bot: update RSS feed
This commit is contained in:
github-actions[bot]
38
feed.xml
38
feed.xml
@@ -7,39 +7,39 @@
|
||||
<docs>http://www.rssboard.org/rss-specification</docs>
|
||||
<generator>python-feedgen</generator>
|
||||
<language>en</language>
|
||||
<lastBuildDate>Sat, 07 Mar 2026 00:03:56 +0000</lastBuildDate>
|
||||
<lastBuildDate>Sun, 08 Mar 2026 00:02:58 +0000</lastBuildDate>
|
||||
<item>
|
||||
<title>SkillNet: Create, Evaluate, and Connect AI Skills</title>
|
||||
<link>https://arxiv.org/abs/2603.04448</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.04448.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuan Liang, Ruobin Zhong, Haoming Xu, Chen Jiang, Yi Zhong, Runnan Fang, Jia-Chen Gu, Shumin Deng, Yunzhi Yao, Mengru Wang, Shuofei Qiao, Xin Xu, Tongtong Wu, Kun Wang, Yang Liu, Zhen Bi, Jungang Lou, Yuchen Eleanor Jiang, Hangcheng Zhu, Gang Yu, Haiwen Hong, Longtao Huang, Hui Xue, Chenxi Wang, Yijun Wang, Zifei Shan, Xi Chen, Zhaopeng Tu, Feiyu Xiong, Xin Xie, Peng Zhang, Zhengke Gui, Lei Liang, Jun Zhou, Chiyu Wu, Jin Shang, Yu Gong, Junyu Lin, Changliang Xu, Hongjie Deng, Wen Zhang, Keyan Ding, Qiang Zhang, Fei Huang, Ningyu Zhang, Jeff Z. Pan, Guilin Qi, Haofen Wang, Huajun Chen</p><p><b>Upvotes:</b> 43</p><p><b>Summary:</b> Current AI agents can flexibly invoke tools and execute complex tasks, yet their long-term advancement is hindered by the lack of systematic accumulation and transfer of skills. Without a unified mechanism for skill consolidation, agents frequently ``reinvent the wheel'', rediscovering solutions in isolated contexts without leveraging prior strategies. To overcome this limitation, we introduce SkillNet, an open infrastructure designed to create, evaluate, and organize AI skills at scale. SkillNet structures skills within a unified ontology that supports creating skills from heterogeneous sources, establishing rich relational connections, and performing multi-dimensional evaluation across Safety, Completeness, Executability, Maintainability, and Cost-awareness. Our infrastructure integrates a repository of over 200,000 skills, an interactive platform, and a versatile Python toolkit. Experimental evaluations on ALFWorld, WebShop, and ScienceWorld demonstrate that SkillNet significantly enhances agent performance, improving average rewards by 40% and reducing execution steps by 30% across multiple backbone models. By formalizing skills as evolving, composable assets, SkillNet provides a robust foundation for agents to move from transient experience to durable mastery.</p></description>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.04448.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuan Liang, Ruobin Zhong, Haoming Xu, Chen Jiang, Yi Zhong, Runnan Fang, Jia-Chen Gu, Shumin Deng, Yunzhi Yao, Mengru Wang, Shuofei Qiao, Xin Xu, Tongtong Wu, Kun Wang, Yang Liu, Zhen Bi, Jungang Lou, Yuchen Eleanor Jiang, Hangcheng Zhu, Gang Yu, Haiwen Hong, Longtao Huang, Hui Xue, Chenxi Wang, Yijun Wang, Zifei Shan, Xi Chen, Zhaopeng Tu, Feiyu Xiong, Xin Xie, Peng Zhang, Zhengke Gui, Lei Liang, Jun Zhou, Chiyu Wu, Jin Shang, Yu Gong, Junyu Lin, Changliang Xu, Hongjie Deng, Wen Zhang, Keyan Ding, Qiang Zhang, Fei Huang, Ningyu Zhang, Jeff Z. Pan, Guilin Qi, Haofen Wang, Huajun Chen</p><p><b>Upvotes:</b> 55</p><p><b>Summary:</b> Current AI agents can flexibly invoke tools and execute complex tasks, yet their long-term advancement is hindered by the lack of systematic accumulation and transfer of skills. Without a unified mechanism for skill consolidation, agents frequently ``reinvent the wheel'', rediscovering solutions in isolated contexts without leveraging prior strategies. To overcome this limitation, we introduce SkillNet, an open infrastructure designed to create, evaluate, and organize AI skills at scale. SkillNet structures skills within a unified ontology that supports creating skills from heterogeneous sources, establishing rich relational connections, and performing multi-dimensional evaluation across Safety, Completeness, Executability, Maintainability, and Cost-awareness. Our infrastructure integrates a repository of over 200,000 skills, an interactive platform, and a versatile Python toolkit. Experimental evaluations on ALFWorld, WebShop, and ScienceWorld demonstrate that SkillNet significantly enhances agent performance, improving average rewards by 40% and reducing execution steps by 30% across multiple backbone models. By formalizing skills as evolving, composable assets, SkillNet provides a robust foundation for agents to move from transient experience to durable mastery.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.04448</guid>
|
||||
<pubDate>Thu, 26 Feb 2026 14:24:02 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>AgentVista: Evaluating Multimodal Agents in Ultra-Challenging Realistic Visual Scenarios</title>
|
||||
<link>https://arxiv.org/abs/2602.23166</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.23166.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhaochen Su, Jincheng Gao, Hangyu Guo, Zhenhua Liu, Lueyang Zhang, Xinyu Geng, Shijue Huang, Peng Xia, Guanyu Jiang, Cheng Wang, Yue Zhang, Yi R. Fung, Junxian He</p><p><b>Upvotes:</b> 29</p><p><b>Summary:</b> Real-world multimodal agents solve multi-step workflows grounded in visual evidence. For example, an agent can troubleshoot a device by linking a wiring photo to a schematic and validating the fix with online documentation, or plan a trip by interpreting a transit map and checking schedules under routing constraints. However, existing multimodal benchmarks mainly evaluate single-turn visual reasoning or specific tool skills, and they do not fully capture the realism, visual subtlety, and long-horizon tool use that practical agents require. We introduce AgentVista, a benchmark for generalist multimodal agents that spans 25 sub-domains across 7 categories, pairing realistic and detail-rich visual scenarios with natural hybrid tool use. Tasks require long-horizon tool interactions across modalities, including web search, image search, page navigation, and code-based operations for both image processing and general programming. Comprehensive evaluation of state-of-the-art models exposes significant gaps in their ability to carry out long-horizon multimodal tool use. Even the best model in our evaluation, Gemini-3-Pro with tools, achieves only 27.3% overall accuracy, and hard instances can require more than 25 tool-calling turns. We expect AgentVista to accelerate the development of more capable and reliable multimodal agents for realistic and ultra-challenging problem solving.</p></description>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.23166.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhaochen Su, Jincheng Gao, Hangyu Guo, Zhenhua Liu, Lueyang Zhang, Xinyu Geng, Shijue Huang, Peng Xia, Guanyu Jiang, Cheng Wang, Yue Zhang, Yi R. Fung, Junxian He</p><p><b>Upvotes:</b> 31</p><p><b>Summary:</b> Real-world multimodal agents solve multi-step workflows grounded in visual evidence. For example, an agent can troubleshoot a device by linking a wiring photo to a schematic and validating the fix with online documentation, or plan a trip by interpreting a transit map and checking schedules under routing constraints. However, existing multimodal benchmarks mainly evaluate single-turn visual reasoning or specific tool skills, and they do not fully capture the realism, visual subtlety, and long-horizon tool use that practical agents require. We introduce AgentVista, a benchmark for generalist multimodal agents that spans 25 sub-domains across 7 categories, pairing realistic and detail-rich visual scenarios with natural hybrid tool use. Tasks require long-horizon tool interactions across modalities, including web search, image search, page navigation, and code-based operations for both image processing and general programming. Comprehensive evaluation of state-of-the-art models exposes significant gaps in their ability to carry out long-horizon multimodal tool use. Even the best model in our evaluation, Gemini-3-Pro with tools, achieves only 27.3% overall accuracy, and hard instances can require more than 25 tool-calling turns. We expect AgentVista to accelerate the development of more capable and reliable multimodal agents for realistic and ultra-challenging problem solving.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.23166</guid>
