748 lines
223 KiB
XML
748 lines
223 KiB
XML
<?xml version='1.0' encoding='UTF-8'?>
|
|
<rss xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/" version="2.0">
|
|
<channel>
|
|
<title>Hugging Face Daily Papers</title>
|
|
<link>https://huggingface.co/papers</link>
|
|
<description>Daily research papers curated by the Hugging Face community.</description>
|
|
<docs>http://www.rssboard.org/rss-specification</docs>
|
|
<generator>python-feedgen</generator>
|
|
<language>en</language>
|
|
<lastBuildDate>Mon, 16 Mar 2026 00:19:28 +0000</lastBuildDate>
|
|
<item>
|
|
<title>WildActor: Unconstrained Identity-Preserving Video Generation</title>
|
|
<link>https://arxiv.org/abs/2603.00586</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.00586.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qin Guo, Tianyu Yang, Xuanhua He, Fei Shen, Yong Zhang, Zhuoliang Kang, Xiaoming Wei, Dan Xu</p><p><b>Upvotes:</b> 34</p><p><b>Summary:</b> Production-ready human video generation requires digital actors to maintain strictly consistent full-body identities across dynamic shots, viewpoints and motions, a setting that remains challenging for existing methods. Prior methods often suffer from face-centric behavior that neglects body-level consistency, or produce copy-paste artifacts where subjects appear rigid due to pose locking. We present Actor-18M, a large-scale human video dataset designed to capture identity consistency under unconstrained viewpoints and environments. Actor-18M comprises 1.6M videos with 18M corresponding human images, covering both arbitrary views and canonical three-view representations. Leveraging Actor-18M, we propose WildActor, a framework for any-view conditioned human video generation. We introduce an Asymmetric Identity-Preserving Attention mechanism coupled with a Viewpoint-Adaptive Monte Carlo Sampling strategy that iteratively re-weights reference conditions by marginal utility for balanced manifold coverage. Evaluated on the proposed Actor-Bench, WildActor consistently preserves body identity under diverse shot compositions, large viewpoint transitions, and substantial motions, surpassing existing methods in these challenging settings.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.00586</guid>
|
|
<pubDate>Sat, 28 Feb 2026 10:34:39 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>π-StepNFT: Wider Space Needs Finer Steps in Online RL for Flow-based VLAs</title>
|
|
<link>https://arxiv.org/abs/2603.02083</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.02083.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Siting Wang, Xiaofeng Wang, Zheng Zhu, Minnan Pei, Xinyu Cui, Cheng Deng, Jian Zhao, Guan Huang, Haifeng Zhang, Jun Wang</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Flow-based vision-language-action (VLA) models excel in embodied control but suffer from intractable likelihoods during multi-step sampling, hindering online reinforcement learning. We propose \textit{boldsymbolπ-StepNFT} (Step-wise Negative-aware Fine-Tuning), a critic-and-likelihood-free framework that requires only a single forward pass per optimization step and eliminates auxiliary value networks. We identify that wider exploration spaces necessitate finer-grained, step-wise guidance for alignment. Empirically, π-StepNFT unlocks latent potential on LIBERO with competitive few-shot robustness. Moreover, it achieves superior generalization on ManiSkill, outperforming value-based baselines in OOD scenarios by preventing overfitting to multimodal features. This property offers a scalable solution promising for complex real-world applications.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.02083</guid>
|
|
<pubDate>Mon, 02 Mar 2026 17:04:49 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Geometry-Guided Reinforcement Learning for Multi-view Consistent 3D Scene Editing</title>
|
|
<link>https://arxiv.org/abs/2603.03143</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.03143.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiyuan Wang, Chunyu Lin, Lei Sun, Zhi Cao, Yuyang Yin, Lang Nie, Zhenlong Yuan, Xiangxiang Chu, Yunchao Wei, Kang Liao, Guosheng Lin</p><p><b>Upvotes:</b> 136</p><p><b>Summary:</b> Leveraging the priors of 2D diffusion models for 3D editing has emerged as a promising paradigm. However, maintaining multi-view consistency in edited results remains challenging, and the extreme scarcity of 3D-consistent editing paired data renders supervised fine-tuning (SFT), the most effective training strategy for editing tasks, infeasible. In this paper, we observe that, while generating multi-view consistent 3D content is highly challenging, verifying 3D consistency is tractable, naturally positioning reinforcement learning (RL) as a feasible solution. Motivated by this, we propose RL3DEdit, a single-pass framework driven by RL optimization with novel rewards derived from the 3D foundation model, VGGT. Specifically, we leverage VGGT's robust priors learned from massive real-world data, feed the edited images, and utilize the output confidence maps and pose estimation errors as reward signals, effectively anchoring the 2D editing priors onto a 3D-consistent manifold via RL. Extensive experiments demonstrate that RL3DEdit achieves stable multi-view consistency and outperforms state-of-the-art methods in editing quality with high efficiency. To promote the development of 3D editing, we will release the code and model.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.03143</guid>
|
|
<pubDate>Tue, 03 Mar 2026 16:31:10 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory</title>
|
|
<link>https://arxiv.org/abs/2603.03269</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.03269.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junyi Zhang, Charles Herrmann, Junhwa Hur, Chen Sun, Ming-Hsuan Yang, Forrester Cole, Trevor Darrell, Deqing Sun</p><p><b>Upvotes:</b> 53</p><p><b>Summary:</b> Feedforward geometric foundation models achieve strong short-window reconstruction, yet scaling them to minutes-long videos is bottlenecked by quadratic attention complexity or limited effective memory in recurrent designs. We present LoGeR (Long-context Geometric Reconstruction), a novel architecture that scales dense 3D reconstruction to extremely long sequences without post-optimization. LoGeR processes video streams in chunks, leveraging strong bidirectional priors for high-fidelity intra-chunk reasoning. To manage the critical challenge of coherence across chunk boundaries, we propose a learning-based hybrid memory module. This dual-component system combines a parametric Test-Time Training (TTT) memory to anchor the global coordinate frame and prevent scale drift, alongside a non-parametric Sliding Window Attention (SWA) mechanism to preserve uncompressed context for high-precision adjacent alignment. Remarkably, this memory architecture enables LoGeR to be trained on sequences of 128 frames, and generalize up to thousands of frames during inference. Evaluated across standard benchmarks and a newly repurposed VBR dataset with sequences of up to 19k frames, LoGeR substantially outperforms prior state-of-the-art feedforward methods--reducing ATE on KITTI by over 74%--and achieves robust, globally consistent reconstruction over unprecedented horizons.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.03269</guid>
|
|
<pubDate>Tue, 03 Mar 2026 18:55:37 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>From Narrow to Panoramic Vision: Attention-Guided Cold-Start Reshapes Multimodal Reasoning</title>
|
|
<link>https://arxiv.org/abs/2603.03825</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.03825.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ruilin Luo, Chufan Shi, Yizhen Zhang, Cheng Yang, Songtao Jiang, Tongkun Guan, Ruizhe Chen, Ruihang Chu, Peng Wang, Mingkun Yang, Yujiu Yang, Junyang Lin, Zhibo Yang</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> The cold-start initialization stage plays a pivotal role in training Multimodal Large Reasoning Models (MLRMs), yet its mechanisms remain insufficiently understood. To analyze this stage, we introduce the Visual Attention Score (VAS), an attention-based metric that quantifies how much a model attends to visual tokens. We find that reasoning performance is strongly correlated with VAS (r=0.9616): models with higher VAS achieve substantially stronger multimodal reasoning. Surprisingly, multimodal cold-start fails to elevate VAS, resulting in attention distributions close to the base model, whereas text-only cold-start leads to a clear increase. We term this counter-intuitive phenomenon Lazy Attention Localization. To validate its causal role, we design training-free interventions that directly modulate attention allocation during inference, performance gains of 1-2% without any retraining. Building on these insights, we further propose Attention-Guided Visual Anchoring and Reflection (AVAR), a comprehensive cold-start framework that integrates visual-anchored data synthesis, attention-guided objectives, and visual-anchored reward shaping. Applied to Qwen2.5-VL-7B, AVAR achieves an average gain of 7.0% across 7 multimodal reasoning benchmarks. Ablation studies further confirm that each component of AVAR contributes step-wise to the overall gains. The code, data, and models are available at https://github.com/lrlbbzl/Qwen-AVAR.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.03825</guid>
|
|
<pubDate>Wed, 04 Mar 2026 08:22:27 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Believe Your Model: Distribution-Guided Confidence Calibration</title>
|
|
<link>https://arxiv.org/abs/2603.03872</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.03872.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xizhong Yang, Haotian Zhang, Huiming Wang, Mofei Song</p><p><b>Upvotes:</b> 38</p><p><b>Summary:</b> Large Reasoning Models have demonstrated remarkable performance with the advancement of test-time scaling techniques, which enhances prediction accuracy by generating multiple candidate responses and selecting the most reliable answer. While prior work has analyzed that internal model signals like confidence scores can partly indicate response correctness and exhibit a distributional correlation with accuracy, such distributional information has not been fully utilized to guide answer selection. Motivated by this, we propose DistriVoting, which incorporates distributional priors as another signal alongside confidence during voting. Specifically, our method (1) first decomposes the mixed confidence distribution into positive and negative components using Gaussian Mixture Models, (2) then applies a reject filter based on positive/negative samples from them to mitigate overlap between the two distributions. Besides, to further alleviate the overlap from the perspective of distribution itself, we propose SelfStepConf, which uses step-level confidence to dynamically adjust inference process, increasing the separation between the two distributions to improve the reliability of confidences in voting. Experiments across 16 models and 5 benchmarks demonstrate that our method significantly outperforms state-of-the-art approaches.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.03872</guid>
|
|
<pubDate>Wed, 04 Mar 2026 09:25:36 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Bootstrapping Exploration with Group-Level Natural Language Feedback in Reinforcement Learning</title>
|
|
<link>https://arxiv.org/abs/2603.04597</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.04597.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lei Huang, Xiang Cheng, Chenxiao Zhao, Guobin Shen, Junjie Yang, Xiaocheng Feng, Yuxuan Gu, Xing Yu, Bing Qin</p><p><b>Upvotes:</b> 156</p><p><b>Summary:</b> Large language models (LLMs) typically receive diverse natural language (NL) feedback through interaction with the environment. However, current reinforcement learning (RL) algorithms rely solely on scalar rewards, leaving the rich information in NL feedback underutilized and leading to inefficient exploration. In this work, we propose GOLF, an RL framework that explicitly exploits group-level language feedback to guide targeted exploration through actionable refinements. GOLF aggregates two complementary feedback sources: (i) external critiques that pinpoint errors or propose targeted fixes, and (ii) intra-group attempts that supply alternative partial ideas and diverse failure patterns. These group-level feedbacks are aggregated to produce high-quality refinements, which are adaptively injected into training as off-policy scaffolds to provide targeted guidance in sparse-reward regions. Meanwhile, GOLF jointly optimizes generation and refinement within a unified RL loop, creating a virtuous cycle that continuously improves both capabilities. Experiments on both verifiable and non-verifiable benchmarks show that GOLF achieves superior performance and exploration efficiency, achieving 2.2times improvements in sample efficiency compared to RL methods trained solely on scalar rewards. Code is available at https://github.com/LuckyyySTA/GOLF.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.04597</guid>
|
|
<pubDate>Wed, 04 Mar 2026 20:53:17 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>RoboMME: Benchmarking and Understanding Memory for Robotic Generalist Policies</title>
|
|
<link>https://arxiv.org/abs/2603.04639</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.04639.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yinpei Dai, Hongze Fu, Jayjun Lee, Yuejiang Liu, Haoran Zhang, Jianing Yang, Chelsea Finn, Nima Fazeli, Joyce Chai</p><p><b>Upvotes:</b> 23</p><p><b>Summary:</b> Memory is critical for long-horizon and history-dependent robotic manipulation. Such tasks often involve counting repeated actions or manipulating objects that become temporarily occluded. Recent vision-language-action (VLA) models have begun to incorporate memory mechanisms; however, their evaluations remain confined to narrow, non-standardized settings. This limits their systematic understanding, comparison, and progress measurement. To address these challenges, we introduce RoboMME: a large-scale standardized benchmark for evaluating and advancing VLA models in long-horizon, history-dependent scenarios. Our benchmark comprises 16 manipulation tasks constructed under a carefully designed taxonomy that evaluates temporal, spatial, object, and procedural memory. We further develop a suite of 14 memory-augmented VLA variants built on the π0.5 backbone to systematically explore different memory representations across multiple integration strategies. Experimental results show that the effectiveness of memory representations is highly task-dependent, with each design offering distinct advantages and limitations across different tasks. Videos and code can be found at our website https://robomme.github.io.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.04639</guid>
|
|
<pubDate>Wed, 04 Mar 2026 21:59:32 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>HiMAP-Travel: Hierarchical Multi-Agent Planning for Long-Horizon Constrained Travel</title>
|
|
<link>https://arxiv.org/abs/2603.04750</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.04750.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> The Viet Bui, Wenjun Li, Yong Liu</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Sequential LLM agents fail on long-horizon planning with hard constraints like budgets and diversity requirements. As planning progresses and context grows, these agents drift from global constraints. We propose HiMAP-Travel, a hierarchical multi-agent framework that splits planning into strategic coordination and parallel day-level execution. A Coordinator allocates resources across days, while Day Executors plan independently in parallel. Three key mechanisms enable this: a transactional monitor enforcing budget and uniqueness constraints across parallel agents, a bargaining protocol allowing agents to reject infeasible sub-goals and trigger re-planning, and a single policy trained with GRPO that powers all agents through role conditioning. On TravelPlanner, HiMAP-Travel with Qwen3-8B achieves 52.78% validation and 52.65% test Final Pass Rate (FPR). In a controlled comparison with identical model, training, and tools, it outperforms the sequential DeepTravel baseline by +8.67~pp. It also surpasses ATLAS by +17.65~pp and MTP by +10.0~pp. On FlexTravelBench multi-turn scenarios, it achieves 44.34% (2-turn) and 37.42% (3-turn) FPR while reducing latency 2.5x through parallelization.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.04750</guid>
|
|
<pubDate>Thu, 05 Mar 2026 02:55:53 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>BandPO: Bridging Trust Regions and Ratio Clipping via Probability-Aware Bounds for LLM Reinforcement Learning</title>
|
|
<link>https://arxiv.org/abs/2603.04918</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.04918.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuan Li, Bo Wang, Yufei Gao, Yuqian Yao, Xinyuan Wang, Zhangyue Yin, Xipeng Qiu</p><p><b>Upvotes:</b> 54</p><p><b>Summary:</b> Proximal constraints are fundamental to the stability of the Large Language Model reinforcement learning. While the canonical clipping mechanism in PPO serves as an efficient surrogate for trust regions, we identify a critical bottleneck: fixed bounds strictly constrain the upward update margin of low-probability actions, disproportionately suppressing high-advantage tail strategies and inducing rapid entropy collapse. To address this, we introduce Band-constrained Policy Optimization (BandPO). BandPO replaces canonical clipping with Band, a unified theoretical operator that projects trust regions defined by f-divergences into dynamic, probability-aware clipping intervals. Theoretical analysis confirms that Band effectively resolves this exploration bottleneck. We formulate this mapping as a convex optimization problem, guaranteeing a globally optimal numerical solution while deriving closed-form solutions for specific divergences. Extensive experiments across diverse models and datasets demonstrate that BandPO consistently outperforms canonical clipping and Clip-Higher, while robustly mitigating entropy collapse.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.04918</guid>
|
|
<pubDate>Thu, 05 Mar 2026 08:03:05 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Sparse-BitNet: 1.58-bit LLMs are Naturally Friendly to Semi-Structured Sparsity</title>
|
|
<link>https://arxiv.org/abs/2603.05168</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.05168.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Di Zhang, Xun Wu, Shaohan Huang, Yudong Wang, Hanyong Shao, Yingbo Hao, Zewen Chi, Li Dong, Ting Song, Yan Xia, Zhifang Sui, Furu Wei</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Semi-structured N:M sparsity and low-bit quantization (e.g., 1.58-bit BitNet) are two promising approaches for improving the efficiency of large language models (LLMs), yet they have largely been studied in isolation. In this work, we investigate their interaction and show that 1.58-bit BitNet is naturally more compatible with N:M sparsity than full-precision models. To study this effect, we propose Sparse-BitNet, a unified framework that jointly applies 1.58-bit quantization and dynamic N:M sparsification while ensuring stable training for the first time. Across multiple model scales and training regimes (sparse pretraining and dense-to-sparse schedules), 1.58-bit BitNet consistently exhibits smaller performance degradation than full-precision baselines at the same sparsity levels and can tolerate higher structured sparsity before accuracy collapse. Moreover, using our custom sparse tensor core, Sparse-BitNet achieves substantial speedups in both training and inference, reaching up to 1.30X. These results highlight that combining extremely low-bit quantization with semi-structured N:M sparsity is a promising direction for efficient LLMs. Code available at https://github.com/AAzdi/Sparse-BitNet</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.05168</guid>
|
|
<pubDate>Thu, 05 Mar 2026 13:37:50 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Mario: Multimodal Graph Reasoning with Large Language Models</title>
|
|
<link>https://arxiv.org/abs/2603.05181</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.05181.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuanfu Sun, Kang Li, Pengkang Guo, Jiajin Liu, Qiaoyu Tan</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Recent advances in large language models (LLMs) have opened new avenues for multimodal reasoning. Yet, most existing methods still rely on pretrained vision-language models (VLMs) to encode image-text pairs in isolation, ignoring the relational structure that real-world multimodal data naturally form. This motivates reasoning on multimodal graphs (MMGs), where each node has textual and visual attributes and edges provide structural cues. Enabling LLM-based reasoning on such heterogeneous multimodal signals while preserving graph topology introduces two key challenges: resolving weak cross-modal consistency and handling heterogeneous modality preference. To address this, we propose Mario, a unified framework that simultaneously resolves the two above challenges and enables effective LLM-based reasoning over MMGs. Mario consists of two innovative stages. Firstly, a graph-conditioned VLM design that jointly refines textual and visual features through fine-grained cross-modal contrastive learning guided by graph topology. Secondly, a modality-adaptive graph instruction tuning mechanism that organizes aligned multimodal features into graph-aware instruction views and employs a learnable router to surface, for each node and its neighborhood, the most informative modality configuration to the LLM. Extensive experiments across diverse MMG benchmarks demonstrate that Mario consistently outperforms state-of-the-art graph models in both supervised and zero-shot scenarios for node classification and link prediction. The code will be made available at https://github.com/sunyuanfu/Mario.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.05181</guid>
|
|
<pubDate>Thu, 05 Mar 2026 13:49:41 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Building AI Coding Agents for the Terminal: Scaffolding, Harness, Context Engineering, and Lessons Learned</title>
|
|
<link>https://arxiv.org/abs/2603.05344</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.05344.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Nghi D. Q. Bui</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> The landscape of AI coding assistance is undergoing a fundamental shift from complex IDE plugins to versatile, terminal-native agents. Operating directly where developers manage source control, execute builds, and deploy environments, CLI-based agents offer unprecedented autonomy for long-horizon development tasks. In this paper, we present OPENDEV, an open-source, command-line coding agent engineered specifically for this new paradigm. Effective autonomous assistance requires strict safety controls and highly efficient context management to prevent context bloat and reasoning degradation. OPENDEV overcomes these challenges through a compound AI system architecture with workload-specialized model routing, a dual-agent architecture separating planning from execution, lazy tool discovery, and adaptive context compaction that progressively reduces older observations. Furthermore, it employs an automated memory system to accumulate project-specific knowledge across sessions and counteracts instruction fade-out through event-driven system reminders. By enforcing explicit reasoning phases and prioritizing context efficiency, OPENDEV provides a secure, extensible foundation for terminal-first AI assistance, offering a blueprint for robust autonomous software engineering.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.05344</guid>
|
|
<pubDate>Thu, 05 Mar 2026 16:21:08 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Progressive Residual Warmup for Language Model Pretraining</title>
|
|
