampled-token OPD.</p> + https://arxiv.org/abs/2603.25562 + Thu, 26 Mar 2026 15:35:59 +0000 - MonoArt: Progressive Structural Reasoning for Monocular Articulated 3D Reconstruction - https://arxiv.org/abs/2603.19231 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19231.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haitian Li, Haozhe Xie, Junxiang Xu, Beichen Wen, Fangzhou Hong, Ziwei Liu</p><p><b>Upvotes:</b> 31</p><p><b>Summary:</b> Reconstructing articulated 3D objects from a single image requires jointly inferring object geometry, part structure, and motion parameters from limited visual evidence. A key difficulty lies in the entanglement between motion cues and object structure, which makes direct articulation regression unstable. Existing methods address this challenge through multi-view supervision, retrieval-based assembly, or auxiliary video generation, often sacrificing scalability or efficiency. We present MonoArt, a unified framework grounded in progressive structural reasoning. Rather than predicting articulation directly from image features, MonoArt progressively transforms visual observations into canonical geometry, structured part representations, and motion-aware embeddings within a single architecture. This structured reasoning process enables stable and interpretable articulation inference without external motion templates or multi-stage pipelines. Extensive experiments on PartNet-Mobility demonstrate that OM achieves state-of-the-art performance in both reconstruction accuracy and inference speed. The framework further generalizes to robotic manipulation and articulated scene reconstruction.</p> - https://arxiv.org/abs/2603.19231 - Thu, 19 Mar 2026 17:59:52 +0000 + PixelSmile: Toward Fine-Grained Facial Expression Editing + https://arxiv.org/abs/2603.25728 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.25728.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiabin Hua, Hengyuan Xu, Aojie Li, Wei Cheng, Gang Yu, Xingjun Ma, Yu-Gang Jiang</p><p><b>Upvotes:</b> 111</p><p><b>Summary:</b> Fine-grained facial expression editing has long been limited by intrinsic semantic overlap. To address this, we construct the Flex Facial Expression (FFE) dataset with continuous affective annotations and establish FFE-Bench to evaluate structural confusion, editing accuracy, linear controllability, and the trade-off between expression editing and identity preservation. We propose PixelSmile, a diffusion framework that disentangles expression semantics via fully symmetric joint training. PixelSmile combines intensity supervision with contrastive learning to produce stronger and more distinguishable expressions, achieving precise and stable linear expression control through textual latent interpolation. Extensive experiments demonstrate that PixelSmile achieves superior disentanglement and robust identity preservation, confirming its effectiveness for continuous, controllable, and fine-grained expression editing, while naturally supporting smooth expression blending.</p> + https://arxiv.org/abs/2603.25728 + Thu, 26 Mar 2026 17:59:04 +0000 - Cubic Discrete Diffusion: Discrete Visual Generation on High-Dimensional Representation Tokens - https://arxiv.org/abs/2603.19232 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19232.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuqing Wang, Chuofan Ma, Zhijie Lin, Yao Teng, Lijun Yu, Shuai Wang, Jiaming Han, Jiashi Feng, Yi Jiang, Xihui Liu</p><p><b>Upvotes:</b> 30</p><p><b>Summary:</b> Visual generation with discrete tokens has gained significant attention as it enables a unified token prediction paradigm shared with language models, promising seamless multimodal architectures. However, current discrete generation methods remain limited to low-dimensional latent tokens (typically 8-32 dims), sacrificing the semantic richness essential for understanding. While high-dimensional pretrained representations (768-1024 dims) could bridge this gap, their discrete generation poses fundamental challenges. In this paper, we present Cubic Discrete Diffusion (CubiD), the first discrete generation model for high-dimensional representations. CubiD performs fine-grained masking throughout the high-dimensional discrete representation -- any dimension at any position can be masked and predicted from partial observations. This enables the model to learn rich correlations both within and across spatial positions, with the number of generation steps fixed at T regardless of feature dimensionality, where T ll hwd. On ImageNet-256, CubiD achieves state-of-the-art discrete generation with strong scaling behavior from 900M to 3.7B parameters. Crucially, we validate that these discretized tokens preserve original representation capabilities, demonstrating that the same discrete tokens can effectively serve both understanding and generation tasks. We hope this work will inspire future research toward unified multimodal architectures. Code is available at: https://github.com/YuqingWang1029/CubiD.