|
||||
<pubDate>Thu, 26 Feb 2026 16:30:46 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Large Multimodal Models as General In-Context Classifiers</title>
|
||||
<link>https://arxiv.org/abs/2602.23229</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.23229.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Marco Garosi, Matteo Farina, Alessandro Conti, Massimiliano Mancini, Elisa Ricci</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Which multimodal model should we use for classification? Previous studies suggest that the answer lies in CLIP-like contrastive Vision-Language Models (VLMs), due to their remarkable performance in zero-shot classification. In contrast, Large Multimodal Models (LMM) are more suitable for complex tasks. In this work, we argue that this answer overlooks an important capability of LMMs: in-context learning. We benchmark state-of-the-art LMMs on diverse datasets for closed-world classification and find that, although their zero-shot performance is lower than CLIP's, LMMs with a few in-context examples can match or even surpass contrastive VLMs with cache-based adapters, their "in-context" equivalent. We extend this analysis to the open-world setting, where the generative nature of LMMs makes them more suitable for the task. In this challenging scenario, LMMs struggle whenever provided with imperfect context information. To address this issue, we propose CIRCLE, a simple training-free method that assigns pseudo-labels to in-context examples, iteratively refining them with the available context itself. Through extensive experiments, we show that CIRCLE establishes a robust baseline for open-world classification, surpassing VLM counterparts and highlighting the potential of LMMs to serve as unified classifiers, and a flexible alternative to specialized models.</p></description>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.23229.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Marco Garosi, Matteo Farina, Alessandro Conti, Massimiliano Mancini, Elisa Ricci</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Which multimodal model should we use for classification? Previous studies suggest that the answer lies in CLIP-like contrastive Vision-Language Models (VLMs), due to their remarkable performance in zero-shot classification. In contrast, Large Multimodal Models (LMM) are more suitable for complex tasks. In this work, we argue that this answer overlooks an important capability of LMMs: in-context learning. We benchmark state-of-the-art LMMs on diverse datasets for closed-world classification and find that, although their zero-shot performance is lower than CLIP's, LMMs with a few in-context examples can match or even surpass contrastive VLMs with cache-based adapters, their "in-context" equivalent. We extend this analysis to the open-world setting, where the generative nature of LMMs makes them more suitable for the task. In this challenging scenario, LMMs struggle whenever provided with imperfect context information. To address this issue, we propose CIRCLE, a simple training-free method that assigns pseudo-labels to in-context examples, iteratively refining them with the available context itself. Through extensive experiments, we show that CIRCLE establishes a robust baseline for open-world classification, surpassing VLM counterparts and highlighting the potential of LMMs to serve as unified classifiers, and a flexible alternative to specialized models.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.23229</guid>
|
||||
<pubDate>Thu, 26 Feb 2026 17:08:18 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Truncated Step-Level Sampling with Process Rewards for Retrieval-Augmented Reasoning</title>
|
||||
<link>https://arxiv.org/abs/2602.23440</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.23440.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chris Samarinas, Haw-Shiuan Chang, Hamed Zamani</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Training large language models to reason with search engines via reinforcement learning is hindered by a fundamental credit assignment problem: existing methods such as Search-R1 provide only a sparse outcome reward after an entire multi-step trajectory, making it infeasible to attribute success or failure to individual reasoning and retrieval decisions. Process-reward methods like StepSearch alleviate this by introducing step-level supervision, but rely on heuristic rewards such as TF-IDF overlap with gold documents, and still sample k complete trajectories per example, retaining high gradient variance. We propose SLATE, a framework built on two complementary ideas: (1) truncated step-level sampling, which generates k trajectories that share a common prefix and differ only at the next step, and (2) dense LLM-as-judge rewards, which replace heuristic scoring with a capable LLM evaluator that assesses the quality of each reasoning step, search query, and answer, providing richer and more reliable supervision. We theoretically prove that under the same dense reward structure, truncated sampling reduces the variance of advantage estimates by up to a factor of T compared to full-trajectory sampling for T-step trajectories, yielding lower-variance, better-targeted policy gradients. Experiments on seven QA benchmarks confirm that SLATE consistently outperforms both sparse-reward and process-reward baselines, with the largest gains on harder multi-hop tasks and smaller models.</p></description>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.23440.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chris Samarinas, Haw-Shiuan Chang, Hamed Zamani</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Training large language models to reason with search engines via reinforcement learning is hindered by a fundamental credit assignment problem: existing methods such as Search-R1 provide only a sparse outcome reward after an entire multi-step trajectory, making it infeasible to attribute success or failure to individual reasoning and retrieval decisions. Process-reward methods like StepSearch alleviate this by introducing step-level supervision, but rely on heuristic rewards such as TF-IDF overlap with gold documents, and still sample k complete trajectories per example, retaining high gradient variance. We propose SLATE, a framework built on two complementary ideas: (1) truncated step-level sampling, which generates k trajectories that share a common prefix and differ only at the next step, and (2) dense LLM-as-judge rewards, which replace heuristic scoring with a capable LLM evaluator that assesses the quality of each reasoning step, search query, and answer, providing richer and more reliable supervision. We theoretically prove that under the same dense reward structure, truncated sampling reduces the variance of advantage estimates by up to a factor of T compared to full-trajectory sampling for T-step trajectories, yielding lower-variance, better-targeted policy gradients. Experiments on seven QA benchmarks confirm that SLATE consistently outperforms both sparse-reward and process-reward baselines, with the largest gains on harder multi-hop tasks and smaller models.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.23440</guid>
|
||||
<pubDate>Thu, 26 Feb 2026 19:05:40 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>DreamWorld: Unified World Modeling in Video Generation</title>
|
||||