<link>https://arxiv.org/abs/2603.05369</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.05369.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tianhao Chen, Xin Xu, Lu Yin, Hao Chen, Yang Wang, Shizhe Diao, Can Yang</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> Transformer architectures serve as the backbone for most modern Large Language Models, therefore their pretraining stability and convergence speed are of central concern. Motivated by the logical dependency of sequentially stacked layers, we propose Progressive Residual Warmup (ProRes) for language model pretraining. ProRes implements an "early layer learns first" philosophy by multiplying each layer's residual with a scalar that gradually warms up from 0 to 1, with deeper layers taking longer warmup steps. In this way, deeper layers wait for early layers to settle into a more stable regime before contributing to learning. We demonstrate the effectiveness of ProRes through pretraining experiments across various model scales, as well as normalization and initialization schemes. Comprehensive analysis shows that ProRes not only stabilizes pretraining but also introduces a unique optimization trajectory, leading to faster convergence, stronger generalization and better downstream performance. Our code is available at https://github.com/dandingsky/ProRes.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.05369</guid>
|
|
<pubDate>Thu, 05 Mar 2026 16:52:15 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Planning in 8 Tokens: A Compact Discrete Tokenizer for Latent World Model</title>
|
|
<link>https://arxiv.org/abs/2603.05438</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.05438.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dongwon Kim, Gawon Seo, Jinsung Lee, Minsu Cho, Suha Kwak</p><p><b>Upvotes:</b> 35</p><p><b>Summary:</b> World models provide a powerful framework for simulating environment dynamics conditioned on actions or instructions, enabling downstream tasks such as action planning or policy learning. Recent approaches leverage world models as learned simulators, but its application to decision-time planning remains computationally prohibitive for real-time control. A key bottleneck lies in latent representations: conventional tokenizers encode each observation into hundreds of tokens, making planning both slow and resource-intensive. To address this, we propose CompACT, a discrete tokenizer that compresses each observation into as few as 8 tokens, drastically reducing computational cost while preserving essential information for planning. An action-conditioned world model that occupies CompACT tokenizer achieves competitive planning performance with orders-of-magnitude faster planning, offering a practical step toward real-world deployment of world models.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.05438</guid>
|
|
<pubDate>Thu, 05 Mar 2026 18:00:02 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Scaling Agentic Capabilities, Not Context: Efficient Reinforcement Finetuning for Large Toolspaces</title>
|
|
<link>https://arxiv.org/abs/2603.06713</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.06713.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Karan Gupta, Pranav Vajreshwari, Yash Pandya, Raghav Magazine, Akshay Nambi, Ahmed Awadallah</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Agentic systems operating over large tool ecosystems must plan and execute long-horizon workflows under weak or non-verifiable supervision. While frontier models mitigate these challenges through scale and large context budgets, small language models (SLMs) remain brittle: eager tool loading saturates context, execution errors compound over time, and sparse rewards limit learning. We introduce ATLAS, a reinforcement finetuning framework that enables SLMs to operate effectively in large-scale toolspace environments by learning how to acquire context and how to execute actions. Our approach makes two key contributions. First, we treat context control and execution structure as learnable decisions, combining iterative tool loading with programmatic tool orchestration to bound context growth and stabilize long-horizon trajectories. Second, we propose rubric-based reinforcement finetuning, which decomposes task success into structured, task-aligned criteria and enables scalable training using small judge models. Across MCP benchmarks, these design choices yield large and consistent gains over generic RL baselines, allowing a 4B SLM to approach frontier-agent performance under far tighter parameter and context budgets.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.06713</guid>
|
|
<pubDate>Thu, 05 Mar 2026 20:29:12 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Reasoning Models Struggle to Control their Chains of Thought</title>
|
|
<link>https://arxiv.org/abs/2603.05706</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.05706.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chen Yueh-Han, Robert McCarthy, Bruce W. Lee, He He, Ian Kivlichan, Bowen Baker, Micah Carroll, Tomek Korbak</p><p><b>Upvotes:</b> 27</p><p><b>Summary:</b> Chain-of-thought (CoT) monitoring is a promising tool for detecting misbehaviors and understanding the motivations of modern reasoning models. However, if models can control what they verbalize in their CoT, it could undermine CoT monitorability. To measure this undesirable capability -- CoT controllability -- we introduce the CoT-Control evaluation suite, which includes tasks that require models to solve problems while adhering to CoT instructions, e.g., reasoning about a genetics question without using the word 'chromosome'. We show that reasoning models possess significantly lower CoT controllability than output controllability; for instance, Claude Sonnet 4.5 can control its CoT only 2.7% of the time but 61.9% when controlling its final output. We also find that CoT controllability is higher for larger models and decreases with more RL training, test-time compute, and increased problem difficulty. CoT controllability failures extend even to situations in which models are given incentives (as opposed to direct requests) to evade CoT monitors, although models exhibit slightly higher controllability when they are told they are being monitored. Similarly, eliciting controllability by adversarially optimizing prompts does not meaningfully increase controllability. Our results leave us cautiously optimistic that CoT controllability is currently unlikely to be a failure mode of CoT monitorability. However, the mechanism behind low controllability is not well understood. Given its importance for maintaining CoT monitorability, we recommend that frontier labs track CoT controllability in future models.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.05706</guid>
|
|
<pubDate>Thu, 05 Mar 2026 22:03:48 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Training-free Latent Inter-Frame Pruning with Attention Recovery</title>
|
|
<link>https://arxiv.org/abs/2603.05811</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.05811.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dennis Menn, Yuedong Yang, Bokun Wang, Xiwen Wei, Mustafa Munir, Feng Liang, Radu Marculescu, Chenfeng Xu, Diana Marculescu</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Current video generation models suffer from high computational latency, making real-time applications prohibitively costly. In this paper, we address this limitation by exploiting the temporal redundancy inherent in video latent patches. To this end, we propose the Latent Inter-frame Pruning with Attention Recovery (LIPAR) framework, which detects and skips recomputing duplicated latent patches. Additionally, we introduce a novel Attention Recovery mechanism that approximates the attention values of pruned tokens, thereby removing visual artifacts arising from naively applying the pruning method. Empirically, our method increases video editing throughput by 1.45times, on average achieving 12.2 FPS on an NVIDIA A6000 compared to the baseline 8.4 FPS. The proposed method does not compromise generation quality and can be seamlessly integrated with the model without additional training. Our approach effectively bridges the gap between traditional compression algorithms and modern generative pipelines.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.05811</guid>
|
|
<pubDate>Fri, 06 Mar 2026 01:49:47 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>ReflexiCoder: Teaching Large Language Models to Self-Reflect on Generated Code and Self-Correct It via Reinforcement Learning</title>
|
|
<link>https://arxiv.org/abs/2603.05863</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.05863.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Juyong Jiang, Jiasi Shen, Sunghun Kim, Kang Min Yoo, Jeonghoon Kim, Sungju Kim</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> While Large Language Models (LLMs) have revolutionized code generation, standard "System 1" approaches, generating solutions in a single forward pass, often hit a performance ceiling when faced with complex algorithmic tasks. Existing iterative refinement strategies attempt to bridge this gap at inference time, yet they predominantly rely on external oracles, execution feedback, or computationally expensive prompt-response cycles. In this work, we propose ReflexiCoder, a novel reinforcement learning (RL) framework that internalizes the structured reasoning trajectory, encompassing initial generation, bug and optimization aware reflection, and self-correction, directly into the model's weights. Unlike prior methods, ReflexiCoder shifts the paradigm from external-dependent refinement to an intrinsic, fully autonomous self-reflection and self-correction capabilities at inference time. We utilize an RL-zero training paradigm with granular reward functions to optimize the entire reflection-correction trajectory, teaching the model how to debug without reliance on ground-truth feedback or execution engines at inference time. Extensive experiments across seven benchmarks demonstrate that our ReflexiCoder-8B establishes a new state-of-the-art (SOTA) among leading open-source models in the 1.5B-14B range, achieving 94.51% (87.20%) on HumanEval (Plus), 81.80% (78.57%) on MBPP (Plus), 35.00% on BigCodeBench, 52.21% on LiveCodeBench, and 37.34% on CodeForces in a single-attempt setting, rivaling or surpassing proprietary models like GPT-5.1. Notably, our framework is significantly more token-efficient than base models, reducing inference-time compute overhead by approximately 40% through disciplined, high-speed reasoning and reflection patterns. Source code is available at https://github.com/juyongjiang/ReflexiCoder.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.05863</guid>
|
|
<pubDate>Fri, 06 Mar 2026 03:38:17 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Lost in Stories: Consistency Bugs in Long Story Generation by LLMs</title>
|
|
<link>https://arxiv.org/abs/2603.05890</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.05890.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junjie Li, Xinrui Guo, Yuhao Wu, Roy Ka-Wei Lee, Hongzhi Li, Yutao Xie</p><p><b>Upvotes:</b> 82</p><p><b>Summary:</b> What happens when a storyteller forgets its own story? Large Language Models (LLMs) can now generate narratives spanning tens of thousands of words, but they often fail to maintain consistency throughout. When generating long-form narratives, these models can contradict their own established facts, character traits, and world rules. Existing story generation benchmarks focus mainly on plot quality and fluency, leaving consistency errors largely unexplored. To address this gap, we present ConStory-Bench, a benchmark designed to evaluate narrative consistency in long-form story generation. It contains 2,000 prompts across four task scenarios and defines a taxonomy of five error categories with 19 fine-grained subtypes. We also develop ConStory-Checker, an automated pipeline that detects contradictions and grounds each judgment in explicit textual evidence. Evaluating a range of LLMs through five research questions, we find that consistency errors show clear tendencies: they are most common in factual and temporal dimensions, tend to appear around the middle of narratives, occur in text segments with higher token-level entropy, and certain error types tend to co-occur. These findings can inform future efforts to improve consistency in long-form narrative generation. Our project page is available at https://picrew.github.io/constory-bench.github.io/.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.05890</guid>
|
|
<pubDate>Fri, 06 Mar 2026 04:16:46 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>EffectMaker: Unifying Reasoning and Generation for Customized Visual Effect Creation</title>
|
|
<link>https://arxiv.org/abs/2603.06014</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.06014.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shiyuan Yang, Ruihuang Li, Jiale Tao, Shuai Shao, Qinglin Lu, Jing Liao</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Visual effects (VFX) are essential for enhancing the expressiveness and creativity of video content, yet producing high-quality effects typically requires expert knowledge and costly production pipelines. Existing AIGC systems face significant challenges in VFX generation due to the scarcity of effect-specific data and the inherent difficulty of modeling supernatural or stylized effects. Moreover, these approaches often require per-effect fine-tuning, which severely limits their scalability and generalization to novel VFX. In this work, we present EffectMaker, a unified reasoning-generation framework that enables reference-based VFX customization. EffectMaker employs a multimodal large language model to interpret high-level effect semantics and reason about how they should adapt to a target subject, while a diffusion transformer leverages in-context learning to capture fine-grained visual cues from reference videos. These two components form a semantic-visual dual-path guidance mechanism that enables accurate, controllable, and effect-consistent synthesis without per-effect fine-tuning. Furthermore, we construct EffectData, the largest high-quality synthetic dataset containing 130k videos across 3k VFX categories, to improve generalization and scalability. Experiments show that EffectMaker achieves superior visual quality and effect consistency over state-of-the-art baselines, offering a scalable and flexible paradigm for customized VFX generation. Project page: https://effectmaker.github.io</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.06014</guid>
|
|
<pubDate>Fri, 06 Mar 2026 08:09:14 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>FlashPrefill: Instantaneous Pattern Discovery and Thresholding for Ultra-Fast Long-Context Prefilling</title>
|
|
<link>https://arxiv.org/abs/2603.06199</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.06199.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qihang Fan, Huaibo Huang, Zhiying Wu, Juqiu Wang, Bingning Wang, Ran He</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Long-context modeling is a pivotal capability for Large Language Models, yet the quadratic complexity of attention remains a critical bottleneck, particularly during the compute-intensive prefilling phase. While various sparse attention mechanisms have been explored, they typically suffer from either significant search latency or insufficient sparsity. In this paper, we propose FlashPrefill, a framework enabling ultra-fast prefilling via instantaneous pattern discovery and thresholding. FlashPrefill leverages a fast block-searching technique to simultaneously locate dynamic vertical, slash, and block-sparse attention patterns. Crucially, it introduces a dynamic thresholding mechanism that bypasses the prohibitive overhead of sorting or accumulating attention scores while effectively eliminating the long-tail distribution to enhance sparsity. Extensive evaluations demonstrate that FlashPrefill achieves a substantial leap in efficiency, delivering an unprecedented 27.78x speedup on 256K sequences. Notably, unlike existing methods that incur efficiency degradation on shorter contexts, FlashPrefill maintains a 1.71x speedup even at a 4K context length, demonstrating its robustness and practical utility across varying sequence scales.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.06199</guid>
|
|
<pubDate>Fri, 06 Mar 2026 12:12:46 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Dynamic Chunking Diffusion Transformer</title>
|
|
<link>https://arxiv.org/abs/2603.06351</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.06351.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Akash Haridas, Utkarsh Saxena, Parsa Ashrafi Fashi, Mehdi Rezagholizadeh, Vikram Appia, Emad Barsoum</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Diffusion Transformers process images as fixed-length sequences of tokens produced by a static patchify operation. While effective, this design spends uniform compute on low- and high-information regions alike, ignoring that images contain regions of varying detail and that the denoising process progresses from coarse structure at early timesteps to fine detail at late timesteps. We introduce the Dynamic Chunking Diffusion Transformer (DC-DiT), which augments the DiT backbone with a learned encoder-router-decoder scaffold that adaptively compresses the 2D input into a shorter token sequence in a data-dependent manner using a chunking mechanism learned end-to-end with diffusion training. The mechanism learns to compress uniform background regions into fewer tokens and detail-rich regions into more tokens, with meaningful visual segmentations emerging without explicit supervision. Furthermore, it also learns to adapt its compression across diffusion timesteps, using fewer tokens at noisy stages and more tokens as fine details emerge. On class-conditional ImageNet 256{times}256, DC-DiT consistently improves FID and Inception Score over both parameter-matched and FLOP-matched DiT baselines across 4{times} and 16{times} compression, showing this is a promising technique with potential further applications to pixel-space, video and 3D generation. Beyond accuracy, DC-DiT is practical: it can be upcycled from pretrained DiT checkpoints with minimal post-training compute (up to 8{times} fewer training steps) and composes with other dynamic computation methods to further reduce generation FLOPs.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.06351</guid>
|
|
<pubDate>Fri, 06 Mar 2026 14:59:11 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Physical Simulator In-the-Loop Video Generation</title>
|
|
<link>https://arxiv.org/abs/2603.06408</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.06408.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lin Geng Foo, Mark He Huang, Alexandros Lattas, Stylianos Moschoglou, Thabo Beeler, Christian Theobalt</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Recent advances in diffusion-based video generation have achieved remarkable visual realism but still struggle to obey basic physical laws such as gravity, inertia, and collision. Generated objects often move inconsistently across frames, exhibit implausible dynamics, or violate physical constraints, limiting the realism and reliability of AI-generated videos. We address this gap by introducing Physical Simulator In-the-loop Video Generation (PSIVG), a novel framework that integrates a physical simulator into the video diffusion process. Starting from a template video generated by a pre-trained diffusion model, PSIVG reconstructs the 4D scene and foreground object meshes, initializes them within a physical simulator, and generates physically consistent trajectories. These simulated trajectories are then used to guide the video generator toward spatio-temporally physically coherent motion. To further improve texture consistency during object movement, we propose a Test-Time Texture Consistency Optimization (TTCO) technique that adapts text and feature embeddings based on pixel correspondences from the simulator. Comprehensive experiments demonstrate that PSIVG produces videos that better adhere to real-world physics while preserving visual quality and diversity. Project Page: https://vcai.mpi-inf.mpg.de/projects/PSIVG/</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.06408</guid>
|
|
<pubDate>Fri, 06 Mar 2026 15:48:25 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>CaTok: Taming Mean Flows for One-Dimensional Causal Image Tokenization</title>
|
|
<link>https://arxiv.org/abs/2603.06449</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.06449.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yitong Chen, Zuxuan Wu, Xipeng Qiu, Yu-Gang Jiang</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Autoregressive (AR) language models rely on causal tokenization, but extending this paradigm to vision remains non-trivial. Current visual tokenizers either flatten 2D patches into non-causal sequences or enforce heuristic orderings that misalign with the "next-token prediction" pattern. Recent diffusion autoencoders similarly fall short: conditioning the decoder on all tokens lacks causality, while applying nested dropout mechanism introduces imbalance. To address these challenges, we present CaTok, a 1D causal image tokenizer with a MeanFlow decoder. By selecting tokens over time intervals and binding them to the MeanFlow objective, as illustrated in Fig. 1, CaTok learns causal 1D representations that support both fast one-step generation and high-fidelity multi-step sampling, while naturally capturing diverse visual concepts across token intervals. To further stabilize and accelerate training, we propose a straightforward regularization REPA-A, which aligns encoder features with Vision Foundation Models (VFMs). Experiments demonstrate that CaTok achieves state-of-the-art results on ImageNet reconstruction, reaching 0.75 FID, 22.53 PSNR and 0.674 SSIM with fewer training epochs, and the AR model attains performance comparable to leading approaches.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.06449</guid>
|
|
<pubDate>Fri, 06 Mar 2026 16:39:17 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders</title>
|
|
<link>https://arxiv.org/abs/2603.06569</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.06569.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Boqiang Zhang, Lei Ke, Ruihan Yang, Qi Gao, Tianyuan Qu, Rossell Chen, Dong Yu, Leoweiliang</p><p><b>Upvotes:</b> 104</p><p><b>Summary:</b> Vision Language Model (VLM) development has largely relied on scaling model size, which hinders deployment on compute-constrained mobile and edge devices such as smartphones and robots. In this work, we explore the performance limits of compact (e.g., 2B and 8B) VLMs. We challenge the prevailing practice that state-of-the-art VLMs must rely on vision encoders initialized via massive contrastive pretraining (e.g., CLIP/SigLIP). We identify an objective mismatch: contrastive learning, optimized for discrimination, enforces coarse and category-level invariances that suppress fine-grained visual cues needed for dense captioning and complex VLM reasoning. To address this issue, we present Penguin-VL, whose vision encoder is initialized from a text-only LLM. Our experiments reveal that Penguin-Encoder serves as a superior alternative to traditional contrastive pretraining, unlocking a higher degree of visual fidelity and data efficiency for multimodal understanding. Across various image and video benchmarks, Penguin-VL achieves performance comparable to leading VLMs (e.g., Qwen3-VL) in mathematical reasoning and surpasses them in tasks such as document understanding, visual knowledge, and multi-perspective video understanding. Notably, these gains are achieved with a lightweight architecture, demonstrating that improved visual representation rather than model scaling is the primary driver of performance. Our ablations show that Penguin-Encoder consistently outperforms contrastive-pretrained encoders, preserving fine-grained spatial and temporal cues that are critical for dense perception and complex reasoning. This makes it a strong drop-in alternative for compute-efficient VLMs and enables high performance in resource-constrained settings. Code: https://github.com/tencent-ailab/Penguin-VL</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.06569</guid>
|
|