</p> - https://arxiv.org/abs/2603.19232 - Thu, 19 Mar 2026 17:59:55 +0000 + MuRF: Unlocking the Multi-Scale Potential of Vision Foundation Models + https://arxiv.org/abs/2603.25744 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.25744.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bocheng Zou, Mu Cai, Mark Stanley, Dingfu Lu, Yong Jae Lee</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Vision Foundation Models (VFMs) have become the cornerstone of modern computer vision, offering robust representations across a wide array of tasks. While recent advances allow these models to handle varying input sizes during training, inference typically remains restricted to a single, fixed scale. This prevalent single-scale paradigm overlooks a fundamental property of visual perception: varying resolutions offer complementary inductive biases, where low-resolution views excel at global semantic recognition and high-resolution views are essential for fine-grained refinement. In this work, we propose Multi-Resolution Fusion (MuRF), a simple yet universally effective strategy to harness this synergy at inference time. Instead of relying on a single view, MuRF constructs a unified representation by processing an image at multiple resolutions through a frozen VFM and fusing the resulting features. The universality of MuRF is its most compelling attribute. It is not tied to a specific architecture, serving instead as a fundamental, training-free enhancement to visual representation. We empirically validate this by applying MuRF to a broad spectrum of critical computer vision tasks across multiple distinct VFM families - primarily DINOv2, but also demonstrating successful generalization to contrastive models like SigLIP2.</p> + https://arxiv.org/abs/2603.25744 + Thu, 26 Mar 2026 17:59:58 +0000 - Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding - https://arxiv.org/abs/2603.19235 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19235.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xianjin Wu, Dingkang Liang, Tianrui Feng, Kui Xia, Yumeng Zhang, Xiaofan Li, Xiao Tan, Xiang Bai</p><p><b>Upvotes:</b> 84</p><p><b>Summary:</b> While Multimodal Large Language Models demonstrate impressive semantic capabilities, they often suffer from spatial blindness, struggling with fine-grained geometric reasoning and physical dynamics. Existing solutions typically rely on explicit 3D modalities or complex geometric scaffolding, which are limited by data scarcity and generalization challenges. In this work, we propose a paradigm shift by leveraging the implicit spatial prior within large-scale video generation models. We posit that to synthesize temporally coherent videos, these models inherently learn robust 3D structural priors and physical laws. We introduce VEGA-3D (Video Extracted Generative Awareness), a plug-and-play framework that repurposes a pre-trained video diffusion model as a Latent World Simulator. By extracting spatiotemporal features from intermediate noise levels and integrating them with semantic representations via a token-level adaptive gated fusion mechanism, we enrich MLLMs with dense geometric cues without explicit 3D supervision. Extensive experiments across 3D scene understanding, spatial reasoning, and embodied manipulation benchmarks demonstrate that our method outperforms state-of-the-art baselines, validating that generative priors provide a scalable foundation for physical-world understanding. Code is publicly available at https://github.com/H-EmbodVis/VEGA-3D.</p> - https://arxiv.org/abs/2603.19235 - Thu, 19 Mar 2026 17:59:58 +0000 + Less Gaussians, Texture More: 4K Feed-Forward Textured Splatting + https://arxiv.org/abs/2603.25745 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.25745.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yixing Lao, Xuyang Bai, Xiaoyang Wu, Nuoyuan Yan, Zixin Luo, Tian Fang, Jean-Daniel Nahmias, Yanghai Tsin, Shiwei Li, Hengshuang Zhao</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Existing feed-forward 3D Gaussian Splatting methods predict pixel-aligned primitives, leading to a quadratic growth in primitive count as resolution increases. This fundamentally limits their scalability, making high-resolution synthesis such as 4K intractable. We introduce LGTM (Less Gaussians, Texture More), a feed-forward framework that overcomes this resolution scaling barrier. By predicting compact Gaussian primitives coupled with per-primitive textures, LGTM decouples geometric complexity from rendering resolution. This approach enables high-fidelity 4K novel view synthesis without per-scene optimization, a capability previously out of reach for feed-forward methods, all while using significantly fewer Gaussian primitives. Project page: https://yxlao.github.io/lgtm/</p> + https://arxiv.org/abs/2603.25745 + Thu, 26 Mar 2026 17:59:59 +0000