<link>https://arxiv.org/abs/2603.00466</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.00466.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Boming Tan, Xiangdong Zhang, Ning Liao, Yuqing Zhang, Shaofeng Zhang, Xue Yang, Qi Fan, Yanyong Zhang</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Despite impressive progress in video generation, existing models remain limited to surface-level plausibility, lacking a coherent and unified understanding of the world. Prior approaches typically incorporate only a single form of world-related knowledge or rely on rigid alignment strategies to introduce additional knowledge. However, aligning the single world knowledge is insufficient to constitute a world model that requires jointly modeling multiple heterogeneous dimensions (e.g., physical commonsense, 3D and temporal consistency). To address this limitation, we introduce DreamWorld, a unified framework that integrates complementary world knowledge into video generators via a Joint World Modeling Paradigm, jointly predicting video pixels and features from foundation models to capture temporal dynamics, spatial geometry, and semantic consistency. However, naively optimizing these heterogeneous objectives can lead to visual instability and temporal flickering. To mitigate this issue, we propose Consistent Constraint Annealing (CCA) to progressively regulate world-level constraints during training, and Multi-Source Inner-Guidance to enforce learned world priors at inference. Extensive evaluations show that DreamWorld improves world consistency, outperforming Wan2.1 by 2.26 points on VBench. Code will be made publicly available at https://github.com/ABU121111/DreamWorld{mypink{Github}}.</p></description>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.00466.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Boming Tan, Xiangdong Zhang, Ning Liao, Yuqing Zhang, Shaofeng Zhang, Xue Yang, Qi Fan, Yanyong Zhang</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Despite impressive progress in video generation, existing models remain limited to surface-level plausibility, lacking a coherent and unified understanding of the world. Prior approaches typically incorporate only a single form of world-related knowledge or rely on rigid alignment strategies to introduce additional knowledge. However, aligning the single world knowledge is insufficient to constitute a world model that requires jointly modeling multiple heterogeneous dimensions (e.g., physical commonsense, 3D and temporal consistency). To address this limitation, we introduce DreamWorld, a unified framework that integrates complementary world knowledge into video generators via a Joint World Modeling Paradigm, jointly predicting video pixels and features from foundation models to capture temporal dynamics, spatial geometry, and semantic consistency. However, naively optimizing these heterogeneous objectives can lead to visual instability and temporal flickering. To mitigate this issue, we propose Consistent Constraint Annealing (CCA) to progressively regulate world-level constraints during training, and Multi-Source Inner-Guidance to enforce learned world priors at inference. Extensive evaluations show that DreamWorld improves world consistency, outperforming Wan2.1 by 2.26 points on VBench. Code will be made publicly available at https://github.com/ABU121111/DreamWorld{mypink{Github}}.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.00466</guid>
|
||||
<pubDate>Sat, 28 Feb 2026 05:02:39 +0000</pubDate>
|
||||
</item>
|
||||
@@ -53,14 +53,14 @@
|
||||
<item>
|
||||
<title>SageBwd: A Trainable Low-bit Attention</title>
|
||||
<link>https://arxiv.org/abs/2603.02170</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.02170.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jintao Zhang, Marco Chen, Haoxu Wang, Kai Jiang, Ion Stoica, Joseph E. Gonzalez, Jianfei Chen, Jun Zhu</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Low-bit attention, such as SageAttention, has emerged as an effective approach for accelerating model inference, but its applicability to training remains poorly understood. In prior work, we introduced SageBwd, a trainable INT8 attention that quantizes six of seven attention matrix multiplications while preserving fine-tuning performance. However, SageBwd exhibited a persistent performance gap to full-precision attention (FPA) during pre-training. In this work, we investigate why this gap occurs and demonstrate that SageBwd matches full-precision attention during pretraining. Through experiments and theoretical analysis, we reach a few important insights and conclusions: (i) QK-norm is necessary for stable training at large tokens per step, (ii) quantization errors primarily arise from the backward-pass score gradient dS, (iii) reducing tokens per step enables SageBwd to match FPA performance in pre-training, and (iv) K-smoothing remains essential for training stability, while Q-smoothing provides limited benefit during pre-training.</p></description>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.02170.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jintao Zhang, Marco Chen, Haoxu Wang, Kai Jiang, Ion Stoica, Joseph E. Gonzalez, Jianfei Chen, Jun Zhu</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Low-bit attention, such as SageAttention, has emerged as an effective approach for accelerating model inference, but its applicability to training remains poorly understood. In prior work, we introduced SageBwd, a trainable INT8 attention that quantizes six of seven attention matrix multiplications while preserving fine-tuning performance. However, SageBwd exhibited a persistent performance gap to full-precision attention (FPA) during pre-training. In this work, we investigate why this gap occurs and demonstrate that SageBwd matches full-precision attention during pretraining. Through experiments and theoretical analysis, we reach a few important insights and conclusions: (i) QK-norm is necessary for stable training at large tokens per step, (ii) quantization errors primarily arise from the backward-pass score gradient dS, (iii) reducing tokens per step enables SageBwd to match FPA performance in pre-training, and (iv) K-smoothing remains essential for training stability, while Q-smoothing provides limited benefit during pre-training.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.02170</guid>
|
||||
<pubDate>Mon, 02 Mar 2026 18:39:49 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>HiFi-Inpaint: Towards High-Fidelity Reference-Based Inpainting for Generating Detail-Preserving Human-Product Images</title>
|
||||
<link>https://arxiv.org/abs/2603.02210</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.02210.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yichen Liu, Donghao Zhou, Jie Wang, Xin Gao, Guisheng Liu, Jiatong Li, Quanwei Zhang, Qiang Lyu, Lanqing Guo, Shilei Wen, Weiqiang Wang, Pheng-Ann Heng</p><p><b>Upvotes:</b> 24</p><p><b>Summary:</b> Human-product images, which showcase the integration of humans and products, play a vital role in advertising, e-commerce, and digital marketing. The essential challenge of generating such images lies in ensuring the high-fidelity preservation of product details. Among existing paradigms, reference-based inpainting offers a targeted solution by leveraging product reference images to guide the inpainting process. However, limitations remain in three key aspects: the lack of diverse large-scale training data, the struggle of current models to focus on product detail preservation, and the inability of coarse supervision for achieving precise guidance. To address these issues, we propose HiFi-Inpaint, a novel high-fidelity reference-based inpainting framework tailored for generating human-product images. HiFi-Inpaint introduces Shared Enhancement Attention (SEA) to refine fine-grained product features and Detail-Aware Loss (DAL) to enforce precise pixel-level supervision using high-frequency maps. Additionally, we construct a new dataset, HP-Image-40K, with samples curated from self-synthesis data and processed with automatic filtering. Experimental results show that HiFi-Inpaint achieves state-of-the-art performance, delivering detail-preserving human-product images.</p></description>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.02210.