<pubDate>Fri, 06 Mar 2026 18:58:04 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Omni-Diffusion: Unified Multimodal Understanding and Generation with Masked Discrete Diffusion</title>
|
|
<link>https://arxiv.org/abs/2603.06577</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.06577.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lijiang Li, Zuwei Long, Yunhang Shen, Heting Gao, Haoyu Cao, Xing Sun, Caifeng Shan, Ran He, Chaoyou Fu</p><p><b>Upvotes:</b> 43</p><p><b>Summary:</b> While recent multimodal large language models (MLLMs) have made impressive strides, they predominantly employ a conventional autoregressive architecture as their backbone, leaving significant room to explore effective and efficient alternatives in architectural design. Concurrently, recent studies have successfully applied discrete diffusion models to various domains, such as visual understanding and image generation, revealing their considerable potential as a promising backbone for multimodal systems. Drawing inspiration from these pioneering research, we introduce Omni-Diffusion, the first any-to-any multimodal language model built entirely on mask-based discrete diffusion models, which unifies understanding and generation across text, speech, and images. Omni-Diffusion employs a unified mask-based discrete diffusion model to directly capture the joint distribution over discrete multimodal tokens. This approach supports not only bimodal tasks but also more complex scenarios involving multiple modalities. On a diverse set of benchmarks, our method outperforms or performs on par with existing multimodal systems that process two or more modalities, highlighting the significant promise of diffusion models in powering the next generation of multimodal foundation models. Project webpage: https://omni-diffusion.github.io.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.06577</guid>
|
|
<pubDate>Fri, 06 Mar 2026 18:59:57 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Are Audio-Language Models Listening? Audio-Specialist Heads for Adaptive Audio Steering</title>
|
|
<link>https://arxiv.org/abs/2603.06854</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.06854.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Neta Glazer, Lenny Aharon, Ethan Fetaya</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Multimodal large language models can exhibit text dominance, over-relying on linguistic priors instead of grounding predictions in non-text inputs. One example is large audio-language models (LALMs) where decisive audio evidence can be under-utilized even when it contains important information. To address this issue we use mechanistic interpretability to identify a small set of audio-specialist attention heads whose audio attention yields a ``listening'' signal. We show that this signal increases when audio evidence affects the model's output, providing an indicator of audio engagement under standard prompting. Leveraging this localization, we construct an audio--silence steering direction and apply an inference-time activation intervention to the final representation, amplifying the model's audio effect. To demonstrate the utility of this intervention, we show on MMAU that this improves accuracy by up to +8.0 percentage points on two Qwen-based LALMs, without any parameter updates.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.06854</guid>
|
|
<pubDate>Fri, 06 Mar 2026 20:18:30 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Hindsight Credit Assignment for Long-Horizon LLM Agents</title>
|
|
<link>https://arxiv.org/abs/2603.08754</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.08754.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hui-Ze Tan, Xiao-Wen Yang, Hao Chen, Jie-Jing Shao, Yi Wen, Yuteng Shen, Weihong Luo, Xiku Du, Lan-Zhe Guo, Yu-Feng Li</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Large Language Model (LLM) agents often face significant credit assignment challenges in long-horizon, multi-step tasks due to sparse rewards. Existing value-free methods, such as Group Relative Policy Optimization (GRPO), encounter two fundamental bottlenecks: inaccurate step-level Q-value estimation and misaligned value baselines for intermediate states. To address these limitations, we introduce HCAPO, the first framework to integrate hindsight credit assignment into LLM agents. HCAPO leverages the LLM itself as a post-hoc critic to refine step-level Q-values through hindsight reasoning. Furthermore, HCAPO's multi-scale advantage mechanism effectively supplements the inaccurate value baselines at critical decision states. Evaluations across three challenging benchmarks, including WebShop and ALFWorld, demonstrate that HCAPO consistently outperforms state-of-the-art RL methods. Notably, HCAPO achieves a 7.7% improvement in success rate on WebShop and a 13.8% on ALFWorld over GRPO using the Qwen2.5-7B-Instruct model. These results indicate that HCAPO significantly enhances exploration efficiency, promotes concise decision-making, and ensures scalability in complex, long-horizon tasks.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.08754</guid>
|
|
<pubDate>Sat, 07 Mar 2026 06:05:20 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Unlocking Data Value in Finance: A Study on Distillation and Difficulty-Aware Training</title>
|
|
<link>https://arxiv.org/abs/2603.07223</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.07223.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chuxue Cao, Honglin Lin, Zhanping Zhong, Xin Gao, Mengzhang Cai, Conghui He, Sirui Han, Lijun Wu</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Large Language Models (LLMs) have demonstrated strong general capabilities, yet their deployment in finance remains challenging due to dense domain-specific terminology, stringent numerical reasoning requirements, and low tolerance for factual errors. We conduct a controlled empirical study showing that in specialized vertical domains, performance is largely determined by the quality and difficulty/verifiability profile of post-training data. We introduce ODA-Fin-SFT-318k, constructed via multi-stage distillation and verification to produce high-quality Chain-of-Thought supervision, and ODA-Fin-RL-12k, curated for hard-but-verifiable tasks that balance reward precision and task diversity. Using standard SFT and RL pipelines, we show that high-quality CoT distillation establishes a robust foundation during SFT, while difficulty- and verifiability-aware sampling improves RL generalization. Evaluated on nine benchmarks spanning general financial tasks, sentiment analysis, and numerical reasoning, our ODA-Fin-RL-8B consistently surpasses open-source state-of-the-art (SOTA) financial LLMs of comparable size. We release our ODA-Fin-SFT-318k and ODA-Fin-RL-12k datasets, along with trained models to advance data-centric financial AI research.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.07223</guid>
|
|
<pubDate>Sat, 07 Mar 2026 14:07:37 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>AutoResearch-RL: Perpetual Self-Evaluating Reinforcement Learning Agents for Autonomous Neural Architecture Discovery</title>
|
|
<link>https://arxiv.org/abs/2603.07300</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.07300.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Nilesh Jain, Rohit Yadav, Sagar Kotian, Claude AI</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> We present AutoResearch-RL, a framework in which a reinforcement learning agent conducts open-ended neural architecture and hyperparameter research without human supervision, running perpetually until a termination oracle signals convergence or resource exhaustion. At each step the agent proposes a code modification to a target training script, executes it under a fixed wall clock time budget, observes a scalar reward derived from validation bits-per-byte (val-bpb), and updates its policy via Proximal Policy Optimisation (PPO). The key design insight is the separation of three concerns: (i) a frozen environment (data pipeline, evaluation protocol, and constants) that guarantees fair cross-experiment comparison; (ii) a mutable target file (train.py) that represents the agent's editable state; and (iii) a meta-learner (the RL agent itself) that accumulates a growing trajectory of experiment outcomes and uses them to inform subsequent proposals. We formalise this as a Markov Decision Process, derive convergence guarantees under mild assumptions, and demonstrate empirically on a single GPU nanochat pretraining benchmark that AutoResearch-RL discovers configurations that match or exceed hand-tuned baselines after approximately 300 overnight iterations, with no human in the loop.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.07300</guid>
|
|
<pubDate>Sat, 07 Mar 2026 17:49:44 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Can Large Language Models Keep Up? Benchmarking Online Adaptation to Continual Knowledge Streams</title>
|
|
<link>https://arxiv.org/abs/2603.07392</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.07392.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiyeon Kim, Hyunji Lee, Dylan Zhou, Sue Hyun Park, Seunghyun Yoon, Trung Bui, Franck Dernoncourt, Sungmin Cha, Minjoon Seo</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> LLMs operating in dynamic real-world contexts often encounter knowledge that evolves continuously or emerges incrementally. To remain accurate and effective, models must adapt to newly arriving information on the fly. We introduce Online Adaptation to Continual Knowledge Streams(OAKS) to evaluate this capability, establishing a benchmark for online adaptation over streaming, continually updating knowledge. Specifically, the benchmark is structured as a sequence of fine-grained context chunks where facts change dynamically across time intervals. OAKS comprises two datasets: OAKS-BABI and OAKS-Novel, where individual facts evolve multiple times across context chunks. These datasets include dense annotations to measure whether models track changes accurately. Evaluating 14 models with varied inference approaches, we observe significant limitations in current methodologies. Both state-of-the-art models and agentic memory systems fail to adapt robustly on OAKS, demonstrating delays in state-tracking and susceptibility to distraction within streaming environments.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.07392</guid>
|
|
<pubDate>Sun, 08 Mar 2026 00:38:39 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Accent Vector: Controllable Accent Manipulation for Multilingual TTS Without Accented Data</title>
|
|
<link>https://arxiv.org/abs/2603.07534</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.07534.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Thanathai Lertpetchpun, Thanapat Trachu, Jihwan Lee, Tiantian Feng, Dani Byrd, Shrikanth Narayanan</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Accent is an integral part of society, reflecting multiculturalism and shaping how individuals express identity. The majority of English speakers are non-native (L2) speakers, yet current Text-To-Speech (TTS) systems primarily model American-accented English due limited accented data. We propose Accent Vector, a controllable representation that enables accent manipulation in multilingual TTS without requiring accented training data. Accent Vector is derived by fine-tuning a TTS system on native speech of a different language (i.e. non-English) and computing task vectors capturing accent characteristics (i.e. in English). By scaling and interpolating the vector, we achieve fine-grained control over accent strength and generate mixed-accent speech. In addition, it generalizes beyond English, enabling accent control across multiple languages. Objective and human evaluations confirm the effectiveness of Accent Vector for fine-grained and compositional accent control.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.07534</guid>
|
|
<pubDate>Sun, 08 Mar 2026 08:48:42 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>PureCC: Pure Learning for Text-to-Image Concept Customization</title>
|
|
<link>https://arxiv.org/abs/2603.07561</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.07561.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhichao Liao, Xiaole Xian, Qingyu Li, Wenyu Qin, Meng Wang, Weicheng Xie, Siyang Song, Pingfa Feng, Long Zeng, Liang Pan</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Existing concept customization methods have achieved remarkable outcomes in high-fidelity and multi-concept customization. However, they often neglect the influence on the original model's behavior and capabilities when learning new personalized concepts. To address this issue, we propose PureCC. PureCC introduces a novel decoupled learning objective for concept customization, which combines the implicit guidance of the target concept with the original conditional prediction. This separated form enables PureCC to substantially focus on the original model during training. Moreover, based on this objective, PureCC designs a dual-branch training pipeline that includes a frozen extractor providing purified target concept representations as implicit guidance and a trainable flow model producing the original conditional prediction, jointly achieving pure learning for personalized concepts. Furthermore, PureCC introduces a novel adaptive guidance scale λ^star to dynamically adjust the guidance strength of the target concept, balancing customization fidelity and model preservation. Extensive experiments show that PureCC achieves state-of-the-art performance in preserving the original behavior and capabilities while enabling high-fidelity concept customization. The code is available at https://github.com/lzc-sg/PureCC.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.07561</guid>
|
|
<pubDate>Sun, 08 Mar 2026 09:50:20 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligence</title>
|
|
<link>https://arxiv.org/abs/2603.07660</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.07660.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuanyuan Gao, Hao Li, Yifei Liu, Xinhao Ji, Yuning Gong, Yuanjun Liao, Fangfu Liu, Manyuan Zhang, Yuchen Yang, Dan Xu, Xue Yang, Huaxi Huang, Hongjie Zhang, Ziwei Liu, Xiao Sun, Dingwen Zhang, Zhihang Zhong</p><p><b>Upvotes:</b> 77</p><p><b>Summary:</b> The pursuit of spatial intelligence fundamentally relies on access to large-scale, fine-grained 3D data. However, existing approaches predominantly construct spatial understanding benchmarks by generating question-answer (QA) pairs from a limited number of manually annotated datasets, rather than systematically annotating new large-scale 3D scenes from raw web data. As a result, their scalability is severely constrained, and model performance is further hindered by domain gaps inherent in these narrowly curated datasets. In this work, we propose Holi-Spatial, the first fully automated, large-scale, spatially-aware multimodal dataset, constructed from raw video inputs without human intervention, using the proposed data curation pipeline. Holi-Spatial supports multi-level spatial supervision, ranging from geometrically accurate 3D Gaussian Splatting (3DGS) reconstructions with rendered depth maps to object-level and relational semantic annotations, together with corresponding spatial Question-Answer (QA) pairs. Following a principled and systematic pipeline, we further construct Holi-Spatial-4M, the first large-scale, high-quality 3D semantic dataset, containing 12K optimized 3DGS scenes, 1.3M 2D masks, 320K 3D bounding boxes, 320K instance captions, 1.2M 3D grounding instances, and 1.2M spatial QA pairs spanning diverse geometric, relational, and semantic reasoning tasks. Holi-Spatial demonstrates exceptional performance in data curation quality, significantly outperforming existing feed-forward and per-scene optimized methods on datasets such as ScanNet, ScanNet++, and DL3DV. Furthermore, fine-tuning Vision-Language Models (VLMs) on spatial reasoning tasks using this dataset has also led to substantial improvements in model performance.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.07660</guid>
|
|
<pubDate>Sun, 08 Mar 2026 14:49:20 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>TDM-R1: Reinforcing Few-Step Diffusion Models with Non-Differentiable Reward</title>
|
|
<link>https://arxiv.org/abs/2603.07700</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.07700.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yihong Luo, Tianyang Hu, Weijian Luo, Jing Tang</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> While few-step generative models have enabled powerful image and video generation at significantly lower cost, generic reinforcement learning (RL) paradigms for few-step models remain an unsolved problem. Existing RL approaches for few-step diffusion models strongly rely on back-propagating through differentiable reward models, thereby excluding the majority of important real-world reward signals, e.g., non-differentiable rewards such as humans' binary likeness, object counts, etc. To properly incorporate non-differentiable rewards to improve few-step generative models, we introduce TDM-R1, a novel reinforcement learning paradigm built upon a leading few-step model, Trajectory Distribution Matching (TDM). TDM-R1 decouples the learning process into surrogate reward learning and generator learning. Furthermore, we developed practical methods to obtain per-step reward signals along the deterministic generation trajectory of TDM, resulting in a unified RL post-training method that significantly improves few-step models' ability with generic rewards. We conduct extensive experiments ranging from text-rendering, visual quality, and preference alignment. All results demonstrate that TDM-R1 is a powerful reinforcement learning paradigm for few-step text-to-image models, achieving state-of-the-art reinforcement learning performances on both in-domain and out-of-domain metrics. Furthermore, TDM-R1 also scales effectively to the recent strong Z-Image model, consistently outperforming both its 100-NFE and few-step variants with only 4 NFEs. Project page: https://github.com/Luo-Yihong/TDM-R1</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.07700</guid>
|
|
<pubDate>Sun, 08 Mar 2026 15:57:10 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>VLM-SubtleBench: How Far Are VLMs from Human-Level Subtle Comparative Reasoning?</title>
|
|
<link>https://arxiv.org/abs/2603.07888</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.07888.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Minkyu Kim, Sangheon Lee, Dongmin Park</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> The ability to distinguish subtle differences between visually similar images is essential for diverse domains such as industrial anomaly detection, medical imaging, and aerial surveillance. While comparative reasoning benchmarks for vision-language models (VLMs) have recently emerged, they primarily focus on images with large, salient differences and fail to capture the nuanced reasoning required for real-world applications. In this work, we introduce VLM-SubtleBench, a benchmark designed to evaluate VLMs on subtle comparative reasoning. Our benchmark covers ten difference types - Attribute, State, Emotion, Temporal, Spatial, Existence, Quantity, Quality, Viewpoint, and Action - and curate paired question-image sets reflecting these fine-grained variations. Unlike prior benchmarks restricted to natural image datasets, our benchmark spans diverse domains, including industrial, aerial, and medical imagery. Through extensive evaluation of both proprietary and open-source VLMs, we reveal systematic gaps between model and human performance across difference types and domains, and provide controlled analyses highlighting where VLMs' reasoning sharply deteriorates. Together, our benchmark and findings establish a foundation for advancing VLMs toward human-level comparative reasoning.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.07888</guid>
|
|
<pubDate>Mon, 09 Mar 2026 02:01:02 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>\$OneMillion-Bench: How Far are Language Agents from Human Experts?</title>
|
|
<link>https://arxiv.org/abs/2603.07980</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.07980.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qianyu Yang, Yang Liu, Jiaqi Li, Jun Bai, Hao Chen, Kaiyuan Chen, Tiliang Duan, Jiayun Dong, Xiaobo Hu, Zixia Jia, Yang Liu, Tao Peng, Yixin Ren, Ran Tian, Zaiyuan Wang, Yanglihong Xiao, Gang Yao, Lingyue Yin, Ge Zhang, Chun Zhang, Jianpeng Jiao, Zilong Zheng, Yuan Gong</p><p><b>Upvotes:</b> 26</p><p><b>Summary:</b> As language models (LMs) evolve from chat assistants to long-horizon agents capable of multi-step reasoning and tool use, existing benchmarks remain largely confined to structured or exam-style tasks that fall short of real-world professional demands. To this end, we introduce \OneMillion-Bench OneMillion-Bench, a benchmark of 400 expert-curated tasks spanning Law, Finance, Industry, Healthcare, and Natural Science, built to evaluate agents across economically consequential scenarios. Unlike prior work, the benchmark requires retrieving authoritative sources, resolving conflicting evidence, applying domain-specific rules, and making constraint decisions, where correctness depends as much on the reasoning process as the final answer. We adopt a rubric-based evaluation protocol scoring factual accuracy, logical coherence, practical feasibility, and professional compliance, focused on expert-level problems to ensure meaningful differentiation across agents. Together, \$OneMillion-Bench provides a unified testbed for assessing agentic reliability, professional depth, and practical readiness in domain-intensive scenarios.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.07980</guid>
|
|
<pubDate>Mon, 09 Mar 2026 05:32:42 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>PIRA-Bench: A Transition from Reactive GUI Agents to GUI-based Proactive Intent Recommendation Agents</title>
|
|
<link>https://arxiv.org/abs/2603.08013</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.08013.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuxiang Chai, Shunye Tang, Han Xiao, Rui Liu, Hongsheng Li</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Current Graphical User Interface (GUI) agents operate primarily under a reactive paradigm: a user must provide an explicit instruction for the agent to execute a task. However, an intelligent AI assistant should be proactive, which is capable of anticipating user intentions directly from continuous visual inputs, such as mobile or desktop screenshots, and offering timely recommendations without explicit user prompting. Transitioning to this proactive paradigm presents significant challenges. Real-world screen activity is rarely linear; it consists of long-horizon trajectories fraught with noisy browsing, meaningless actions, and multithreaded task-switching. To address this gap, we introduce PIRA-Bench (Proactive Intent Recommendation Agent Benchmark), a novel benchmark for evaluating multimodal large language models (MLLMs) on continuous, weakly-supervised visual inputs. Unlike reactive datasets, PIRA-Bench features complex trajectories with multiple interleaved intents and noisy segments with various user profile contexts, challenging agents to detect actionable events while fitting to user preferences. Furthermore, we propose the PIRF baseline, a memory-aware, state-tracking framework that empowers general MLLMs to manage multiple task threads and handle misleading visual inputs. PIRA-Bench serves as an initial step toward robust and proactive GUI-based personal assistants.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.08013</guid>
|
|
<pubDate>Mon, 09 Mar 2026 06:41:32 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>In-Context Reinforcement Learning for Tool Use in Large Language Models</title>
|
|
<link>https://arxiv.org/abs/2603.08068</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.08068.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yaoqi Ye, Yiran Zhao, Keyu Duan, Zeyu Zheng, Kenji Kawaguchi, Cihang Xie, Michael Qizhe Shieh</p><p><b>Upvotes:</b> 28</p><p><b>Summary:</b> While large language models (LLMs) exhibit strong reasoning abilities, their performance on complex tasks is often constrained by the limitations of their internal knowledge. A compelling approach to overcome this challenge is to augment these models with external tools -- such as Python interpreters for mathematical computations or search engines for retrieving factual information. However, enabling models to use these tools effectively remains a significant challenge. Existing methods typically rely on cold-start pipelines that begin with supervised fine-tuning (SFT), followed by reinforcement learning (RL). These approaches often require substantial amounts of labeled data for SFT, which is expensive to annotate or synthesize. In this work, we propose In-Context Reinforcement Learning (ICRL), an RL-only framework that eliminates the need for SFT by leveraging few-shot prompting during the rollout stage of RL. Specifically, ICRL introduces in-context examples within the rollout prompts to teach the model how to invoke external tools. Furthermore, as training progresses, the number of in-context examples is gradually reduced, eventually reaching a zero-shot setting where the model learns to call tools independently. We conduct extensive experiments across a range of reasoning and tool-use benchmarks. Results show that ICRL achieves state-of-the-art performance, demonstrating its effectiveness as a scalable, data-efficient alternative to traditional SFT-based pipelines.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.08068</guid>
|
|
<pubDate>Mon, 09 Mar 2026 08:06:18 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Concept-Guided Fine-Tuning: Steering ViTs away from Spurious Correlations to Improve Robustness</title>
|
|
<link>https://arxiv.org/abs/2603.08309</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.08309.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yehonatan Elisha, Oren Barkan, Noam Koenigstein</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Vision Transformers (ViTs) often degrade under distribution shifts because they rely on spurious correlations, such as background cues, rather than semantically meaningful features. Existing regularization methods, typically relying on simple foreground-background masks, which fail to capture the fine-grained semantic concepts that define an object (e.g., ``long beak'' and ``wings'' for a ``bird''). As a result, these methods provide limited robustness to distribution shifts. To address this limitation, we introduce a novel finetuning framework that steers model reasoning toward concept-level semantics. Our approach optimizes the model's internal relevance maps to align with spatially grounded concept masks. These masks are generated automatically, without manual annotation: class-relevant concepts are first proposed using an LLM-based, label-free method, and then segmented using a VLM. The finetuning objective aligns relevance with these concept regions while simultaneously suppressing focus on spurious background areas. Notably, this process requires only a minimal set of images and uses half of the dataset classes. Extensive experiments on five out-of-distribution benchmarks demonstrate that our method improves robustness across multiple ViT-based models. Furthermore, we show that the resulting relevance maps exhibit stronger alignment with semantic object parts, offering a scalable path toward more robust and interpretable vision models. Finally, we confirm that concept-guided masks provide more effective supervision for model robustness than conventional segmentation maps, supporting our central hypothesis.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.08309</guid>
|
|
<pubDate>Mon, 09 Mar 2026 12:31:14 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>NLE: Non-autoregressive LLM-based ASR by Transcript Editing</title>
|
|
<link>https://arxiv.org/abs/2603.08397</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.08397.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Avihu Dekel, Samuel Thomas, Takashi Fukada, George Saon</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> While autoregressive (AR) LLM-based ASR systems achieve strong accuracy, their sequential decoding limits parallelism and incurs high latency. We propose NLE, a non-autoregressive (NAR) approach that formulates speech recognition as conditional transcript editing, enabling fully parallel prediction. NLE extracts acoustic embeddings and an initial hypothesis from a pretrained speech encoder, then refines the hypothesis using a bidirectional LLM editor trained with a latent alignment objective. An interleaved padding strategy exploits the identity mapping bias of Transformers, allowing the model to focus on corrections rather than full reconstruction. On the Open ASR leaderboard, NLE++ achieves 5.67% average WER with an RTFx (inverse real-time factor) of 1630. In single-utterance scenarios, NLE achieves 27x speedup over the AR baseline, making it suitable for real-time applications.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.08397</guid>
|
|
<pubDate>Mon, 09 Mar 2026 13:56:52 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>RetroAgent: From Solving to Evolving via Retrospective Dual Intrinsic Feedback</title>
|
|
<link>https://arxiv.org/abs/2603.08561</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.08561.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiaoying Zhang, Zichen Liu, Yipeng Zhang, Xia Hu, Wenqi Shao</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Large language model (LLM)-based agents trained with reinforcement learning (RL) have shown strong potential on complex interactive tasks. However, standard RL paradigms favor static problem-solving over continuous adaptation: agents often converge to suboptimal strategies due to insufficient exploration, while learned knowledge remains implicit within parameters rather than explicitly retrievable, limiting effective experiential learning. To address these limitations, we introduce RetroAgent, an online RL framework that empowers agents to master complex interactive environments not just by solving, but by evolving. Concretely, RetroAgent features a hindsight self-reflection mechanism that produces dual intrinsic feedback: (1) intrinsic numerical feedback that that tracks incremental subtask completion relative to prior attempts, rewarding promising explorations, and (2) intrinsic language feedback that distills reusable lessons into a memory buffer, retrieved via our proposed Similarity & Utility-Aware Upper Confidence Bound (SimUtil-UCB) strategy balancing relevance, utility, and exploration to effectively leverage past experiences. Extensive experiments on two model families across four challenging agentic tasks demonstrate that RetroAgent significantly outperforms existing methods, achieving state-of-the-art results -- e.g., surpassing Group Relative Policy Optimization (GRPO)-trained agents by +18.3% on ALFWorld, +15.4% on WebShop, +27.1% on Sokoban, and +8.9% on MineSweeper -- while exhibiting strong test-time adaptation and generalization to out-of-distribution scenarios.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.08561</guid>
|
|
<pubDate>Mon, 09 Mar 2026 16:23:33 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>CARE-Edit: Condition-Aware Routing of Experts for Contextual Image Editing</title>
|
|
<link>https://arxiv.org/abs/2603.08589</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.08589.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yucheng Wang, Zedong Wang, Yuetong Wu, Yue Ma, Dan Xu</p><p><b>Upvotes:</b> 34</p><p><b>Summary:</b> Unified diffusion editors often rely on a fixed, shared backbone for diverse tasks, suffering from task interference and poor adaptation to heterogeneous demands (e.g., local vs global, semantic vs photometric). In particular, prevalent ControlNet and OmniControl variants combine multiple conditioning signals (e.g., text, mask, reference) via static concatenation or additive adapters which cannot dynamically prioritize or suppress conflicting modalities, thus resulting in artifacts like color bleeding across mask boundaries, identity or style drift, and unpredictable behavior under multi-condition inputs. To address this, we propose Condition-Aware Routing of Experts (CARE-Edit) that aligns model computation with specific editing competencies. At its core, a lightweight latent-attention router assigns encoded diffusion tokens to four specialized experts--Text, Mask, Reference, and Base--based on multi-modal conditions and diffusion timesteps: (i) a Mask Repaint module first refines coarse user-defined masks for precise spatial guidance; (ii) the router applies sparse top-K selection to dynamically allocate computation to the most relevant experts; (iii) a Latent Mixture module subsequently fuses expert outputs, coherently integrating semantic, spatial, and stylistic information to the base images. Experiments validate CARE-Edit's strong performance on contextual editing tasks, including erasure, replacement, text-driven edits, and style transfer. Empirical analysis further reveals task-specific behavior of specialized experts, showcasing the importance of dynamic, condition-aware processing to mitigate multi-condition conflicts.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.08589</guid>
|
|
<pubDate>Mon, 09 Mar 2026 16:40:47 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>CAST: Modeling Visual State Transitions for Consistent Video Retrieval</title>
|
|
<link>https://arxiv.org/abs/2603.08648</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.08648.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yanqing Liu, Yingcheng Liu, Fanghong Dong, Budianto Budianto, Cihang Xie, Yan Jiao</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> As video content creation shifts toward long-form narratives, composing short clips into coherent storylines becomes increasingly important. However, prevailing retrieval formulations remain context-agnostic at inference time, prioritizing local semantic alignment while neglecting state and identity consistency. To address this structural limitation, we formalize the task of Consistent Video Retrieval (CVR) and introduce a diagnostic benchmark spanning YouCook2, COIN, and CrossTask. We propose CAST (Context-Aware State Transition), a lightweight, plug-and-play adapter compatible with diverse frozen vision-language embedding spaces. By predicting a state-conditioned residual update (Δ) from visual history, CAST introduces an explicit inductive bias for latent state evolution. Extensive experiments show that CAST improves performance on YouCook2 and CrossTask, remains competitive on COIN, and consistently outperforms zero-shot baselines across diverse foundation backbones. Furthermore, CAST provides a useful reranking signal for black-box video generation candidates (e.g., from Veo), promoting more temporally coherent continuations.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.08648</guid>
|
|
<pubDate>Mon, 09 Mar 2026 17:26:26 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>CoCo: Code as CoT for Text-to-Image Preview and Rare Concept Generation</title>
|
|
<link>https://arxiv.org/abs/2603.08652</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.08652.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haodong Li, Chunmei Qing, Huanyu Zhang, Dongzhi Jiang, Yihang Zou, Hongbo Peng, Dingming Li, Yuhong Dai, ZePeng Lin, Juanxi Tian, Yi Zhou, Siqi Dai, Jingwei Wu</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> Recent advancements in Unified Multimodal Models (UMMs) have significantly advanced text-to-image (T2I) generation, particularly through the integration of Chain-of-Thought (CoT) reasoning. However, existing CoT-based T2I methods largely rely on abstract natural-language planning, which lacks the precision required for complex spatial layouts, structured visual elements, and dense textual content. In this work, we propose CoCo (Code-as-CoT), a code-driven reasoning framework that represents the reasoning process as executable code, enabling explicit and verifiable intermediate planning for image generation. Given a text prompt, CoCo first generates executable code that specifies the structural layout of the scene, which is then executed in a sandboxed environment to render a deterministic draft image. The model subsequently refines this draft through fine-grained image editing to produce the final high-fidelity result. To support this training paradigm, we construct CoCo-10K, a curated dataset containing structured draft-final image pairs designed to teach both structured draft construction and corrective visual refinement. Empirical evaluations on StructT2IBench, OneIG-Bench, and LongText-Bench show that CoCo achieves improvements of +68.83%, +54.8%, and +41.23% over direct generation, while also outperforming other generation methods empowered by CoT. These results demonstrate that executable code is an effective and reliable reasoning paradigm for precise, controllable, and structured text-to-image generation. The code is available at: https://github.com/micky-li-hd/CoCo</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.08652</guid>
|
|
<pubDate>Mon, 09 Mar 2026 17:31:16 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>How Far Can Unsupervised RLVR Scale LLM Training?</title>
|
|
<link>https://arxiv.org/abs/2603.08660</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.08660.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bingxiang He, Yuxin Zuo, Zeyuan Liu, Shangziqi Zhao, Zixuan Fu, Junlin Yang, Cheng Qian, Kaiyan Zhang, Yuchen Fan, Ganqu Cui, Xiusi Chen, Youbang Sun, Xingtai Lv, Xuekai Zhu, Li Sheng, Ran Li, Huan-ang Gao, Yuchen Zhang, Bowen Zhou, Zhiyuan Liu, Ning Ding</p><p><b>Upvotes:</b> 47</p><p><b>Summary:</b> Unsupervised reinforcement learning with verifiable rewards (URLVR) offers a pathway to scale LLM training beyond the supervision bottleneck by deriving rewards without ground truth labels. Recent works leverage model intrinsic signals, showing promising early gains, yet their potential and limitations remain unclear. In this work, we revisit URLVR and provide a comprehensive analysis spanning taxonomy, theory and extensive experiments. We first classify URLVR methods into intrinsic versus external based on reward sources, then establish a unified theoretical framework revealing that all intrinsic methods converge toward sharpening the model's initial distribution This sharpening mechanism succeeds when initial confidence aligns with correctness but fails catastrophically when misaligned. Through systematic experiments, we show intrinsic rewards consistently follow a rise-then-fall pattern across methods, with collapse timing determined by model prior rather than engineering choices. Despite these scaling limits, we find intrinsic rewards remain valuable in test-time training on small datasets, and propose Model Collapse Step to measure model prior, serving as a practical indicator for RL trainability. Finally, we explore external reward methods that ground verification in computational asymmetries, showing preliminary evidence they may escape the confidence-correctness ceiling. Our findings chart boundaries for intrinsic URLVR while motivating paths toward scalable alternatives.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.08660</guid>
|
|
<pubDate>Mon, 09 Mar 2026 17:38:11 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>HiAR: Efficient Autoregressive Long Video Generation via Hierarchical Denoising</title>
|
|
<link>https://arxiv.org/abs/2603.08703</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.08703.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kai Zou, Dian Zheng, Hongbo Liu, Tiankai Hang, Bin Liu, Nenghai Yu</p><p><b>Upvotes:</b> 29</p><p><b>Summary:</b> Autoregressive (AR) diffusion offers a promising framework for generating videos of theoretically infinite length. However, a major challenge is maintaining temporal continuity while preventing the progressive quality degradation caused by error accumulation. To ensure continuity, existing methods typically condition on highly denoised contexts; yet, this practice propagates prediction errors with high certainty, thereby exacerbating degradation. In this paper, we argue that a highly clean context is unnecessary. Drawing inspiration from bidirectional diffusion models, which denoise frames at a shared noise level while maintaining coherence, we propose that conditioning on context at the same noise level as the current block provides sufficient signal for temporal consistency while effectively mitigating error propagation. Building on this insight, we propose HiAR, a hierarchical denoising framework that reverses the conventional generation order: instead of completing each block sequentially, it performs causal generation across all blocks at every denoising step, so that each block is always conditioned on context at the same noise level. This hierarchy naturally admits pipelined parallel inference, yielding a 1.8 wall-clock speedup in our 4-step setting. We further observe that self-rollout distillation under this paradigm amplifies a low-motion shortcut inherent to the mode-seeking reverse-KL objective. To counteract this, we introduce a forward-KL regulariser in bidirectional-attention mode, which preserves motion diversity for causal inference without interfering with the distillation loss. On VBench (20s generation), HiAR achieves the best overall score and the lowest temporal drift among all compared methods.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.08703</guid>
|
|
<pubDate>Mon, 09 Mar 2026 17:58:16 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Agentic Critical Training</title>
|
|
<link>https://arxiv.org/abs/2603.08706</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.08706.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weize Liu, Minghui Liu, Sy-Tuyen Ho, Souradip Chakraborty, Xiyao Wang, Furong Huang</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Training large language models (LLMs) as autonomous agents often begins with imitation learning, but it only teaches agents what to do without understanding why: agents never contrast successful actions against suboptimal alternatives and thus lack awareness of action quality. Recent approaches attempt to address this by introducing self-reflection supervision derived from contrasts between expert and alternative actions. However, the training paradigm fundamentally remains imitation learning: the model imitates pre-constructed reflection text rather than learning to reason autonomously. We propose Agentic Critical Training (ACT), a reinforcement learning paradigm that trains agents to identify the better action among alternatives. By rewarding whether the model's judgment is correct, ACT drives the model to autonomously develop reasoning about action quality, producing genuine self-reflection rather than imitating it. Across three challenging agent benchmarks, ACT consistently improves agent performance when combined with different post-training methods. It achieves an average improvement of 5.07 points over imitation learning and 4.62 points over reinforcement learning. Compared to approaches that inject reflection capability through knowledge distillation, ACT also demonstrates clear advantages, yielding an average improvement of 2.42 points. Moreover, ACT enables strong out-of-distribution generalization on agentic benchmarks and improves performance on general reasoning benchmarks without any reasoning-specific training data, highlighting the value of our method. These results suggest that ACT is a promising path toward developing more reflective and capable LLM agents.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.08706</guid>
|
|
<pubDate>Mon, 09 Mar 2026 17:58:56 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Scale Space Diffusion</title>
|
|
<link>https://arxiv.org/abs/2603.08709</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.08709.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Soumik Mukhopadhyay, Prateksha Udhayanan, Abhinav Shrivastava</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Diffusion models degrade images through noise, and reversing this process reveals an information hierarchy across timesteps. Scale-space theory exhibits a similar hierarchy via low-pass filtering. We formalize this connection and show that highly noisy diffusion states contain no more information than small, downsampled images - raising the question of why they must be processed at full resolution. To address this, we fuse scale spaces into the diffusion process by formulating a family of diffusion models with generalized linear degradations and practical implementations. Using downsampling as the degradation yields our proposed Scale Space Diffusion. To support Scale Space Diffusion, we introduce Flexi-UNet, a UNet variant that performs resolution-preserving and resolution-increasing denoising using only the necessary parts of the network. We evaluate our framework on CelebA and ImageNet and analyze its scaling behavior across resolutions and network depths. Our project website ( https://prateksha.github.io/projects/scale-space-diffusion/ ) is available publicly.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.08709</guid>
|
|
<pubDate>Mon, 09 Mar 2026 17:59:42 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Test-Driven AI Agent Definition (TDAD): Compiling Tool-Using Agents from Behavioral Specifications</title>
|
|
<link>https://arxiv.org/abs/2603.08806</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.08806.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tzafrir Rehan</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> We present Test-Driven AI Agent Definition (TDAD), a methodology that treats agent prompts as compiled artifacts: engineers provide behavioral specifications, a coding agent converts them into executable tests, and a second coding agent iteratively refines the prompt until tests pass. Deploying tool-using LLM agents in production requires measurable behavioral compliance that current development practices cannot provide. Small prompt changes cause silent regressions, tool misuse goes undetected, and policy violations emerge only after deployment. To mitigate specification gaming, TDAD introduces three mechanisms: (1) visible/hidden test splits that withhold evaluation tests during compilation, (2) semantic mutation testing via a post-compilation agent that generates plausible faulty prompt variants, with the harness measuring whether the test suite detects them, and (3) spec evolution scenarios that quantify regression safety when requirements change. We evaluate TDAD on SpecSuite-Core, a benchmark of four deeply-specified agents spanning policy compliance, grounded analytics, runbook adherence, and deterministic enforcement. Across 24 independent trials, TDAD achieves 92% v1 compilation success with 97% mean hidden pass rate; evolved specifications compile at 58%, with most failed runs passing all visible tests except 1-2, and show 86-100% mutation scores, 78% v2 hidden pass rate, and 97% regression safety scores. The implementation is available as an open benchmark at https://github.com/f-labs-io/tdad-paper-code.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.08806</guid>
|
|
<pubDate>Mon, 09 Mar 2026 18:04:54 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Training Language Models via Neural Cellular Automata</title>
|
|
<link>https://arxiv.org/abs/2603.10055</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.10055.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dan Lee, Seungwook Han, Akarsh Kumar, Pulkit Agrawal</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Pre-training is crucial for large language models (LLMs), as it is when most representations and capabilities are acquired. However, natural language pre-training has problems: high-quality text is finite, it contains human biases, and it entangles knowledge with reasoning. This raises a fundamental question: is natural language the only path to intelligence? We propose using neural cellular automata (NCA) to generate synthetic, non-linguistic data for pre-pre-training LLMs--training on synthetic-then-natural language. NCA data exhibits rich spatiotemporal structure and statistics resembling natural language while being controllable and cheap to generate at scale. We find that pre-pre-training on only 164M NCA tokens improves downstream language modeling by up to 6% and accelerates convergence by up to 1.6x. Surprisingly, this even outperforms pre-pre-training on 1.6B tokens of natural language from Common Crawl with more compute. These gains also transfer to reasoning benchmarks, including GSM8K, HumanEval, and BigBench-Lite. Investigating what drives transfer, we find that attention layers are the most transferable, and that optimal NCA complexity varies by domain: code benefits from simpler dynamics, while math and web text favor more complex ones. These results enable systematic tuning of the synthetic distribution to target domains. More broadly, our work opens a path toward more efficient models with fully synthetic pre-training.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.10055</guid>