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yichen Liu, Donghao Zhou, Jie Wang, Xin Gao, Guisheng Liu, Jiatong Li, Quanwei Zhang, Qiang Lyu, Lanqing Guo, Shilei Wen, Weiqiang Wang, Pheng-Ann Heng</p><p><b>Upvotes:</b> 25</p><p><b>Summary:</b> Human-product images, which showcase the integration of humans and products, play a vital role in advertising, e-commerce, and digital marketing. The essential challenge of generating such images lies in ensuring the high-fidelity preservation of product details. Among existing paradigms, reference-based inpainting offers a targeted solution by leveraging product reference images to guide the inpainting process. However, limitations remain in three key aspects: the lack of diverse large-scale training data, the struggle of current models to focus on product detail preservation, and the inability of coarse supervision for achieving precise guidance. To address these issues, we propose HiFi-Inpaint, a novel high-fidelity reference-based inpainting framework tailored for generating human-product images. HiFi-Inpaint introduces Shared Enhancement Attention (SEA) to refine fine-grained product features and Detail-Aware Loss (DAL) to enforce precise pixel-level supervision using high-frequency maps. Additionally, we construct a new dataset, HP-Image-40K, with samples curated from self-synthesis data and processed with automatic filtering. Experimental results show that HiFi-Inpaint achieves state-of-the-art performance, delivering detail-preserving human-product images.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.02210</guid>
|
||||
<pubDate>Mon, 02 Mar 2026 18:59:36 +0000</pubDate>
|
||||
</item>
|
||||
@@ -74,7 +74,7 @@
|
||||
<item>
|
||||
<title>MOOSE-Star: Unlocking Tractable Training for Scientific Discovery by Breaking the Complexity Barrier</title>
|
||||
<link>https://arxiv.org/abs/2603.03756</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.03756.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zonglin Yang, Lidong Bing</p><p><b>Upvotes:</b> 74</p><p><b>Summary:</b> While large language models (LLMs) show promise in scientific discovery, existing research focuses on inference or feedback-driven training, leaving the direct modeling of the generative reasoning process, P(hypothesis|background) (P(h|b)), unexplored. We demonstrate that directly training P(h|b) is mathematically intractable due to the combinatorial complexity (O(N^k)) inherent in retrieving and composing inspirations from a vast knowledge base. To break this barrier, we introduce MOOSE-Star, a unified framework enabling tractable training and scalable inference. In the best case, MOOSE-Star reduces complexity from exponential to logarithmic (O(log N)) by (1) training on decomposed subtasks derived from the probabilistic equation of discovery, (2) employing motivation-guided hierarchical search to enable logarithmic retrieval and prune irrelevant subspaces, and (3) utilizing bounded composition for robustness against retrieval noise. To facilitate this, we release TOMATO-Star, a dataset of 108,717 decomposed papers (38,400 GPU hours) for training. Furthermore, we show that while brute-force sampling hits a ''complexity wall,'' MOOSE-Star exhibits continuous test-time scaling.</p></description>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.03756.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zonglin Yang, Lidong Bing</p><p><b>Upvotes:</b> 77</p><p><b>Summary:</b> While large language models (LLMs) show promise in scientific discovery, existing research focuses on inference or feedback-driven training, leaving the direct modeling of the generative reasoning process, P(hypothesis|background) (P(h|b)), unexplored. We demonstrate that directly training P(h|b) is mathematically intractable due to the combinatorial complexity (O(N^k)) inherent in retrieving and composing inspirations from a vast knowledge base. To break this barrier, we introduce MOOSE-Star, a unified framework enabling tractable training and scalable inference. In the best case, MOOSE-Star reduces complexity from exponential to logarithmic (O(log N)) by (1) training on decomposed subtasks derived from the probabilistic equation of discovery, (2) employing motivation-guided hierarchical search to enable logarithmic retrieval and prune irrelevant subspaces, and (3) utilizing bounded composition for robustness against retrieval noise. To facilitate this, we release TOMATO-Star, a dataset of 108,717 decomposed papers (38,400 GPU hours) for training. Furthermore, we show that while brute-force sampling hits a ''complexity wall,'' MOOSE-Star exhibits continuous test-time scaling.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.03756</guid>
|
||||
<pubDate>Wed, 04 Mar 2026 06:11:18 +0000</pubDate>
|
||||
</item>
|
||||
@@ -95,28 +95,28 @@
|
||||
<item>
|
||||
<title>Distribution-Conditioned Transport</title>
|
||||
<link>https://arxiv.org/abs/2603.04736</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.04736.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Nic Fishman, Gokul Gowri, Paolo L. B. Fischer, Marinka Zitnik, Omar Abudayyeh, Jonathan Gootenberg</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Learning a transport model that maps a source distribution to a target distribution is a canonical problem in machine learning, but scientific applications increasingly require models that can generalize to source and target distributions unseen during training. We introduce distribution-conditioned transport (DCT), a framework that conditions transport maps on learned embeddings of source and target distributions, enabling generalization to unseen distribution pairs. DCT also allows semi-supervised learning for distributional forecasting problems: because it learns from arbitrary distribution pairs, it can leverage distributions observed at only one condition to improve transport prediction. DCT is agnostic to the underlying transport mechanism, supporting models ranging from flow matching to distributional divergence-based models (e.g. Wasserstein, MMD). We demonstrate the practical performance benefits of DCT on synthetic benchmarks and four applications in biology: batch effect transfer in single-cell genomics, perturbation prediction from mass cytometry data, learning clonal transcriptional dynamics in hematopoiesis, and modeling T-cell receptor sequence evolution.</p></description>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.04736.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Nic Fishman, Gokul Gowri, Paolo L. B. Fischer, Marinka Zitnik, Omar Abudayyeh, Jonathan Gootenberg</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Learning a transport model that maps a source distribution to a target distribution is a canonical problem in machine learning, but scientific applications increasingly require models that can generalize to source and target distributions unseen during training. We introduce distribution-conditioned transport (DCT), a framework that conditions transport maps on learned embeddings of source and target distributions, enabling generalization to unseen distribution pairs. DCT also allows semi-supervised learning for distributional forecasting problems: because it learns from arbitrary distribution pairs, it can leverage distributions observed at only one condition to improve transport prediction. DCT is agnostic to the underlying transport mechanism, supporting models ranging from flow matching to distributional divergence-based models (e.g. Wasserstein, MMD). We demonstrate the practical performance benefits of DCT on synthetic benchmarks and four applications in biology: batch effect transfer in single-cell genomics, perturbation prediction from mass cytometry data, learning clonal transcriptional dynamics in hematopoiesis, and modeling T-cell receptor sequence evolution.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.04736</guid>
|
||||
<pubDate>Thu, 05 Mar 2026 02:17:08 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Interactive Benchmarks</title>
|
||||
<link>https://arxiv.org/abs/2603.04737</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.04737.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Baoqing Yue, Zihan Zhu, Yifan Zhang, Jichen Feng, Hufei Yang, Mengdi Wang</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Standard benchmarks have become increasingly unreliable due to saturation, subjectivity, and poor generalization. We argue that evaluating model's ability to acquire information actively is important to assess model's intelligence. We propose Interactive Benchmarks, a unified evaluation paradigm that assesses model's reasoning ability in an interactive process under budget constraints. We instantiate this framework across two settings: Interactive Proofs, where models interact with a judge to deduce objective truths or answers in logic and mathematics; and Interactive Games, where models reason strategically to maximize long-horizon utilities. Our results show that interactive benchmarks provide a robust and faithful assessment of model intelligence, revealing that there is still substantial room to improve in interactive scenarios. Project page: https://github.com/interactivebench/interactivebench</p></description>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.04737.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Baoqing Yue, Zihan Zhu, Yifan Zhang, Jichen Feng, Hufei Yang, Mengdi Wang</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Standard benchmarks have become increasingly unreliable due to saturation, subjectivity, and poor generalization. We argue that evaluating model's ability to acquire information actively is important to assess model's intelligence. We propose Interactive Benchmarks, a unified evaluation paradigm that assesses model's reasoning ability in an interactive process under budget constraints. We instantiate this framework across two settings: Interactive Proofs, where models interact with a judge to deduce objective truths or answers in logic and mathematics; and Interactive Games, where models reason strategically to maximize long-horizon utilities. Our results show that interactive benchmarks provide a robust and faithful assessment of model intelligence, revealing that there is still substantial room to improve in interactive scenarios. Project page: https://github.com/interactivebench/interactivebench</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.04737</guid>
|
||||
<pubDate>Thu, 05 Mar 2026 02:18:26 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>DARE: Aligning LLM Agents with the R Statistical Ecosystem via Distribution-Aware Retrieval</title>
|
||||
<link>https://arxiv.org/abs/2603.04743</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.04743.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Maojun Sun, Yue Wu, Yifei Xie, Ruijian Han, Binyan Jiang, Defeng Sun, Yancheng Yuan, Jian Huang</p><p><b>Upvotes:</b> 41</p><p><b>Summary:</b> Large Language Model (LLM) agents can automate data-science workflows, but many rigorous statistical methods implemented in R remain underused because LLMs struggle with statistical knowledge and tool retrieval. Existing retrieval-augmented approaches focus on function-level semantics and ignore data distribution, producing suboptimal matches. We propose DARE (Distribution-Aware Retrieval Embedding), a lightweight, plug-and-play retrieval model that incorporates data distribution information into function representations for R package retrieval. Our main contributions are: (i) RPKB, a curated R Package Knowledge Base derived from 8,191 high-quality CRAN packages; (ii) DARE, an embedding model that fuses distributional features with function metadata to improve retrieval relevance; and (iii) RCodingAgent, an R-oriented LLM agent for reliable R code generation and a suite of statistical analysis tasks for systematically evaluating LLM agents in realistic analytical scenarios. Empirically, DARE achieves an NDCG at 10 of 93.47%, outperforming state-of-the-art open-source embedding models by up to 17% on package retrieval while using substantially fewer parameters. Integrating DARE into RCodingAgent yields significant gains on downstream analysis tasks. This work helps narrow the gap between LLM automation and the mature R statistical ecosystem.</p></description>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.04743.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Maojun Sun, Yue Wu, Yifei Xie, Ruijian Han, Binyan Jiang, Defeng Sun, Yancheng Yuan, Jian Huang</p><p><b>Upvotes:</b> 42</p><p><b>Summary:</b> Large Language Model (LLM) agents can automate data-science workflows, but many rigorous statistical methods implemented in R remain underused because LLMs struggle with statistical knowledge and tool retrieval. Existing retrieval-augmented approaches focus on function-level semantics and ignore data distribution, producing suboptimal matches. We propose DARE (Distribution-Aware Retrieval Embedding), a lightweight, plug-and-play retrieval model that incorporates data distribution information into function representations for R package retrieval. Our main contributions are: (i) RPKB, a curated R Package Knowledge Base derived from 8,191 high-quality CRAN packages; (ii) DARE, an embedding model that fuses distributional features with function metadata to improve retrieval relevance; and (iii) RCodingAgent, an R-oriented LLM agent for reliable R code generation and a suite of statistical analysis tasks for systematically evaluating LLM agents in realistic analytical scenarios. Empirically, DARE achieves an NDCG at 10 of 93.47%, outperforming state-of-the-art open-source embedding models by up to 17% on package retrieval while using substantially fewer parameters. Integrating DARE into RCodingAgent yields significant gains on downstream analysis tasks. This work helps narrow the gap between LLM automation and the mature R statistical ecosystem.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.04743</guid>
|
||||
<pubDate>Thu, 05 Mar 2026 02:29:54 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Timer-S1: A Billion-Scale Time Series Foundation Model with Serial Scaling</title>
|
||||
<link>https://arxiv.org/abs/2603.04791</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.04791.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yong Liu, Xingjian Su, Shiyu Wang, Haoran Zhang, Haixuan Liu, Yuxuan Wang, Zhou Ye, Yang Xiang, Jianmin Wang, Mingsheng Long</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> We introduce Timer-S1, a strong Mixture-of-Experts (MoE) time series foundation model with 8.3B total parameters, 0.75B activated parameters for each token, and a context length of 11.5K. To overcome the scalability bottleneck in existing pre-trained time series foundation models, we perform Serial Scaling in three dimensions: model architecture, dataset, and training pipeline. Timer-S1 integrates sparse TimeMoE blocks and generic TimeSTP blocks for Serial-Token Prediction (STP), a generic training objective that adheres to the serial nature of forecasting. The proposed paradigm introduces serial computations to improve long-term predictions while avoiding costly rolling-style inference and pronounced error accumulation in the standard next-token prediction. Pursuing a high-quality and unbiased training dataset, we curate TimeBench, a corpus with one trillion time points, and apply meticulous data augmentation to mitigate predictive bias. We further pioneer a post-training stage, including continued pre-training and long-context extension, to enhance short-term and long-context performance. Evaluated on the large-scale GIFT-Eval leaderboard, Timer-S1 achieves state-of-the-art forecasting performance, attaining the best MASE and CRPS scores as a pre-trained model. Timer-S1 will be released to facilitate further research.</p></description>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.04791.