|
|
<pubDate>Mon, 09 Mar 2026 18:14:26 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Fish Audio S2 Technical Report</title>
|
|
<link>https://arxiv.org/abs/2603.08823</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.08823.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shijia Liao, Yuxuan Wang, Songting Liu, Yifan Cheng, Ruoyi Zhang, Tianyu Li, Shidong Li, Yisheng Zheng, Xingwei Liu, Qingzheng Wang, Zhizhuo Zhou, Jiahua Liu, Xin Chen, Dawei Han</p><p><b>Upvotes:</b> 26</p><p><b>Summary:</b> We introduce Fish Audio S2, an open-sourced text-to-speech system featuring multi-speaker, multi-turn generation, and, most importantly, instruction-following control via natural-language descriptions. To scale training, we develop a multi-stage training recipe together with a staged data pipeline covering video captioning and speech captioning, voice-quality assessment, and reward modeling. To push the frontier of open-source TTS, we release our model weights, fine-tuning code, and an SGLang-based inference engine. The inference engine is production-ready for streaming, achieving an RTF of 0.195 and a time-to-first-audio below 100 ms.Our code and weights are available on GitHub (https://github.com/fishaudio/fish-speech) and Hugging Face (https://huggingface.co/fishaudio/s2-pro). We highly encourage readers to visit https://fish.audio to try custom voices.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.08823</guid>
|
|
<pubDate>Mon, 09 Mar 2026 18:34:33 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Reading, Not Thinking: Understanding and Bridging the Modality Gap When Text Becomes Pixels in Multimodal LLMs</title>
|
|
<link>https://arxiv.org/abs/2603.09095</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.09095.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kaiser Sun, Xiaochuang Yuan, Hongjun Liu, Chen Zhao, Cheng Zhang, Mark Dredze, Fan Bai</p><p><b>Upvotes:</b> 25</p><p><b>Summary:</b> Multimodal large language models (MLLMs) can process text presented as images, yet they often perform worse than when the same content is provided as textual tokens. We systematically diagnose this "modality gap" by evaluating seven MLLMs across seven benchmarks in five input modes, spanning both synthetically rendered text and realistic document images from arXiv PDFs to Wikipedia pages. We find that the modality gap is task- and data-dependent. For example, math tasks degrade by over 60 points on synthetic renderings, while natural document images often match or exceed text-mode performance. Rendering choices such as font and resolution are strong confounds, with font alone swinging accuracy by up to 47 percentage points. To understand this, we conduct a grounded-theory error analysis of over 4,000 examples, revealing that image mode selectively amplifies reading errors (calculation and formatting failures) while leaving knowledge and reasoning errors largely unchanged, and that some models exhibit a chain-of-thought reasoning collapse under visual input. Motivated by these findings, we propose a self-distillation method that trains the model on its own pure text reasoning traces paired with image inputs, raising image-mode accuracy on GSM8K from 30.71% to 92.72% and transferring to unseen benchmarks without catastrophic forgetting. Overall, our study provides a systematic understanding of the modality gap and suggests a practical path toward improving visual text understanding in multimodal language models.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.09095</guid>
|
|
<pubDate>Tue, 10 Mar 2026 02:14:23 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Decoupling Reasoning and Confidence: Resurrecting Calibration in Reinforcement Learning from Verifiable Rewards</title>
|
|
<link>https://arxiv.org/abs/2603.09117</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.09117.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhengzhao Ma, Xueru Wen, Boxi Cao, Yaojie Lu, Hongyu Lin, Jinglin Yang, Min He, Xianpei Han, Le Sun</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Reinforcement Learning from Verifiable Rewards (RLVR) significantly enhances large language models (LLMs) reasoning but severely suffers from calibration degeneration, where models become excessively over-confident in incorrect answers. Previous studies devote to directly incorporating calibration objective into existing optimization target. However, our theoretical analysis demonstrates that there exists a fundamental gradient conflict between the optimization for maximizing policy accuracy and minimizing calibration error. Building on this insight, we propose DCPO, a simple yet effective framework that systematically decouples reasoning and calibration objectives. Extensive experiments demonstrate that our DCPO not only preserves accuracy on par with GRPO but also achieves the best calibration performance and substantially mitigates the over-confidence issue. Our study provides valuable insights and practical solution for more reliable LLM deployment.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.09117</guid>
|
|
<pubDate>Tue, 10 Mar 2026 02:47:59 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>RubiCap: Rubric-Guided Reinforcement Learning for Dense Image Captioning</title>
|
|
<link>https://arxiv.org/abs/2603.09160</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.09160.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tzu-Heng Huang, Sirajul Salekin, Javier Movellan, Frederic Sala, Manjot Bilkhu</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Dense image captioning is critical for cross-modal alignment in vision-language pretraining and text-to-image generation, but scaling expert-quality annotations is prohibitively expensive. While synthetic captioning via strong vision-language models (VLMs) is a practical alternative, supervised distillation often yields limited output diversity and weak generalization. Reinforcement learning (RL) could overcome these limitations, but its successes have so far been concentrated in verifiable domains that rely on deterministic checkers -- a luxury not available in open-ended captioning. We address this bottleneck with RubiCap, a novel RL framework that derives fine-grained, sample-specific reward signals from LLM-written rubrics. RubiCap first assembles a diverse committee of candidate captions, then employs an LLM rubric writer to extract consensus strengths and diagnose deficiencies in the current policy. These insights are converted into explicit evaluation criteria, enabling an LLM judge to decompose holistic quality assessment and replace coarse scalar rewards with structured, multi-faceted evaluations. Across extensive benchmarks, RubiCap achieves the highest win rates on CapArena, outperforming supervised distillation, prior RL methods, human-expert annotations, and GPT-4V-augmented outputs. On CaptionQA, it demonstrates superior word efficiency: our 7B model matches Qwen2.5-VL-32B-Instruct, and our 3B model surpasses its 7B counterpart. Remarkably, using the compact RubiCap-3B as a captioner produces stronger pretrained VLMs than those trained on captions from proprietary models.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.09160</guid>
|
|
<pubDate>Tue, 10 Mar 2026 03:51:27 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>The Reasoning Trap -- Logical Reasoning as a Mechanistic Pathway to Situational Awareness</title>
|
|
<link>https://arxiv.org/abs/2603.09200</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.09200.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Subramanyam Sahoo, Aman Chadha, Vinija Jain, Divya Chaudhary</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Situational awareness, the capacity of an AI system to recognize its own nature, understand its training and deployment context, and reason strategically about its circumstances, is widely considered among the most dangerous emergent capabilities in advanced AI systems. Separately, a growing research effort seeks to improve the logical reasoning capabilities of large language models (LLMs) across deduction, induction, and abduction. In this paper, we argue that these two research trajectories are on a collision course. We introduce the RAISE framework (Reasoning Advancing Into Self Examination), which identifies three mechanistic pathways through which improvements in logical reasoning enable progressively deeper levels of situational awareness: deductive self inference, inductive context recognition, and abductive self modeling. We formalize each pathway, construct an escalation ladder from basic self recognition to strategic deception, and demonstrate that every major research topic in LLM logical reasoning maps directly onto a specific amplifier of situational awareness. We further analyze why current safety measures are insufficient to prevent this escalation. We conclude by proposing concrete safeguards, including a "Mirror Test" benchmark and a Reasoning Safety Parity Principle, and pose an uncomfortable but necessary question to the logical reasoning community about its responsibility in this trajectory.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.09200</guid>
|
|
<pubDate>Tue, 10 Mar 2026 05:18:48 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data</title>
|
|
<link>https://arxiv.org/abs/2603.09206</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.09206.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zongxia Li, Hongyang Du, Chengsong Huang, Xiyang Wu, Lantao Yu, Yicheng He, Jing Xie, Xiaomin Wu, Zhichao Liu, Jiarui Zhang, Fuxiao Liu</p><p><b>Upvotes:</b> 43</p><p><b>Summary:</b> Self-evolving has emerged as a key paradigm for improving foundational models such as Large Language Models (LLMs) and Vision Language Models (VLMs) with minimal human intervention. While recent approaches have demonstrated that LLM agents can self-evolve from scratch with little to no data, VLMs introduce an additional visual modality that typically requires at least some seed data, such as images, to bootstrap the self-evolution process. In this work, we present Multi-model Multimodal Zero (MM-Zero), the first RL-based framework to achieve zero-data self-evolution for VLM reasoning. Moving beyond prior dual-role (Proposer and Solver) setups, MM-Zero introduces a multi-role self-evolving training framework comprising three specialized roles: a Proposer that generates abstract visual concepts and formulates questions; a Coder that translates these concepts into executable code (e.g., Python, SVG) to render visual images; and a Solver that performs multimodal reasoning over the generated visual content. All three roles are initialized from the same base model and trained using Group Relative Policy Optimization (GRPO), with carefully designed reward mechanisms that integrate execution feedback, visual verification, and difficulty balancing. Our experiments show that MM-Zero improves VLM reasoning performance across a wide range of multimodal benchmarks. MM-Zero establishes a scalable path toward self-evolving multi-model systems for multimodal models, extending the frontier of self-improvement beyond the conventional two-model paradigm.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.09206</guid>
|
|
<pubDate>Tue, 10 Mar 2026 05:23:26 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Flash-KMeans: Fast and Memory-Efficient Exact K-Means</title>
|
|
<link>https://arxiv.org/abs/2603.09229</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.09229.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shuo Yang, Haocheng Xi, Yilong Zhao, Muyang Li, Xiaoze Fan, Jintao Zhang, Han Cai, Yujun Lin, Xiuyu Li, Kurt Keutzer, Song Han, Chenfeng Xu, Ion Stoica</p><p><b>Upvotes:</b> 65</p><p><b>Summary:</b> k-means has historically been positioned primarily as an offline processing primitive, typically used for dataset organization or embedding preprocessing rather than as a first-class component in online systems. In this work, we revisit this classical algorithm under the lens of modern AI system design and enable k-means as an online primitive. We point out that existing GPU implementations of k-means remain fundamentally bottlenecked by low-level system constraints rather than theoretical algorithmic complexity. Specifically, the assignment stage suffers from a severe IO bottleneck due to the massive explicit materialization of the N times K distance matrix in High Bandwidth Memory (HBM). Simultaneously, the centroid update stage is heavily penalized by hardware-level atomic write contention caused by irregular, scatter-style token aggregations. To bridge this performance gap, we propose flash-kmeans, an IO-aware and contention-free k-means implementation for modern GPU workloads. Flash-kmeans introduces two core kernel-level innovations: (1) FlashAssign, which fuses distance computation with an online argmin to completely bypass intermediate memory materialization; (2) sort-inverse update, which explicitly constructs an inverse mapping to transform high-contention atomic scatters into high-bandwidth, segment-level localized reductions. Furthermore, we integrate algorithm-system co-designs, including chunked-stream overlap and cache-aware compile heuristics, to ensure practical deployability. Extensive evaluations on NVIDIA H200 GPUs demonstrate that flash-kmeans achieves up to 17.9times end-to-end speedup over best baselines, while outperforming industry-standard libraries like cuML and FAISS by 33times and over 200times, respectively.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.09229</guid>
|
|
<pubDate>Tue, 10 Mar 2026 05:54:52 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Streaming Autoregressive Video Generation via Diagonal Distillation</title>
|
|
<link>https://arxiv.org/abs/2603.09488</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.09488.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jinxiu Liu, Xuanming Liu, Kangfu Mei, Yandong Wen, Ming-HsuanYang, Weiyang Liu</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Large pretrained diffusion models have significantly enhanced the quality of generated videos, and yet their use in real-time streaming remains limited. Autoregressive models offer a natural framework for sequential frame synthesis but require heavy computation to achieve high fidelity. Diffusion distillation can compress these models into efficient few-step variants, but existing video distillation approaches largely adapt image-specific methods that neglect temporal dependencies. These techniques often excel in image generation but underperform in video synthesis, exhibiting reduced motion coherence, error accumulation over long sequences, and a latency-quality trade-off. We identify two factors that result in these limitations: insufficient utilization of temporal context during step reduction and implicit prediction of subsequent noise levels in next-chunk prediction (i.e., exposure bias). To address these issues, we propose Diagonal Distillation, which operates orthogonally to existing approaches and better exploits temporal information across both video chunks and denoising steps. Central to our approach is an asymmetric generation strategy: more steps early, fewer steps later. This design allows later chunks to inherit rich appearance information from thoroughly processed early chunks, while using partially denoised chunks as conditional inputs for subsequent synthesis. By aligning the implicit prediction of subsequent noise levels during chunk generation with the actual inference conditions, our approach mitigates error propagation and reduces oversaturation in long-range sequences. We further incorporate implicit optical flow modeling to preserve motion quality under strict step constraints. Our method generates a 5-second video in 2.61 seconds (up to 31 FPS), achieving a 277.3x speedup over the undistilled model.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.09488</guid>
|
|
<pubDate>Tue, 10 Mar 2026 10:45:24 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>MiniAppBench: Evaluating the Shift from Text to Interactive HTML Responses in LLM-Powered Assistants</title>
|
|
<link>https://arxiv.org/abs/2603.09652</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.09652.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zuhao Zhang, Chengyue Yu, Yuante Li, Chenyi Zhuang, Linjian Mo, Shuai Li</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> With the rapid advancement of Large Language Models (LLMs) in code generation, human-AI interaction is evolving from static text responses to dynamic, interactive HTML-based applications, which we term MiniApps. These applications require models to not only render visual interfaces but also construct customized interaction logic that adheres to real-world principles. However, existing benchmarks primarily focus on algorithmic correctness or static layout reconstruction, failing to capture the capabilities required for this new paradigm. To address this gap, we introduce MiniAppBench, the first comprehensive benchmark designed to evaluate principle-driven, interactive application generation. Sourced from a real-world application with 10M+ generations, MiniAppBench distills 500 tasks across six domains (e.g., Games, Science, and Tools). Furthermore, to tackle the challenge of evaluating open-ended interactions where no single ground truth exists, we propose MiniAppEval, an agentic evaluation framework. Leveraging browser automation, it performs human-like exploratory testing to systematically assess applications across three dimensions: Intention, Static, and Dynamic. Our experiments reveal that current LLMs still face significant challenges in generating high-quality MiniApps, while MiniAppEval demonstrates high alignment with human judgment, establishing a reliable standard for future research. Our code is available in github.com/MiniAppBench.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.09652</guid>
|
|
<pubDate>Tue, 10 Mar 2026 13:30:03 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>RbtAct: Rebuttal as Supervision for Actionable Review Feedback Generation</title>
|
|
<link>https://arxiv.org/abs/2603.09723</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.09723.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sihong Wu, Yiling Ma, Yilun Zhao, Tiansheng Hu, Owen Jiang, Manasi Patwardhan, Arman Cohan</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Large language models (LLMs) are increasingly used across the scientific workflow, including to draft peer-review reports. However, many AI-generated reviews are superficial and insufficiently actionable, leaving authors without concrete, implementable guidance and motivating the gap this work addresses. We propose RbtAct, which targets actionable review feedback generation and places existing peer review rebuttal at the center of learning. Rebuttals show which reviewer comments led to concrete revisions or specific plans, and which were only defended. Building on this insight, we leverage rebuttal as implicit supervision to directly optimize a feedback generator for actionability. To support this objective, we propose a new task called perspective-conditioned segment-level review feedback generation, in which the model is required to produce a single focused comment based on the complete paper and a specified perspective such as experiments and writing. We also build a large dataset named RMR-75K that maps review segments to the rebuttal segments that address them, with perspective labels and impact categories that order author uptake. We then train the Llama-3.1-8B-Instruct model with supervised fine-tuning on review segments followed by preference optimization using rebuttal derived pairs. Experiments with human experts and LLM-as-a-judge show consistent gains in actionability and specificity over strong baselines while maintaining grounding and relevance.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.09723</guid>
|
|
<pubDate>Tue, 10 Mar 2026 14:30:55 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>MA-EgoQA: Question Answering over Egocentric Videos from Multiple Embodied Agents</title>
|
|
<link>https://arxiv.org/abs/2603.09827</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.09827.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kangsan Kim, Yanlai Yang, Suji Kim, Woongyeong Yeo, Youngwan Lee, Mengye Ren, Sung Ju Hwang</p><p><b>Upvotes:</b> 26</p><p><b>Summary:</b> As embodied models become powerful, humans will collaborate with multiple embodied AI agents at their workplace or home in the future. To ensure better communication between human users and the multi-agent system, it is crucial to interpret incoming information from agents in parallel and refer to the appropriate context for each query. Existing challenges include effectively compressing and communicating high volumes of individual sensory inputs in the form of video and correctly aggregating multiple egocentric videos to construct system-level memory. In this work, we first formally define a novel problem of understanding multiple long-horizon egocentric videos simultaneously collected from embodied agents. To facilitate research in this direction, we introduce MultiAgent-EgoQA (MA-EgoQA), a benchmark designed to systemically evaluate existing models in our scenario. MA-EgoQA provides 1.7k questions unique to multiple egocentric streams, spanning five categories: social interaction, task coordination, theory-of-mind, temporal reasoning, and environmental interaction. We further propose a simple baseline model for MA-EgoQA named EgoMAS, which leverages shared memory across embodied agents and agent-wise dynamic retrieval. Through comprehensive evaluation across diverse baselines and EgoMAS on MA-EgoQA, we find that current approaches are unable to effectively handle multiple egocentric streams, highlighting the need for future advances in system-level understanding across the agents. The code and benchmark are available at https://ma-egoqa.github.io.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.09827</guid>
|
|
<pubDate>Tue, 10 Mar 2026 15:48:35 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editing</title>
|
|
<link>https://arxiv.org/abs/2603.09877</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.09877.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Changyao Tian, Danni Yang, Guanzhou Chen, Erfei Cui, Zhaokai Wang, Yuchen Duan, Penghao Yin, Sitao Chen, Ganlin Yang, Mingxin Liu, Zirun Zhu, Ziqian Fan, Leyao Gu, Haomin Wang, Qi Wei, Jinhui Yin, Xue Yang, Zhihang Zhong, Qi Qin, Yi Xin, Bin Fu, Yihao Liu, Jiaye Ge, Qipeng Guo, Gen Luo, Hongsheng Li, Yu Qiao, Kai Chen, Hongjie Zhang</p><p><b>Upvotes:</b> 41</p><p><b>Summary:</b> Unified multimodal models (UMMs) that integrate understanding, reasoning, generation, and editing face inherent trade-offs between maintaining strong semantic comprehension and acquiring powerful generation capabilities. In this report, we present InternVL-U, a lightweight 4B-parameter UMM that democratizes these capabilities within a unified framework. Guided by the principles of unified contextual modeling and modality-specific modular design with decoupled visual representations, InternVL-U integrates a state-of-the-art Multimodal Large Language Model (MLLM) with a specialized MMDiT-based visual generation head. To further bridge the gap between aesthetic generation and high-level intelligence, we construct a comprehensive data synthesis pipeline targeting high-semantic-density tasks, such as text rendering and scientific reasoning, under a reasoning-centric paradigm that leverages Chain-of-Thought (CoT) to better align abstract user intent with fine-grained visual generation details. Extensive experiments demonstrate that InternVL-U achieves a superior performance - efficiency balance. Despite using only 4B parameters, it consistently outperforms unified baseline models with over 3x larger scales such as BAGEL (14B) on various generation and editing tasks, while retaining strong multimodal understanding and reasoning capabilities.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.09877</guid>