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yong Liu, Xingjian Su, Shiyu Wang, Haoran Zhang, Haixuan Liu, Yuxuan Wang, Zhou Ye, Yang Xiang, Jianmin Wang, Mingsheng Long</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> We introduce Timer-S1, a strong Mixture-of-Experts (MoE) time series foundation model with 8.3B total parameters, 0.75B activated parameters for each token, and a context length of 11.5K. To overcome the scalability bottleneck in existing pre-trained time series foundation models, we perform Serial Scaling in three dimensions: model architecture, dataset, and training pipeline. Timer-S1 integrates sparse TimeMoE blocks and generic TimeSTP blocks for Serial-Token Prediction (STP), a generic training objective that adheres to the serial nature of forecasting. The proposed paradigm introduces serial computations to improve long-term predictions while avoiding costly rolling-style inference and pronounced error accumulation in the standard next-token prediction. Pursuing a high-quality and unbiased training dataset, we curate TimeBench, a corpus with one trillion time points, and apply meticulous data augmentation to mitigate predictive bias. We further pioneer a post-training stage, including continued pre-training and long-context extension, to enhance short-term and long-context performance. Evaluated on the large-scale GIFT-Eval leaderboard, Timer-S1 achieves state-of-the-art forecasting performance, attaining the best MASE and CRPS scores as a pre-trained model. Timer-S1 will be released to facilitate further research.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.04791</guid>
|
||||
<pubDate>Thu, 05 Mar 2026 04:13:57 +0000</pubDate>
|
||||
</item>
|
||||
@@ -130,35 +130,35 @@
|
||||
<item>
|
||||
<title>Locality-Attending Vision Transformer</title>
|
||||
<link>https://arxiv.org/abs/2603.04892</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.04892.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sina Hajimiri, Farzad Beizaee, Fereshteh Shakeri, Christian Desrosiers, Ismail Ben Ayed, Jose Dolz</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Vision transformers have demonstrated remarkable success in classification by leveraging global self-attention to capture long-range dependencies. However, this same mechanism can obscure fine-grained spatial details crucial for tasks such as segmentation. In this work, we seek to enhance segmentation performance of vision transformers after standard image-level classification training. More specifically, we present a simple yet effective add-on that improves performance on segmentation tasks while retaining vision transformers' image-level recognition capabilities. In our approach, we modulate the self-attention with a learnable Gaussian kernel that biases the attention toward neighboring patches. We further refine the patch representations to learn better embeddings at patch positions. These modifications encourage tokens to focus on local surroundings and ensure meaningful representations at spatial positions, while still preserving the model's ability to incorporate global information. Experiments demonstrate the effectiveness of our modifications, evidenced by substantial segmentation gains on three benchmarks (e.g., over 6% and 4% on ADE20K for ViT Tiny and Base), without changing the training regime or sacrificing classification performance. The code is available at https://github.com/sinahmr/LocAtViT/.</p></description>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.04892.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sina Hajimiri, Farzad Beizaee, Fereshteh Shakeri, Christian Desrosiers, Ismail Ben Ayed, Jose Dolz</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Vision transformers have demonstrated remarkable success in classification by leveraging global self-attention to capture long-range dependencies. However, this same mechanism can obscure fine-grained spatial details crucial for tasks such as segmentation. In this work, we seek to enhance segmentation performance of vision transformers after standard image-level classification training. More specifically, we present a simple yet effective add-on that improves performance on segmentation tasks while retaining vision transformers' image-level recognition capabilities. In our approach, we modulate the self-attention with a learnable Gaussian kernel that biases the attention toward neighboring patches. We further refine the patch representations to learn better embeddings at patch positions. These modifications encourage tokens to focus on local surroundings and ensure meaningful representations at spatial positions, while still preserving the model's ability to incorporate global information. Experiments demonstrate the effectiveness of our modifications, evidenced by substantial segmentation gains on three benchmarks (e.g., over 6% and 4% on ADE20K for ViT Tiny and Base), without changing the training regime or sacrificing classification performance. The code is available at https://github.com/sinahmr/LocAtViT/.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.04892</guid>
|
||||
<pubDate>Thu, 05 Mar 2026 07:31:49 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>KARL: Knowledge Agents via Reinforcement Learning</title>
|
||||
<link>https://arxiv.org/abs/2603.05218</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.05218.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jonathan D. Chang, Andrew Drozdov, Shubham Toshniwal, Owen Oertell, Alexander Trott, Jacob Portes, Abhay Gupta, Pallavi Koppol, Ashutosh Baheti, Sean Kulinski, Ivan Zhou, Irene Dea, Krista Opsahl-Ong, Simon Favreau-Lessard, Sean Owen, Jose Javier Gonzalez Ortiz, Arnav Singhvi, Xabi Andrade, Cindy Wang, Kartik Sreenivasan, Sam Havens, Jialu Liu, Peyton DeNiro, Wen Sun, Michael Bendersky, Jonathan Frankle</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> We present a system for training enterprise search agents via reinforcement learning that achieves state-of-the-art performance across a diverse suite of hard-to-verify agentic search tasks. Our work makes four core contributions. First, we introduce KARLBench, a multi-capability evaluation suite spanning six distinct search regimes, including constraint-driven entity search, cross-document report synthesis, tabular numerical reasoning, exhaustive entity retrieval, procedural reasoning over technical documentation, and fact aggregation over internal enterprise notes. Second, we show that models trained across heterogeneous search behaviors generalize substantially better than those optimized for any single benchmark. Third, we develop an agentic synthesis pipeline that employs long-horizon reasoning and tool use to generate diverse, grounded, and high-quality training data, with iterative bootstrapping from increasingly capable models. Fourth, we propose a new post-training paradigm based on iterative large-batch off-policy RL that is sample efficient, robust to train-inference engine discrepancies, and naturally extends to multi-task training with out-of-distribution generalization. Compared to Claude 4.6 and GPT 5.2, KARL is Pareto-optimal on KARLBench across cost-quality and latency-quality trade-offs, including tasks that were out-of-distribution during training. With sufficient test-time compute, it surpasses the strongest closed models. These results show that tailored synthetic data in combination with multi-task reinforcement learning enables cost-efficient and high-performing knowledge agents for grounded reasoning.</p></description>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.05218.