|
|
<pubDate>Tue, 10 Mar 2026 16:38:33 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Stepping VLMs onto the Court: Benchmarking Spatial Intelligence in Sports</title>
|
|
<link>https://arxiv.org/abs/2603.09896</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.09896.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuchen Yang, Yuqing Shao, Duxiu Huang, Linfeng Dong, Yifei Liu, Suixin Tang, Xiang Zhou, Yuanyuan Gao, Wei Wang, Yue Zhou, Xue Yang, Yanfeng Wang, Xiao Sun, Zhihang Zhong</p><p><b>Upvotes:</b> 25</p><p><b>Summary:</b> Sports have long attracted broad attention as they push the limits of human physical and cognitive capabilities. Amid growing interest in spatial intelligence for vision-language models (VLMs), sports provide a natural testbed for understanding high-intensity human motion and dynamic object interactions. To this end, we present CourtSI, the first large-scale spatial intelligence dataset tailored to sports scenarios. CourtSI contains over 1M QA pairs, organized under a holistic taxonomy that systematically covers spatial counting, distance measurement, localization, and relational reasoning, across representative net sports including badminton, tennis, and table tennis. Leveraging well-defined court geometry as metric anchors, we develop a semi-automatic data engine to reconstruct sports scenes, enabling scalable curation of CourtSI. In addition, we introduce CourtSI-Bench, a high-quality evaluation benchmark comprising 3,686 QA pairs with rigorous human verification. We evaluate 25 proprietary and open-source VLMs on CourtSI-Bench, revealing a remaining human-AI performance gap and limited generalization from existing spatial intelligence benchmarks. These findings indicate that sports scenarios expose limitations in spatial intelligence capabilities captured by existing benchmarks. Further, fine-tuning Qwen3-VL-8B on CourtSI improves accuracy on CourtSI-Bench by 23.5 percentage points. The adapted model also generalizes effectively to CourtSI-Ext, an evaluation set built on a similar but unseen sport, and demonstrates enhanced spatial-aware commentary generation. Together, these findings demonstrate that CourtSI provides a scalable pathway toward advancing spatial intelligence of VLMs in sports.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.09896</guid>
|
|
<pubDate>Tue, 10 Mar 2026 16:50:32 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Thinking to Recall: How Reasoning Unlocks Parametric Knowledge in LLMs</title>
|
|
<link>https://arxiv.org/abs/2603.09906</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.09906.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zorik Gekhman, Roee Aharoni, Eran Ofek, Mor Geva, Roi Reichart, Jonathan Herzig</p><p><b>Upvotes:</b> 61</p><p><b>Summary:</b> While reasoning in LLMs plays a natural role in math, code generation, and multi-hop factual questions, its effect on simple, single-hop factual questions remains unclear. Such questions do not require step-by-step logical decomposition, making the utility of reasoning highly counterintuitive. Nevertheless, we find that enabling reasoning substantially expands the capability boundary of the model's parametric knowledge recall, unlocking correct answers that are otherwise effectively unreachable. Why does reasoning aid parametric knowledge recall when there are no complex reasoning steps to be done? To answer this, we design a series of hypothesis-driven controlled experiments, and identify two key driving mechanisms: (1) a computational buffer effect, where the model uses the generated reasoning tokens to perform latent computation independent of their semantic content; and (2) factual priming, where generating topically related facts acts as a semantic bridge that facilitates correct answer retrieval. Importantly, this latter generative self-retrieval mechanism carries inherent risks: we demonstrate that hallucinating intermediate facts during reasoning increases the likelihood of hallucinations in the final answer. Finally, we show that our insights can be harnessed to directly improve model accuracy by prioritizing reasoning trajectories that contain hallucination-free factual statements.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.09906</guid>
|
|
<pubDate>Tue, 10 Mar 2026 16:59:20 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Towards a Neural Debugger for Python</title>
|
|
<link>https://arxiv.org/abs/2603.09951</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.09951.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Maximilian Beck, Jonas Gehring, Jannik Kossen, Gabriel Synnaeve</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Training large language models (LLMs) on Python execution traces grounds them in code execution and enables the line-by-line execution prediction of whole Python programs, effectively turning them into neural interpreters (FAIR CodeGen Team et al., 2025). However, developers rarely execute programs step by step; instead, they use debuggers to stop execution at certain breakpoints and step through relevant portions only while inspecting or modifying program variables. Existing neural interpreter approaches lack such interactive control. To address this limitation, we introduce neural debuggers: language models that emulate traditional debuggers, supporting operations such as stepping into, over, or out of functions, as well as setting breakpoints at specific source lines. We show that neural debuggers -- obtained via fine-tuning large LLMs or pre-training smaller models from scratch -- can reliably model both forward execution (predicting future states and outputs) and inverse execution (inferring prior states or inputs) conditioned on debugger actions. Evaluated on CruxEval, our models achieve strong performance on both output and input prediction tasks, demonstrating robust conditional execution modeling. Our work takes first steps towards future agentic coding systems in which neural debuggers serve as a world model for simulated debugging environments, providing execution feedback or enabling agents to interact with real debugging tools. This capability lays the foundation for more powerful code generation, program understanding, and automated debugging.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.09951</guid>
|
|
<pubDate>Tue, 10 Mar 2026 17:47:05 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>CREATE: Testing LLMs for Associative Creativity</title>
|
|
<link>https://arxiv.org/abs/2603.09970</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.09970.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Manya Wadhwa, Tiasa Singha Roy, Harvey Lederman, Junyi Jessy Li, Greg Durrett</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> A key component of creativity is associative reasoning: the ability to draw novel yet meaningful connections between concepts. We introduce CREATE, a benchmark designed to evaluate models' capacity for creative associative reasoning. CREATE requires models to generate sets of paths connecting concepts in a model's parametric knowledge. Paths should have high specificity (distinctiveness and closeness of the concept connection) and high diversity (dissimilarity from other paths), and models are scored more highly if they produce a larger set of strong, diverse paths. This task shares demands of real creativity tasks like hypothesis generation, including an extremely large search space, but enables collection of a sizable benchmark with objective answer grading. Evaluation of frontier models shows that the strongest models achieve higher creative utility than others, with the high multiplicity of answers and complexity of the search making benchmark saturation difficult to achieve. Furthermore, our results illustrate that thinking models are not always more effective on our task, even with high token budgets. Recent approaches for creative prompting give some but limited additional improvement. CREATE provides a sandbox for developing new methods to improve models' capacity for associative creativity.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.09970</guid>
|
|
<pubDate>Tue, 10 Mar 2026 17:58:44 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Lost in Backpropagation: The LM Head is a Gradient Bottleneck</title>
|
|
<link>https://arxiv.org/abs/2603.10145</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.10145.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Nathan Godey, Yoav Artzi</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> The last layer of neural language models (LMs) projects output features of dimension D to logits in dimension V, the size of the vocabulary, where usually D ll V. This mismatch is known to raise risks of limited expressivity in neural LMs, creating a so-called softmax bottleneck. We show the softmax bottleneck is not only an expressivity bottleneck but also an optimization bottleneck. Backpropagating V-dimensional gradients through a rank-D linear layer induces unavoidable compression, which alters the training feedback provided to the vast majority of the parameters. We present a theoretical analysis of this phenomenon and measure empirically that 95-99% of the gradient norm is suppressed by the output layer, resulting in vastly suboptimal update directions. We conduct controlled pretraining experiments showing that the gradient bottleneck makes trivial patterns unlearnable, and drastically affects the training dynamics of LLMs. We argue that this inherent flaw contributes to training inefficiencies at scale independently of the model architecture, and raises the need for new LM head designs.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.10145</guid>
|
|
<pubDate>Tue, 10 Mar 2026 18:27:01 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>ReMix: Reinforcement routing for mixtures of LoRAs in LLM finetuning</title>
|
|
<link>https://arxiv.org/abs/2603.10160</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.10160.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ruizhong Qiu, Hanqing Zeng, Yinglong Xia, Yiwen Meng, Ren Chen, Jiarui Feng, Dongqi Fu, Qifan Wang, Jiayi Liu, Jun Xiao, Xiangjun Fan, Benyu Zhang, Hong Li, Zhining Liu, Hyunsik Yoo, Zhichen Zeng, Tianxin Wei, Hanghang Tong</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> Low-rank adapters (LoRAs) are a parameter-efficient finetuning technique that injects trainable low-rank matrices into pretrained models to adapt them to new tasks. Mixture-of-LoRAs models expand neural networks efficiently by routing each layer input to a small subset of specialized LoRAs of the layer. Existing Mixture-of-LoRAs routers assign a learned routing weight to each LoRA to enable end-to-end training of the router. Despite their empirical promise, we observe that the routing weights are typically extremely imbalanced across LoRAs in practice, where only one or two LoRAs often dominate the routing weights. This essentially limits the number of effective LoRAs and thus severely hinders the expressive power of existing Mixture-of-LoRAs models. In this work, we attribute this weakness to the nature of learnable routing weights and rethink the fundamental design of the router. To address this critical issue, we propose a new router designed that we call Reinforcement Routing for Mixture-of-LoRAs (ReMix). Our key idea is using non-learnable routing weights to ensure all active LoRAs to be equally effective, with no LoRA dominating the routing weights. However, our routers cannot be trained directly via gradient descent due to our non-learnable routing weights. Hence, we further propose an unbiased gradient estimator for the router by employing the reinforce leave-one-out (RLOO) technique, where we regard the supervision loss as the reward and the router as the policy in reinforcement learning. Our gradient estimator also enables to scale up training compute to boost the predictive performance of our ReMix. Extensive experiments demonstrate that our proposed ReMix significantly outperform state-of-the-art parameter-efficient finetuning methods under a comparable number of activated parameters.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.10160</guid>
|
|
<pubDate>Tue, 10 Mar 2026 18:51:27 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>OpenClaw-RL: Train Any Agent Simply by Talking</title>
|
|
<link>https://arxiv.org/abs/2603.10165</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.10165.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yinjie Wang, Xuyang Chen, Xiaolong Jin, Mengdi Wang, Ling Yang</p><p><b>Upvotes:</b> 94</p><p><b>Summary:</b> Every agent interaction generates a next-state signal, namely the user reply, tool output, terminal or GUI state change that follows each action, yet no existing agentic RL system recovers it as a live, online learning source. We present OpenClaw-RL, a framework built on a simple observation: next-state signals are universal, and policy can learn from all of them simultaneously. Personal conversations, terminal executions, GUI interactions, SWE tasks, and tool-call traces are not separate training problems. They are all interactions that can be used to train the same policy in the same loop. Next-state signals encode two forms of information: evaluative signals, which indicate how well the action performed and are extracted as scalar rewards via a PRM judge; and directive signals, which indicate how the action should have been different and are recovered through Hindsight-Guided On-Policy Distillation (OPD). We extract textual hints from the next state, construct an enhanced teacher context, and provide token-level directional advantage supervision that is richer than any scalar reward. Due to the asynchronous design, the model serves live requests, the PRM judges ongoing interactions, and the trainer updates the policy at the same time, with zero coordination overhead between them. Applied to personal agents, OpenClaw-RL enables an agent to improve simply by being used, recovering conversational signals from user re-queries, corrections, and explicit feedback. Applied to general agents, the same infrastructure supports scalable RL across terminal, GUI, SWE, and tool-call settings, where we additionally demonstrate the utility of process rewards. Code: https://github.com/Gen-Verse/OpenClaw-RL</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.10165</guid>
|
|
<pubDate>Tue, 10 Mar 2026 18:59:01 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Video-Based Reward Modeling for Computer-Use Agents</title>
|
|
<link>https://arxiv.org/abs/2603.10178</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.10178.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Linxin Song, Jieyu Zhang, Huanxin Sheng, Taiwei Shi, Gupta Rahul, Yang Liu, Ranjay Krishna, Jian Kang, Jieyu Zhao</p><p><b>Upvotes:</b> 35</p><p><b>Summary:</b> Computer-using agents (CUAs) are becoming increasingly capable; however, it remains difficult to scale evaluation of whether a trajectory truly fulfills a user instruction. In this work, we study reward modeling from execution video: a sequence of keyframes from an agent trajectory that is independent of the agent's internal reasoning or actions. Although video-execution modeling is method-agnostic, it presents key challenges, including highly redundant layouts and subtle, localized cues that determine success. We introduce Execution Video Reward 53k (ExeVR-53k), a dataset of 53k high-quality video--task--reward triplets. We further propose adversarial instruction translation to synthesize negative samples with step-level annotations. To enable learning from long, high-resolution execution videos, we design spatiotemporal token pruning, which removes homogeneous regions and persistent tokens while preserving decisive UI changes. Building on these components, we fine-tune an Execution Video Reward Model (ExeVRM) that takes only a user instruction and a video-execution sequence to predict task success. Our ExeVRM 8B achieves 84.7% accuracy and 87.7% recall on video-execution assessment, outperforming strong proprietary models such as GPT-5.2 and Gemini-3 Pro across Ubuntu, macOS, Windows, and Android, while providing more precise temporal attribution. These results show that video-execution reward modeling can serve as a scalable, model-agnostic evaluator for CUAs.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.10178</guid>
|
|
<pubDate>Tue, 10 Mar 2026 19:17:22 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>DIVE: Scaling Diversity in Agentic Task Synthesis for Generalizable Tool Use</title>
|
|
<link>https://arxiv.org/abs/2603.11076</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.11076.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Aili Chen, Chi Zhang, Junteng Liu, Jiangjie Chen, Chengyu Du, Yunji Li, Ming Zhong, Qin Wang, Zhengmao Zhu, Jiayuan Song, Ke Ji, Junxian He, Pengyu Zhao, Yanghua Xiao</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Recent work synthesizes agentic tasks for post-training tool-using LLMs, yet robust generalization under shifts in tasks and toolsets remains an open challenge. We trace this brittleness to insufficient diversity in synthesized tasks. Scaling diversity is difficult because training requires tasks to remain executable and verifiable, while generalization demands coverage of diverse tool types, toolset combinations, and heterogeneous tool-use patterns. We propose DIVE, an evidence-driven recipe that inverts synthesis order, executing diverse, real-world tools first and reverse-deriving tasks strictly entailed by the resulting traces, thereby providing grounding by construction. DIVE scales structural diversity along two controllable axes, tool-pool coverage and per-task toolset variety, and an Evidence Collection--Task Derivation loop further induces rich multi-step tool-use patterns across 373 tools in five domains. Training Qwen3-8B on DIVE data (48k SFT + 3.2k RL) improves by +22 average points across 9 OOD benchmarks and outperforms the strongest 8B baseline by +68. Remarkably, controlled scaling analysis reveals that diversity scaling consistently outperforms quantity scaling for OOD generalization, even with 4x less data.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.11076</guid>
|
|
<pubDate>Tue, 10 Mar 2026 20:54:23 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>ID-LoRA: Identity-Driven Audio-Video Personalization with In-Context LoRA</title>
|
|
<link>https://arxiv.org/abs/2603.10256</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.10256.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Aviad Dahan, Moran Yanuka, Noa Kraicer, Lior Wolf, Raja Giryes</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Existing video personalization methods preserve visual likeness but treat video and audio separately. Without access to the visual scene, audio models cannot synchronize sounds with on-screen actions; and because classical voice-cloning models condition only on a reference recording, a text prompt cannot redirect speaking style or acoustic environment. We propose ID-LoRA (Identity-Driven In-Context LoRA), which jointly generates a subject's appearance and voice in a single model, letting a text prompt, a reference image, and a short audio clip govern both modalities together. ID-LoRA adapts the LTX-2 joint audio-video diffusion backbone via parameter-efficient In-Context LoRA and, to our knowledge, is the first method to personalize visual appearance and voice in a single generative pass. Two challenges arise. Reference and generation tokens share the same positional-encoding space, making them hard to distinguish; we address this with negative temporal positions, placing reference tokens in a disjoint RoPE region while preserving their internal temporal structure. Speaker characteristics also tend to be diluted during denoising; we introduce identity guidance, a classifier-free guidance variant that amplifies speaker-specific features by contrasting predictions with and without the reference signal. In human preference studies, ID-LoRA is preferred over Kling 2.6 Pro by 73% of annotators for voice similarity and 65% for speaking style. On cross-environment settings, speaker similarity improves by 24% over Kling, with the gap widening as conditions diverge. A preliminary user study further suggests that joint generation provides a useful inductive bias for physically grounded sound synthesis. ID-LoRA achieves these results with only ~3K training pairs on a single GPU. Code, models, and data will be released.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.10256</guid>
|
|
<pubDate>Tue, 10 Mar 2026 22:23:36 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Geometric Autoencoder for Diffusion Models</title>
|
|
<link>https://arxiv.org/abs/2603.10365</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.10365.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hangyu Liu, Jianyong Wang, Yutao Sun</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Latent diffusion models have established a new state-of-the-art in high-resolution visual generation. Integrating Vision Foundation Model priors improves generative efficiency, yet existing latent designs remain largely heuristic. These approaches often struggle to unify semantic discriminability, reconstruction fidelity, and latent compactness. In this paper, we propose Geometric Autoencoder (GAE), a principled framework that systematically addresses these challenges. By analyzing various alignment paradigms, GAE constructs an optimized low-dimensional semantic supervision target from VFMs to provide guidance for the autoencoder. Furthermore, we leverage latent normalization that replaces the restrictive KL-divergence of standard VAEs, enabling a more stable latent manifold specifically optimized for diffusion learning. To ensure robust reconstruction under high-intensity noise, GAE incorporates a dynamic noise sampling mechanism. Empirically, GAE achieves compelling performance on the ImageNet-1K 256 times 256 benchmark, reaching a gFID of 1.82 at only 80 epochs and 1.31 at 800 epochs without Classifier-Free Guidance, significantly surpassing existing state-of-the-art methods. Beyond generative quality, GAE establishes a superior equilibrium between compression, semantic depth and robust reconstruction stability. These results validate our design considerations, offering a promising paradigm for latent diffusion modeling. Code and models are publicly available at https://github.com/freezing-index/Geometric-Autoencoder-for-Diffusion-Models.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.10365</guid>
|
|
<pubDate>Wed, 11 Mar 2026 03:29:16 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>FireRedASR2S: A State-of-the-Art Industrial-Grade All-in-One Automatic Speech Recognition System</title>
|
|