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jonathan D. Chang, Andrew Drozdov, Shubham Toshniwal, Owen Oertell, Alexander Trott, Jacob Portes, Abhay Gupta, Pallavi Koppol, Ashutosh Baheti, Sean Kulinski, Ivan Zhou, Irene Dea, Krista Opsahl-Ong, Simon Favreau-Lessard, Sean Owen, Jose Javier Gonzalez Ortiz, Arnav Singhvi, Xabi Andrade, Cindy Wang, Kartik Sreenivasan, Sam Havens, Jialu Liu, Peyton DeNiro, Wen Sun, Michael Bendersky, Jonathan Frankle</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> We present a system for training enterprise search agents via reinforcement learning that achieves state-of-the-art performance across a diverse suite of hard-to-verify agentic search tasks. Our work makes four core contributions. First, we introduce KARLBench, a multi-capability evaluation suite spanning six distinct search regimes, including constraint-driven entity search, cross-document report synthesis, tabular numerical reasoning, exhaustive entity retrieval, procedural reasoning over technical documentation, and fact aggregation over internal enterprise notes. Second, we show that models trained across heterogeneous search behaviors generalize substantially better than those optimized for any single benchmark. Third, we develop an agentic synthesis pipeline that employs long-horizon reasoning and tool use to generate diverse, grounded, and high-quality training data, with iterative bootstrapping from increasingly capable models. Fourth, we propose a new post-training paradigm based on iterative large-batch off-policy RL that is sample efficient, robust to train-inference engine discrepancies, and naturally extends to multi-task training with out-of-distribution generalization. Compared to Claude 4.6 and GPT 5.2, KARL is Pareto-optimal on KARLBench across cost-quality and latency-quality trade-offs, including tasks that were out-of-distribution during training. With sufficient test-time compute, it surpasses the strongest closed models. These results show that tailored synthetic data in combination with multi-task reinforcement learning enables cost-efficient and high-performing knowledge agents for grounded reasoning.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.05218</guid>
|
||||
<pubDate>Thu, 05 Mar 2026 14:30:25 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>UltraDexGrasp: Learning Universal Dexterous Grasping for Bimanual Robots with Synthetic Data</title>
|
||||
<link>https://arxiv.org/abs/2603.05312</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.05312.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sizhe Yang, Yiman Xie, Zhixuan Liang, Yang Tian, Jia Zeng, Dahua Lin, Jiangmiao Pang</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Grasping is a fundamental capability for robots to interact with the physical world. Humans, equipped with two hands, autonomously select appropriate grasp strategies based on the shape, size, and weight of objects, enabling robust grasping and subsequent manipulation. In contrast, current robotic grasping remains limited, particularly in multi-strategy settings. Although substantial efforts have targeted parallel-gripper and single-hand grasping, dexterous grasping for bimanual robots remains underexplored, with data being a primary bottleneck. Achieving physically plausible and geometrically conforming grasps that can withstand external wrenches poses significant challenges. To address these issues, we introduce UltraDexGrasp, a framework for universal dexterous grasping with bimanual robots. The proposed data-generation pipeline integrates optimization-based grasp synthesis with planning-based demonstration generation, yielding high-quality and diverse trajectories across multiple grasp strategies. With this framework, we curate UltraDexGrasp-20M, a large-scale, multi-strategy grasp dataset comprising 20 million frames across 1,000 objects. Based on UltraDexGrasp-20M, we further develop a simple yet effective grasp policy that takes point clouds as input, aggregates scene features via unidirectional attention, and predicts control commands. Trained exclusively on synthetic data, the policy achieves robust zero-shot sim-to-real transfer and consistently succeeds on novel objects with varied shapes, sizes, and weights, attaining an average success rate of 81.2% in real-world universal dexterous grasping. To facilitate future research on grasping with bimanual robots, we open-source the data generation pipeline at https://github.com/InternRobotics/UltraDexGrasp.</p></description>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.05312.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sizhe Yang, Yiman Xie, Zhixuan Liang, Yang Tian, Jia Zeng, Dahua Lin, Jiangmiao Pang</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Grasping is a fundamental capability for robots to interact with the physical world. Humans, equipped with two hands, autonomously select appropriate grasp strategies based on the shape, size, and weight of objects, enabling robust grasping and subsequent manipulation. In contrast, current robotic grasping remains limited, particularly in multi-strategy settings. Although substantial efforts have targeted parallel-gripper and single-hand grasping, dexterous grasping for bimanual robots remains underexplored, with data being a primary bottleneck. Achieving physically plausible and geometrically conforming grasps that can withstand external wrenches poses significant challenges. To address these issues, we introduce UltraDexGrasp, a framework for universal dexterous grasping with bimanual robots. The proposed data-generation pipeline integrates optimization-based grasp synthesis with planning-based demonstration generation, yielding high-quality and diverse trajectories across multiple grasp strategies. With this framework, we curate UltraDexGrasp-20M, a large-scale, multi-strategy grasp dataset comprising 20 million frames across 1,000 objects. Based on UltraDexGrasp-20M, we further develop a simple yet effective grasp policy that takes point clouds as input, aggregates scene features via unidirectional attention, and predicts control commands. Trained exclusively on synthetic data, the policy achieves robust zero-shot sim-to-real transfer and consistently succeeds on novel objects with varied shapes, sizes, and weights, attaining an average success rate of 81.2% in real-world universal dexterous grasping. To facilitate future research on grasping with bimanual robots, we open-source the data generation pipeline at https://github.com/InternRobotics/UltraDexGrasp.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.05312</guid>
|
||||
<pubDate>Thu, 05 Mar 2026 15:54:21 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>On-Policy Self-Distillation for Reasoning Compression</title>
|
||||
<link>https://arxiv.org/abs/2603.05433</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.05433.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hejian Sang, Yuanda Xu, Zhengze Zhou, Ran He, Zhipeng Wang, Jiachen Sun</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Reasoning models think out loud, but much of what they say is noise. We introduce OPSDC (On-Policy Self-Distillation for Reasoning Compression), a method that teaches models to reason more concisely by distilling their own concise behavior back into themselves. The entire approach reduces to one idea: condition the same model on a "be concise" instruction to obtain teacher logits, and minimize per-token reverse KL on the student's own rollouts. No ground-truth answers, no token budgets, no difficulty estimators. Just self-distillation. Yet this simplicity belies surprising sophistication: OPSDC automatically compresses easy problems aggressively while preserving the deliberation needed for hard ones. On Qwen3-8B and Qwen3-14B, we achieve 57-59% token reduction on MATH-500 while improving accuracy by 9-16 points absolute. On AIME 2024, the 14B model gains 10 points with 41% compression. The secret? Much of what reasoning models produce is not just redundant-it is actively harmful, compounding errors with every unnecessary token.</p></description>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.05433.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hejian Sang, Yuanda Xu, Zhengze Zhou, Ran He, Zhipeng Wang, Jiachen Sun</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Reasoning models think out loud, but much of what they say is noise. We introduce OPSDC (On-Policy Self-Distillation for Reasoning Compression), a method that teaches models to reason more concisely by distilling their own concise behavior back into themselves. The entire approach reduces to one idea: condition the same model on a "be concise" instruction to obtain teacher logits, and minimize per-token reverse KL on the student's own rollouts. No ground-truth answers, no token budgets, no difficulty estimators. Just self-distillation. Yet this simplicity belies surprising sophistication: OPSDC automatically compresses easy problems aggressively while preserving the deliberation needed for hard ones. On Qwen3-8B and Qwen3-14B, we achieve 57-59% token reduction on MATH-500 while improving accuracy by 9-16 points absolute. On AIME 2024, the 14B model gains 10 points with 41% compression. The secret? Much of what reasoning models produce is not just redundant-it is actively harmful, compounding errors with every unnecessary token.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.05433</guid>