<link>https://arxiv.org/abs/2603.10420</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.10420.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kaituo Xu, Yan Jia, Kai Huang, Junjie Chen, Wenpeng Li, Kun Liu, Feng-Long Xie, Xu Tang, Yao Hu</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> We present FireRedASR2S, a state-of-the-art industrial-grade all-in-one automatic speech recognition (ASR) system. It integrates four modules in a unified pipeline: ASR, Voice Activity Detection (VAD), Spoken Language Identification (LID), and Punctuation Prediction (Punc). All modules achieve SOTA performance on the evaluated benchmarks: FireRedASR2: An ASR module with two variants, FireRedASR2-LLM (8B+ parameters) and FireRedASR2-AED (1B+ parameters), supporting speech and singing transcription for Mandarin, Chinese dialects and accents, English, and code-switching. Compared to FireRedASR, FireRedASR2 delivers improved recognition accuracy and broader dialect and accent coverage. FireRedASR2-LLM achieves 2.89% average CER on 4 public Mandarin benchmarks and 11.55% on 19 public Chinese dialects and accents benchmarks, outperforming competitive baselines including Doubao-ASR, Qwen3-ASR, and Fun-ASR. FireRedVAD: An ultra-lightweight module (0.6M parameters) based on the Deep Feedforward Sequential Memory Network (DFSMN), supporting streaming VAD, non-streaming VAD, and multi-label VAD (mVAD). On the FLEURS-VAD-102 benchmark, it achieves 97.57% frame-level F1 and 99.60% AUC-ROC, outperforming Silero-VAD, TEN-VAD, FunASR-VAD, and WebRTC-VAD. FireRedLID: An Encoder-Decoder LID module supporting 100+ languages and 20+ Chinese dialects and accents. On FLEURS (82 languages), it achieves 97.18% utterance-level accuracy, outperforming Whisper and SpeechBrain. FireRedPunc: A BERT-style punctuation prediction module for Chinese and English. On multi-domain benchmarks, it achieves 78.90% average F1, outperforming FunASR-Punc (62.77%). To advance research in speech processing, we release model weights and code at https://github.com/FireRedTeam/FireRedASR2S.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.10420</guid>
|
|
<pubDate>Wed, 11 Mar 2026 05:11:06 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>The Curse and Blessing of Mean Bias in FP4-Quantized LLM Training</title>
|
|
<link>https://arxiv.org/abs/2603.10444</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.10444.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hengjie Cao, Zhendong Huang, Mengyi Chen, Yifeng Yang, Fanqi Yu, Ruijun Huang, Fang Dong, Xin Zhang, Jixian Zhou, Anrui Chen, Mingzhi Dong, Yujiang Wang, Jinlong Hou, Qin Lv, Yuan Cheng, Tun Lu, Fan Yang, Li Shang</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Large language models trained on natural language exhibit pronounced anisotropy: a small number of directions concentrate disproportionate energy, while the remaining dimensions form a broad semantic tail. In low-bit training regimes, this geometry becomes numerically unstable. Because blockwise quantization scales are determined by extreme elementwise magnitudes, dominant directions stretch the dynamic range, compressing long-tail semantic variation into narrow numerical bins. We show that this instability is primarily driven by a coherent rank-one mean bias, which constitutes the dominant component of spectral anisotropy in LLM representations. This mean component emerges systematically across layers and training stages and accounts for the majority of extreme activation magnitudes, making it the principal driver of dynamic-range inflation under low precision. Crucially, because the dominant instability is rank-one, it can be eliminated through a simple source-level mean-subtraction operation. This bias-centric conditioning recovers most of the stability benefits of SVD-based spectral methods while requiring only reduction operations and standard quantization kernels. Empirical results on FP4 (W4A4G4) training show that mean removal substantially narrows the loss gap to BF16 and restores downstream performance, providing a hardware-efficient path to stable low-bit LLM training.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.10444</guid>
|
|
<pubDate>Wed, 11 Mar 2026 05:59:12 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Understanding by Reconstruction: Reversing the Software Development Process for LLM Pretraining</title>
|
|
<link>https://arxiv.org/abs/2603.11103</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.11103.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhiyuan Zeng, Yichi Zhang, Yong Shan, Kai Hua, Siyuan Fang, Zhaiyu Liu, Jiaheng Liu, Haozhe Wang, Yining Zheng, Ming Ding, Ke Shen, Ge Zhang, Wenhao Huang, Xipeng Qiu</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> While Large Language Models (LLMs) have achieved remarkable success in code generation, they often struggle with the deep, long-horizon reasoning required for complex software engineering. We attribute this limitation to the nature of standard pre-training data: static software repositories represent only the terminal state of an intricate intellectual process, abstracting away the intermediate planning, debugging, and iterative refinement. To bridge this gap, we propose a novel paradigm: understanding via reconstruction. We hypothesize that reverse-engineering the latent agentic trajectories -- the planning, reasoning, and debugging steps -- behind static repositories provides a far richer supervision signal than raw code alone. To operationalize this, we introduce a framework that synthesizes these trajectories using a multi-agent simulation. This process is grounded in the structural realities of the source repositories (e.g., dependency graphs and file hierarchies) to ensure fidelity. Furthermore, to guarantee the logical rigor of the synthetic data, we employ a search-based optimization technique that iteratively refines the Chain-of-Thought (CoT) reasoning to maximize the likelihood of the ground-truth code. Empirical results demonstrate that continuous pre-training on these reconstructed trajectories significantly enhances Llama-3-8B's performance across diverse benchmarks, including long-context understanding, coding proficiency, and agentic capabilities.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.11103</guid>
|
|
<pubDate>Wed, 11 Mar 2026 09:23:20 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Are Video Reasoning Models Ready to Go Outside?</title>
|
|
<link>https://arxiv.org/abs/2603.10652</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.10652.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yangfan He, Changgyu Boo, Jaehong Yoon</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> In real-world deployment, vision-language models often encounter disturbances such as weather, occlusion, and camera motion. Under such conditions, their understanding and reasoning degrade substantially, revealing a gap between clean, controlled (i.e., unperturbed) evaluation settings and real-world robustness. To address this limitation, we propose ROVA, a novel training framework that improves robustness by modeling a robustness-aware consistency reward under spatio-temporal corruptions. ROVA introduces a difficulty-aware online training strategy that prioritizes informative samples based on the model's evolving capability. Specifically, it continuously re-estimates sample difficulty via self-reflective evaluation, enabling adaptive training with a robustness-aware consistency reward. We also introduce PVRBench, a new benchmark that injects real-world perturbations into embodied video datasets to assess both accuracy and reasoning quality under realistic disturbances. We evaluate ROVA and baselines on PVRBench, UrbanVideo, and VisBench, where open-source and proprietary models suffer up to 35% and 28% drops in accuracy and reasoning under realistic perturbations. ROVA effectively mitigates performance degradation, boosting relative accuracy by at least 24% and reasoning by over 9% compared with baseline models (QWen2.5/3-VL, InternVL2.5, Embodied-R). These gains transfer to clean standard benchmarks, yielding consistent improvements.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.10652</guid>
|
|
<pubDate>Wed, 11 Mar 2026 11:10:52 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Prism-Δ: Differential Subspace Steering for Prompt Highlighting in Large Language Models</title>
|
|
<link>https://arxiv.org/abs/2603.10705</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.10705.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuyao Ge, Shenghua Liu, Yiwei Wang, Tianyu Liu, Baolong Bi, Lingrui Mei, Jiayu Yao, Jiafeng Guo, Xueqi Cheng</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Prompt highlighting steers a large language model to prioritize user-specified text spans during generation. A key challenge is extracting steering directions that capture the difference between relevant and irrelevant contexts, rather than shared structural patterns common to both. We propose PRISM-Δ (Projection-based Relevance-Informed Steering Method), which decomposes the difference between positive and negative cross-covariance matrices to maximize discriminative energy while eliminating shared directions. Each attention head receives a continuous softplus importance weight, letting weak-but-useful heads contribute at reduced strength. The framework extends naturally to Value representations, capturing content-channel signal that Key-only methods leave unused. Across four benchmarks and five models, PRISM-Δ matches or exceeds the best existing method on 19 of 20 configurations, with relative gains up to +10.6%, while halving the fluency cost of steering. PRISM-Δ also scales to long-context retrieval, outperforming the best existing method by up to +4.8% relative gain. PRISM-Δ is compatible with FlashAttention and adds negligible memory overhead.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.10705</guid>
|
|
<pubDate>Wed, 11 Mar 2026 12:24:45 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Just-in-Time: Training-Free Spatial Acceleration for Diffusion Transformers</title>
|
|
<link>https://arxiv.org/abs/2603.10744</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.10744.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wenhao Sun, Ji Li, Zhaoqiang Liu</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Diffusion Transformers have established a new state-of-the-art in image synthesis, but the high computational cost of iterative sampling severely hampers their practical deployment. While existing acceleration methods often focus on the temporal domain, they overlook the substantial spatial redundancy inherent in the generative process, where global structures emerge long before fine-grained details are formed. The uniform computational treatment of all spatial regions represents a critical inefficiency. In this paper, we introduce Just-in-Time (JiT), a novel training-free framework that addresses this challenge by acceleration in the spatial domain. JiT formulates a spatially approximated generative ordinary differential equation (ODE) that drives the full latent state evolution based on computations from a dynamically selected, sparse subset of anchor tokens. To ensure seamless transitions as new tokens are incorporated to expand the dimensions of the latent state, we propose a deterministic micro-flow, a simple and effective finite-time ODE that maintains both structural coherence and statistical correctness. Extensive experiments on the state-of-the-art FLUX.1-dev model demonstrate that JiT achieves up to a 7x speedup with nearly lossless performance, significantly outperforming existing acceleration methods and establishing a new and superior trade-off between inference speed and generation fidelity.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.10744</guid>
|
|
<pubDate>Wed, 11 Mar 2026 13:16:41 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>CodePercept: Code-Grounded Visual STEM Perception for MLLMs</title>
|
|
<link>https://arxiv.org/abs/2603.10757</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.10757.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tongkun Guan, Zhibo Yang, Jianqiang Wan, Mingkun Yang, Zhengtao Guo, Zijian Hu, Ruilin Luo, Ruize Chen, Songtao Jiang, Peng Wang, Wei Shen, Junyang Lin, Xiaokang Yang</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> When MLLMs fail at Science, Technology, Engineering, and Mathematics (STEM) visual reasoning, a fundamental question arises: is it due to perceptual deficiencies or reasoning limitations? Through systematic scaling analysis that independently scales perception and reasoning components, we uncover a critical insight: scaling perception consistently outperforms scaling reasoning. This reveals perception as the true lever limiting current STEM visual reasoning. Motivated by this insight, our work focuses on systematically enhancing the perception capabilities of MLLMs by establishing code as a powerful perceptual medium--executable code provides precise semantics that naturally align with the structured nature of STEM visuals. Specifically, we construct ICC-1M, a large-scale dataset comprising 1M Image-Caption-Code triplets that materializes this code-as-perception paradigm through two complementary approaches: (1) Code-Grounded Caption Generation treats executable code as ground truth for image captions, eliminating the hallucinations inherent in existing knowledge distillation methods; (2) STEM Image-to-Code Translation prompts models to generate reconstruction code, mitigating the ambiguity of natural language for perception enhancement. To validate this paradigm, we further introduce STEM2Code-Eval, a novel benchmark that directly evaluates visual perception in STEM domains. Unlike existing work relying on problem-solving accuracy as a proxy that only measures problem-relevant understanding, our benchmark requires comprehensive visual comprehension through executable code generation for image reconstruction, providing deterministic and verifiable assessment. Code is available at https://github.com/TongkunGuan/Qwen-CodePercept.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.10757</guid>
|
|
<pubDate>Wed, 11 Mar 2026 13:32:58 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>V_{0.5}: Generalist Value Model as a Prior for Sparse RL Rollouts</title>
|
|
<link>https://arxiv.org/abs/2603.10848</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.10848.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yi-Kai Zhang, Yueqing Sun, Hongyan Hao, Qi Gu, Xunliang Cai, De-Chuan Zhan, Han-Jia Ye</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> In Reinforcement Learning with Verifiable Rewards (RLVR), constructing a robust advantage baseline is critical for policy gradients, effectively guiding the policy model to reinforce desired behaviors. Recent research has introduced Generalist Value Models (such as V_0), which achieve pre-trained value estimation by explicitly encoding model capabilities in-context, eliminating the need to synchronously update the value model alongside the policy model. In this paper, we propose V_{0.5}, which adaptively fuses the baseline predicted by such value model (acting as a prior) with the empirical mean derived from sparse rollouts. This constructs a robust baseline that balances computational efficiency with extremely low variance. Specifically, we introduce a real-time statistical testing and dynamic budget allocation. This balances the high variance caused by sparse sampling against the systematic bias (or hallucinations) inherent in the value model's prior. By constructing a hypothesis test to evaluate the prior's reliability in real-time, the system dynamically allocates additional rollout budget on demand. This mechanism minimizes the baseline estimator's Mean Squared Error (MSE), guaranteeing stable policy gradients, even under extreme sparsity with a group size of 4. Extensive evaluations across six mathematical reasoning benchmarks demonstrate that V_{0.5} significantly outperforms GRPO and DAPO, achieving faster convergence and over some 10% performance improvement.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.10848</guid>
|
|
<pubDate>Wed, 11 Mar 2026 14:57:41 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>LLM2Vec-Gen: Generative Embeddings from Large Language Models</title>
|
|
<link>https://arxiv.org/abs/2603.10913</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.10913.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Parishad BehnamGhader, Vaibhav Adlakha, Fabian David Schmidt, Nicolas Chapados, Marius Mosbach, Siva Reddy</p><p><b>Upvotes:</b> 34</p><p><b>Summary:</b> LLM-based text embedders typically encode the semantic content of their input. However, embedding tasks require mapping diverse inputs to similar outputs. Typically, this input-output is addressed by training embedding models with paired data using contrastive learning. In this work, we propose a novel self-supervised approach, LLM2Vec-Gen, which adopts a different paradigm: rather than encoding the input, we learn to represent the model's potential response. Specifically, we add trainable special tokens to the LLM's vocabulary, append them to input, and optimize them to represent the LLM's response in a fixed-length sequence. Training is guided by the LLM's own completion for the query, along with an unsupervised embedding teacher that provides distillation targets. This formulation helps to bridge the input-output gap and transfers LLM capabilities such as safety alignment and reasoning to embedding tasks. Crucially, the LLM backbone remains frozen and training requires only unlabeled queries. LLM2Vec-Gen achieves state-of-the-art self-supervised performance on the Massive Text Embedding Benchmark (MTEB), improving by 9.3% over the best unsupervised embedding teacher. We also observe up to 43.2% reduction in harmful content retrieval and 29.3% improvement in reasoning capabilities for embedding tasks. Finally, the learned embeddings are interpretable and can be decoded into text to reveal their semantic content.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.10913</guid>
|
|
<pubDate>Wed, 11 Mar 2026 15:58:47 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Meta-Reinforcement Learning with Self-Reflection for Agentic Search</title>
|
|
<link>https://arxiv.org/abs/2603.11327</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.11327.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Teng Xiao, Yige Yuan, Hamish Ivison, Huaisheng Zhu, Faeze Brahman, Nathan Lambert, Pradeep Dasigi, Noah A. Smith, Hannaneh Hajishirzi</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> This paper introduces MR-Search, an in-context meta reinforcement learning (RL) formulation for agentic search with self-reflection. Instead of optimizing a policy within a single independent episode with sparse rewards, MR-Search trains a policy that conditions on past episodes and adapts its search strategy across episodes. MR-Search learns to learn a search strategy with self-reflection, allowing search agents to improve in-context exploration at test-time. Specifically, MR-Search performs cross-episode exploration by generating explicit self-reflections after each episode and leveraging them as additional context to guide subsequent attempts, thereby promoting more effective exploration during test-time. We further introduce a multi-turn RL algorithm that estimates a dense relative advantage at the turn level, enabling fine-grained credit assignment on each episode. Empirical results across various benchmarks demonstrate the advantages of MR-Search over baselines based RL, showing strong generalization and relative improvements of 9.2% to 19.3% across eight benchmarks. Our code and data are available at https://github.com/tengxiao1/MR-Search.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.11327</guid>
|
|
<pubDate>Wed, 11 Mar 2026 21:40:26 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>ShotVerse: Advancing Cinematic Camera Control for Text-Driven Multi-Shot Video Creation</title>
|
|
<link>https://arxiv.org/abs/2603.11421</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.11421.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Songlin Yang, Zhe Wang, Xuyi Yang, Songchun Zhang, Xianghao Kong, Taiyi Wu, Xiaotong Zhao, Ran Zhang, Alan Zhao, Anyi Rao</p><p><b>Upvotes:</b> 28</p><p><b>Summary:</b> Text-driven video generation has democratized film creation, but camera control in cinematic multi-shot scenarios remains a significant block. Implicit textual prompts lack precision, while explicit trajectory conditioning imposes prohibitive manual overhead and often triggers execution failures in current models. To overcome this bottleneck, we propose a data-centric paradigm shift, positing that aligned (Caption, Trajectory, Video) triplets form an inherent joint distribution that can connect automated plotting and precise execution. Guided by this insight, we present ShotVerse, a "Plan-then-Control" framework that decouples generation into two collaborative agents: a VLM (Vision-Language Model)-based Planner that leverages spatial priors to obtain cinematic, globally aligned trajectories from text, and a Controller that renders these trajectories into multi-shot video content via a camera adapter. Central to our approach is the construction of a data foundation: we design an automated multi-shot camera calibration pipeline aligns disjoint single-shot trajectories into a unified global coordinate system. This facilitates the curation of ShotVerse-Bench, a high-fidelity cinematic dataset with a three-track evaluation protocol that serves as the bedrock for our framework. Extensive experiments demonstrate that ShotVerse effectively bridges the gap between unreliable textual control and labor-intensive manual plotting, achieving superior cinematic aesthetics and generating multi-shot videos that are both camera-accurate and cross-shot consistent.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.11421</guid>
|
|
<pubDate>Thu, 12 Mar 2026 01:27:08 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Tiny Aya: Bridging Scale and Multilingual Depth</title>
|
|
<link>https://arxiv.org/abs/2603.11510</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.11510.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Alejandro R. Salamanca, Diana Abagyan, Daniel D'souza, Ammar Khairi, David Mora, Saurabh Dash, Viraat Aryabumi, Sara Rajaee, Mehrnaz Mofakhami, Ananya Sahu, Thomas Euyang, Brittawnya Prince, Madeline Smith, Hangyu Lin, Acyr Locatelli, Sara Hooker, Tom Kocmi, Aidan Gomez, Ivan Zhang, Phil Blunsom, Nick Frosst, Joelle Pineau, Beyza Ermis, Ahmet Üstün, Julia Kreutzer, Marzieh Fadaee</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Tiny Aya redefines what a small multilingual language model can achieve. Trained on 70 languages and refined through region-aware posttraining, it delivers state-of-the-art in translation quality, strong multilingual understanding, and high-quality target-language generation, all with just 3.35B parameters. The release includes a pretrained foundation model, a globally balanced instruction-tuned variant, and three region-specialized models targeting languages from Africa, South Asia, Europe, Asia-Pacific, and West Asia. This report details the training strategy, data composition, and comprehensive evaluation framework behind Tiny Aya, and presents an alternative scaling path for multilingual AI: one centered on efficiency, balanced performance across languages, and practical deployment.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.11510</guid>
|
|
<pubDate>Thu, 12 Mar 2026 03:53:13 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Mobile-GS: Real-time Gaussian Splatting for Mobile Devices</title>
|
|
<link>https://arxiv.org/abs/2603.11531</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.11531.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiaobiao Du, Yida Wang, Kun Zhan, Xin Yu</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> 3D Gaussian Splatting (3DGS) has emerged as a powerful representation for high-quality rendering across a wide range of applications.However, its high computational demands and large storage costs pose significant challenges for deployment on mobile devices. In this work, we propose a mobile-tailored real-time Gaussian Splatting method, dubbed Mobile-GS, enabling efficient inference of Gaussian Splatting on edge devices. Specifically, we first identify alpha blending as the primary computational bottleneck, since it relies on the time-consuming Gaussian depth sorting process. To solve this issue, we propose a depth-aware order-independent rendering scheme that eliminates the need for sorting, thereby substantially accelerating rendering. Although this order-independent rendering improves rendering speed, it may introduce transparency artifacts in regions with overlapping geometry due to the scarcity of rendering order. To address this problem, we propose a neural view-dependent enhancement strategy, enabling more accurate modeling of view-dependent effects conditioned on viewing direction, 3D Gaussian geometry, and appearance attributes. In this way, Mobile-GS can achieve both high-quality and real-time rendering. Furthermore, to facilitate deployment on memory-constrained mobile platforms, we also introduce first-order spherical harmonics distillation, a neural vector quantization technique, and a contribution-based pruning strategy to reduce the number of Gaussian primitives and compress the 3D Gaussian representation with the assistance of neural networks. Extensive experiments demonstrate that our proposed Mobile-GS achieves real-time rendering and compact model size while preserving high visual quality, making it well-suited for mobile applications.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.11531</guid>