|
||||
<pubDate>Thu, 05 Mar 2026 17:54:40 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>RealWonder: Real-Time Physical Action-Conditioned Video Generation</title>
|
||||
<link>https://arxiv.org/abs/2603.05449</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.05449.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wei Liu, Ziyu Chen, Zizhang Li, Yue Wang, Hong-Xing Yu, Jiajun Wu</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Current video generation models cannot simulate physical consequences of 3D actions like forces and robotic manipulations, as they lack structural understanding of how actions affect 3D scenes. We present RealWonder, the first real-time system for action-conditioned video generation from a single image. Our key insight is using physics simulation as an intermediate bridge: instead of directly encoding continuous actions, we translate them through physics simulation into visual representations (optical flow and RGB) that video models can process. RealWonder integrates three components: 3D reconstruction from single images, physics simulation, and a distilled video generator requiring only 4 diffusion steps. Our system achieves 13.2 FPS at 480x832 resolution, enabling interactive exploration of forces, robot actions, and camera controls on rigid objects, deformable bodies, fluids, and granular materials. We envision RealWonder opens new opportunities to apply video models in immersive experiences, AR/VR, and robot learning. Our code and model weights are publicly available in our project website: https://liuwei283.github.io/RealWonder/</p></description>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.05449.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wei Liu, Ziyu Chen, Zizhang Li, Yue Wang, Hong-Xing Yu, Jiajun Wu</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Current video generation models cannot simulate physical consequences of 3D actions like forces and robotic manipulations, as they lack structural understanding of how actions affect 3D scenes. We present RealWonder, the first real-time system for action-conditioned video generation from a single image. Our key insight is using physics simulation as an intermediate bridge: instead of directly encoding continuous actions, we translate them through physics simulation into visual representations (optical flow and RGB) that video models can process. RealWonder integrates three components: 3D reconstruction from single images, physics simulation, and a distilled video generator requiring only 4 diffusion steps. Our system achieves 13.2 FPS at 480x832 resolution, enabling interactive exploration of forces, robot actions, and camera controls on rigid objects, deformable bodies, fluids, and granular materials. We envision RealWonder opens new opportunities to apply video models in immersive experiences, AR/VR, and robot learning. Our code and model weights are publicly available in our project website: https://liuwei283.github.io/RealWonder/</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.05449</guid>
|
||||
<pubDate>Thu, 05 Mar 2026 18:22:54 +0000</pubDate>
|
||||
</item>
|
||||
@@ -172,7 +172,7 @@
|
||||
<item>
|
||||
<title>RoboPocket: Improve Robot Policies Instantly with Your Phone</title>
|
||||
<link>https://arxiv.org/abs/2603.05504</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.05504.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junjie Fang, Wendi Chen, Han Xue, Fangyuan Zhou, Tian Le, Yi Wang, Yuting Zhang, Jun Lv, Chuan Wen, Cewu Lu</p><p><b>Upvotes:</b> 28</p><p><b>Summary:</b> Scaling imitation learning is fundamentally constrained by the efficiency of data collection. While handheld interfaces have emerged as a scalable solution for in-the-wild data acquisition, they predominantly operate in an open-loop manner: operators blindly collect demonstrations without knowing the underlying policy's weaknesses, leading to inefficient coverage of critical state distributions. Conversely, interactive methods like DAgger effectively address covariate shift but rely on physical robot execution, which is costly and difficult to scale. To reconcile this trade-off, we introduce RoboPocket, a portable system that enables Robot-Free Instant Policy Iteration using single consumer smartphones. Its core innovation is a Remote Inference framework that visualizes the policy's predicted trajectory via Augmented Reality (AR) Visual Foresight. This immersive feedback allows collectors to proactively identify potential failures and focus data collection on the policy's weak regions without requiring a physical robot. Furthermore, we implement an asynchronous Online Finetuning pipeline that continuously updates the policy with incoming data, effectively closing the learning loop in minutes. Extensive experiments demonstrate that RoboPocket adheres to data scaling laws and doubles the data efficiency compared to offline scaling strategies, overcoming their long-standing efficiency bottleneck. Moreover, our instant iteration loop also boosts sample efficiency by up to 2times in distributed environments a small number of interactive corrections per person. Project page and videos: https://robo-pocket.github.io.</p></description>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.05504.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junjie Fang, Wendi Chen, Han Xue, Fangyuan Zhou, Tian Le, Yi Wang, Yuting Zhang, Jun Lv, Chuan Wen, Cewu Lu</p><p><b>Upvotes:</b> 30</p><p><b>Summary:</b> Scaling imitation learning is fundamentally constrained by the efficiency of data collection. While handheld interfaces have emerged as a scalable solution for in-the-wild data acquisition, they predominantly operate in an open-loop manner: operators blindly collect demonstrations without knowing the underlying policy's weaknesses, leading to inefficient coverage of critical state distributions. Conversely, interactive methods like DAgger effectively address covariate shift but rely on physical robot execution, which is costly and difficult to scale. To reconcile this trade-off, we introduce RoboPocket, a portable system that enables Robot-Free Instant Policy Iteration using single consumer smartphones. Its core innovation is a Remote Inference framework that visualizes the policy's predicted trajectory via Augmented Reality (AR) Visual Foresight. This immersive feedback allows collectors to proactively identify potential failures and focus data collection on the policy's weak regions without requiring a physical robot. Furthermore, we implement an asynchronous Online Finetuning pipeline that continuously updates the policy with incoming data, effectively closing the learning loop in minutes. Extensive experiments demonstrate that RoboPocket adheres to data scaling laws and doubles the data efficiency compared to offline scaling strategies, overcoming their long-standing efficiency bottleneck. Moreover, our instant iteration loop also boosts sample efficiency by up to 2times in distributed environments a small number of interactive corrections per person. Project page and videos: https://robo-pocket.github.io.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.05504</guid>
|
||||
<pubDate>Thu, 05 Mar 2026 18:59:38 +0000</pubDate>
|
||||
</item>
|
||||
|
||||
Reference in New Issue
Block a user