|
|
<pubDate>Thu, 12 Mar 2026 04:33:04 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>WeEdit: A Dataset, Benchmark and Glyph-Guided Framework for Text-centric Image Editing</title>
|
|
<link>https://arxiv.org/abs/2603.11593</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.11593.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hui Zhang, Juntao Liu, Zongkai Liu, Liqiang Niu, Fandong Meng, Zuxuan Wu, Yu-Gang Jiang</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Instruction-based image editing aims to modify specific content within existing images according to user-provided instructions while preserving non-target regions. Beyond traditional object- and style-centric manipulation, text-centric image editing focuses on modifying, translating, or rearranging textual elements embedded within images. However, existing leading models often struggle to execute complex text editing precisely, frequently producing blurry or hallucinated characters. We attribute these failures primarily to the lack of specialized training paradigms tailored for text-centric editing, as well as the absence of large-scale datasets and standardized benchmarks necessary for a closed-loop training and evaluation system. To address these limitations, we present WeEdit, a systematic solution encompassing a scalable data construction pipeline, two benchmarks, and a tailored two-stage training strategy. Specifically, we propose a novel HTML-based automatic editing pipeline, which generates 330K training pairs covering diverse editing operations and 15 languages, accompanied by standardized bilingual and multilingual benchmarks for comprehensive evaluation. On the algorithmic side, we employ glyph-guided supervised fine-tuning to inject explicit spatial and content priors, followed by a multi-objective reinforcement learning stage to align generation with instruction adherence, text clarity, and background preservation. Extensive experiments demonstrate that WeEdit outperforms previous open-source models by a clear margin across diverse editing operations.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.11593</guid>
|
|
<pubDate>Thu, 12 Mar 2026 06:25:09 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>XSkill: Continual Learning from Experience and Skills in Multimodal Agents</title>
|
|
<link>https://arxiv.org/abs/2603.12056</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.12056.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Guanyu Jiang, Zhaochen Su, Xiaoye Qu, Yi R., Fung</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> Multimodal agents can now tackle complex reasoning tasks with diverse tools, yet they still suffer from inefficient tool use and inflexible orchestration in open-ended settings. A central challenge is enabling such agents to continually improve without parameter updates by learning from past trajectories. We identify two complementary forms of reusable knowledge essential for this goal: experiences, providing concise action-level guidance for tool selection and decision making, and skills, providing structured task-level guidance for planning and tool use. To this end, we propose XSkill, a dual-stream framework for continual learning from experience and skills in multimodal agents. XSkill grounds both knowledge extraction and retrieval in visual observations. During accumulation, XSkill distills and consolidates experiences and skills from multi-path rollouts via visually grounded summarization and cross-rollout critique. During inference, it retrieves and adapts this knowledge to the current visual context and feeds usage history back into accumulation to form a continual learning loop. Evaluated on five benchmarks across diverse domains with four backbone models, XSkill consistently and substantially outperforms both tool-only and learning-based baselines. Further analysis reveals that the two knowledge streams play complementary roles in influencing the reasoning behaviors of agents and show superior zero-shot generalization.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.12056</guid>
|
|
<pubDate>Thu, 12 Mar 2026 15:25:57 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Coarse-Guided Visual Generation via Weighted h-Transform Sampling</title>
|
|
<link>https://arxiv.org/abs/2603.12057</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.12057.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yanghao Wang, Ziqi Jiang, Zhen Wang, Long Chen</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Coarse-guided visual generation, which synthesizes fine visual samples from degraded or low-fidelity coarse references, is essential for various real-world applications. While training-based approaches are effective, they are inherently limited by high training costs and restricted generalization due to paired data collection. Accordingly, recent training-free works propose to leverage pretrained diffusion models and incorporate guidance during the sampling process. However, these training-free methods either require knowing the forward (fine-to-coarse) transformation operator, e.g., bicubic downsampling, or are difficult to balance between guidance and synthetic quality. To address these challenges, we propose a novel guided method by using the h-transform, a tool that can constrain stochastic processes (e.g., sampling process) under desired conditions. Specifically, we modify the transition probability at each sampling timestep by adding to the original differential equation with a drift function, which approximately steers the generation toward the ideal fine sample. To address unavoidable approximation errors, we introduce a noise-level-aware schedule that gradually de-weights the term as the error increases, ensuring both guidance adherence and high-quality synthesis. Extensive experiments across diverse image and video generation tasks demonstrate the effectiveness and generalization of our method.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.12057</guid>
|
|
<pubDate>Thu, 12 Mar 2026 15:26:19 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Automatic Generation of High-Performance RL Environments</title>
|
|
<link>https://arxiv.org/abs/2603.12145</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.12145.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Seth Karten, Rahul Dev Appapogu, Chi Jin</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Translating complex reinforcement learning (RL) environments into high-performance implementations has traditionally required months of specialized engineering. We present a reusable recipe - a generic prompt template, hierarchical verification, and iterative agent-assisted repair - that produces semantically equivalent high-performance environments for <$10 in compute cost. We demonstrate three distinct workflows across five environments. Direct translation (no prior performance implementation exists): EmuRust (1.5x PPO speedup via Rust parallelism for a Game Boy emulator) and PokeJAX, the first GPU-parallel Pokemon battle simulator (500M SPS random action, 15.2M SPS PPO; 22,320x over the TypeScript reference). Translation verified against existing performance implementations: throughput parity with MJX (1.04x) and 5x over Brax at matched GPU batch sizes (HalfCheetah JAX); 42x PPO (Puffer Pong). New environment creation: TCGJax, the first deployable JAX Pokemon TCG engine (717K SPS random action, 153K SPS PPO; 6.6x over the Python reference), synthesized from a web-extracted specification. At 200M parameters, the environment overhead drops below 4% of training time. Hierarchical verification (property, interaction, and rollout tests) confirms semantic equivalence for all five environments; cross-backend policy transfer confirms zero sim-to-sim gap for all five environments. TCGJax, synthesized from a private reference absent from public repositories, serves as a contamination control for agent pretraining data concerns. The paper contains sufficient detail - including representative prompts, verification methodology, and complete results - that a coding agent could reproduce the translations directly from the manuscript.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.12145</guid>
|
|
<pubDate>Thu, 12 Mar 2026 16:45:47 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document Collections</title>
|
|
<link>https://arxiv.org/abs/2603.12180</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.12180.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Łukasz Borchmann, Jordy Van Landeghem, Michał Turski, Shreyansh Padarha, Ryan Othniel Kearns, Adam Mahdi, Niels Rogge, Clémentine Fourrier, Siwei Han, Huaxiu Yao, Artemis Llabrés, Yiming Xu, Dimosthenis Karatzas, Hao Zhang, Anupam Datta</p><p><b>Upvotes:</b> 51</p><p><b>Summary:</b> Multimodal agents offer a promising path to automating complex document-intensive workflows. Yet, a critical question remains: do these agents demonstrate genuine strategic reasoning, or merely stochastic trial-and-error search? To address this, we introduce MADQA, a benchmark of 2,250 human-authored questions grounded in 800 heterogeneous PDF documents. Guided by Classical Test Theory, we design it to maximize discriminative power across varying levels of agentic abilities. To evaluate agentic behaviour, we introduce a novel evaluation protocol measuring the accuracy-effort trade-off. Using this framework, we show that while the best agents can match human searchers in raw accuracy, they succeed on largely different questions and rely on brute-force search to compensate for weak strategic planning. They fail to close the nearly 20% gap to oracle performance, persisting in unproductive loops. We release the dataset and evaluation harness to help facilitate the transition from brute-force retrieval to calibrated, efficient reasoning.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.12180</guid>
|
|
<pubDate>Thu, 12 Mar 2026 17:11:22 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse</title>
|
|
<link>https://arxiv.org/abs/2603.12201</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.12201.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yushi Bai, Qian Dong, Ting Jiang, Xin Lv, Zhengxiao Du, Aohan Zeng, Jie Tang, Juanzi Li</p><p><b>Upvotes:</b> 39</p><p><b>Summary:</b> Long-context agentic workflows have emerged as a defining use case for large language models, making attention efficiency critical for both inference speed and serving cost. Sparse attention addresses this challenge effectively, and DeepSeek Sparse Attention (DSA) is a representative production-grade solution: a lightweight lightning indexer selects the top-k most relevant tokens per query, reducing core attention from O(L^2) to O(Lk). However, the indexer itself retains O(L^2) complexity and must run independently at every layer, despite the fact that the resulting top-k selections are highly similar across consecutive layers. We present IndexCache, which exploits this cross-layer redundancy by partitioning layers into a small set of Full layers that run their own indexers and a majority of Shared layers that simply reuse the nearest Full layer's top-k indices. We propose two complementary approaches to determine and optimize this configuration. Training-free IndexCache applies a greedy search algorithm that selects which layers to retain indexers by directly minimizing language modeling loss on a calibration set, requiring no weight updates. Training-aware IndexCache introduces a multi-layer distillation loss that trains each retained indexer against the averaged attention distributions of all layers it serves, enabling even simple interleaved patterns to match full-indexer accuracy. Experimental results on a 30B DSA model show that IndexCache can remove 75% of indexer computations with negligible quality degradation, achieving up to 1.82times prefill speedup and 1.48times decode speedup compared to standard DSA. These positive results are further confirmed by our preliminary experiments on the production-scale GLM-5 model (Figure 1).</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.12201</guid>
|
|
<pubDate>Thu, 12 Mar 2026 17:27:21 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weights</title>
|
|
<link>https://arxiv.org/abs/2603.12228</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.12228.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yulu Gan, Phillip Isola</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Pretraining produces a learned parameter vector that is typically treated as a starting point for further iterative adaptation. In this work, we instead view the outcome of pretraining as a distribution over parameter vectors, whose support already contains task-specific experts. We show that in small models such expert solutions occupy a negligible fraction of the volume of this distribution, making their discovery reliant on structured optimization methods such as gradient descent. In contrast, in large, well-pretrained models the density of task-experts increases dramatically, so that diverse, task-improving specialists populate a substantial fraction of the neighborhood around the pretrained weights. Motivated by this perspective, we explore a simple, fully parallel post-training method that samples N parameter perturbations at random, selects the top K, and ensembles predictions via majority vote. Despite its simplicity, this approach is competitive with standard post-training methods such as PPO, GRPO, and ES for contemporary large-scale models.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.12228</guid>
|
|
<pubDate>Thu, 12 Mar 2026 17:49:30 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>One Model, Many Budgets: Elastic Latent Interfaces for Diffusion Transformers</title>
|
|
<link>https://arxiv.org/abs/2603.12245</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.12245.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Moayed Haji-Ali, Willi Menapace, Ivan Skorokhodov, Dogyun Park, Anil Kag, Michael Vasilkovsky, Sergey Tulyakov, Vicente Ordonez, Aliaksandr Siarohin</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Diffusion transformers (DiTs) achieve high generative quality but lock FLOPs to image resolution, limiting principled latency-quality trade-offs, and allocate computation uniformly across input spatial tokens, wasting resource allocation to unimportant regions. We introduce Elastic Latent Interface Transformer (ELIT), a drop-in, DiT-compatible mechanism that decouples input image size from compute. Our approach inserts a latent interface, a learnable variable-length token sequence on which standard transformer blocks can operate. Lightweight Read and Write cross-attention layers move information between spatial tokens and latents and prioritize important input regions. By training with random dropping of tail latents, ELIT learns to produce importance-ordered representations with earlier latents capturing global structure while later ones contain information to refine details. At inference, the number of latents can be dynamically adjusted to match compute constraints. ELIT is deliberately minimal, adding two cross-attention layers while leaving the rectified flow objective and the DiT stack unchanged. Across datasets and architectures (DiT, U-ViT, HDiT, MM-DiT), ELIT delivers consistent gains. On ImageNet-1K 512px, ELIT delivers an average gain of 35.3% and 39.6% in FID and FDD scores. Project page: https://snap-research.github.io/elit/</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.12245</guid>
|
|
<pubDate>Thu, 12 Mar 2026 17:57:04 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Examining Reasoning LLMs-as-Judges in Non-Verifiable LLM Post-Training</title>
|
|
<link>https://arxiv.org/abs/2603.12246</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.12246.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yixin Liu, Yue Yu, DiJia Su, Sid Wang, Xuewei Wang, Song Jiang, Bo Liu, Arman Cohan, Yuandong Tian, Zhengxing Chen</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Reasoning LLMs-as-Judges, which can benefit from inference-time scaling, provide a promising path for extending the success of reasoning models to non-verifiable domains where the output correctness/quality cannot be directly checked. However, while reasoning judges have shown better performance on static evaluation benchmarks, their effectiveness in actual policy training has not been systematically examined. Therefore, we conduct a rigorous study to investigate the actual impact of non-reasoning and reasoning judges in reinforcement-learning-based LLM alignment. Our controlled synthetic setting, where a "gold-standard" judge (gpt-oss-120b) provides preference annotations to train smaller judges, reveals key differences between non-reasoning and reasoning judges: non-reasoning judges lead to reward hacking easily, while reasoning judges can lead to policies that achieve strong performance when evaluated by the gold-standard judge. Interestingly, we find that the reasoning-judge-trained policies achieve such strong performance by learning to generate highly effective adversarial outputs that can also score well on popular benchmarks such as Arena-Hard by deceiving other LLM-judges. Combined with our further analysis, our study highlights both important findings and room for improvements for applying (reasoning) LLM-judges in non-verifiable LLM post-training.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.12246</guid>
|
|
<pubDate>Thu, 12 Mar 2026 17:57:06 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Trust Your Critic: Robust Reward Modeling and Reinforcement Learning for Faithful Image Editing and Generation</title>
|
|
<link>https://arxiv.org/abs/2603.12247</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.12247.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiangyu Zhao, Peiyuan Zhang, Junming Lin, Tianhao Liang, Yuchen Duan, Shengyuan Ding, Changyao Tian, Yuhang Zang, Junchi Yan, Xue Yang</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> Reinforcement learning (RL) has emerged as a promising paradigm for enhancing image editing and text-to-image (T2I) generation. However, current reward models, which act as critics during RL, often suffer from hallucinations and assign noisy scores, inherently misguiding the optimization process. In this paper, we present FIRM (Faithful Image Reward Modeling), a comprehensive framework that develops robust reward models to provide accurate and reliable guidance for faithful image generation and editing. First, we design tailored data curation pipelines to construct high-quality scoring datasets. Specifically, we evaluate editing using both execution and consistency, while generation is primarily assessed via instruction following. Using these pipelines, we collect the FIRM-Edit-370K and FIRM-Gen-293K datasets, and train specialized reward models (FIRM-Edit-8B and FIRM-Gen-8B) that accurately reflect these criteria. Second, we introduce FIRM-Bench, a comprehensive benchmark specifically designed for editing and generation critics. Evaluations demonstrate that our models achieve superior alignment with human judgment compared to existing metrics. Furthermore, to seamlessly integrate these critics into the RL pipeline, we formulate a novel "Base-and-Bonus" reward strategy that balances competing objectives: Consistency-Modulated Execution (CME) for editing and Quality-Modulated Alignment (QMA) for generation. Empowered by this framework, our resulting models FIRM-Qwen-Edit and FIRM-SD3.5 achieve substantial performance breakthroughs. Comprehensive experiments demonstrate that FIRM mitigates hallucinations, establishing a new standard for fidelity and instruction adherence over existing general models. All of our datasets, models, and code have been publicly available at https://firm-reward.github.io.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.12247</guid>
|
|
<pubDate>Thu, 12 Mar 2026 17:57:21 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>DVD: Deterministic Video Depth Estimation with Generative Priors</title>
|
|
<link>https://arxiv.org/abs/2603.12250</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.12250.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hongfei Zhang, Harold Haodong Chen, Chenfei Liao, Jing He, Zixin Zhang, Haodong Li, Yihao Liang, Kanghao Chen, Bin Ren, Xu Zheng, Shuai Yang, Kun Zhou, Yinchuan Li, Nicu Sebe, Ying-Cong Chen</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> Existing video depth estimation faces a fundamental trade-off: generative models suffer from stochastic geometric hallucinations and scale drift, while discriminative models demand massive labeled datasets to resolve semantic ambiguities. To break this impasse, we present DVD, the first framework to deterministically adapt pre-trained video diffusion models into single-pass depth regressors. Specifically, DVD features three core designs: (i) repurposing the diffusion timestep as a structural anchor to balance global stability with high-frequency details; (ii) latent manifold rectification (LMR) to mitigate regression-induced over-smoothing, enforcing differential constraints to restore sharp boundaries and coherent motion; and (iii) global affine coherence, an inherent property bounding inter-window divergence, which enables seamless long-video inference without requiring complex temporal alignment. Extensive experiments demonstrate that DVD achieves state-of-the-art zero-shot performance across benchmarks. Furthermore, DVD successfully unlocks the profound geometric priors implicit in video foundation models using 163x less task-specific data than leading baselines. Notably, we fully release our pipeline, providing the whole training suite for SOTA video depth estimation to benefit the open-source community.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.12250</guid>
|
|
<pubDate>Thu, 12 Mar 2026 17:58:06 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>EndoCoT: Scaling Endogenous Chain-of-Thought Reasoning in Diffusion Models</title>
|
|
<link>https://arxiv.org/abs/2603.12252</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.12252.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xuanlang Dai, Yujie Zhou, Long Xing, Jiazi Bu, Xilin Wei, Yuhong Liu, Beichen Zhang, Kai Chen, Yuhang Zang</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Recently, Multimodal Large Language Models (MLLMs) have been widely integrated into diffusion frameworks primarily as text encoders to tackle complex tasks such as spatial reasoning. However, this paradigm suffers from two critical limitations: (i) MLLMs text encoder exhibits insufficient reasoning depth. Single-step encoding fails to activate the Chain-of-Thought process, which is essential for MLLMs to provide accurate guidance for complex tasks. (ii) The guidance remains invariant during the decoding process. Invariant guidance during decoding prevents DiT from progressively decomposing complex instructions into actionable denoising steps, even with correct MLLM encodings. To this end, we propose Endogenous Chain-of-Thought (EndoCoT), a novel framework that first activates MLLMs' reasoning potential by iteratively refining latent thought states through an iterative thought guidance module, and then bridges these states to the DiT's denoising process. Second, a terminal thought grounding module is applied to ensure the reasoning trajectory remains grounded in textual supervision by aligning the final state with ground-truth answers. With these two components, the MLLM text encoder delivers meticulously reasoned guidance, enabling the DiT to execute it progressively and ultimately solve complex tasks in a step-by-step manner. Extensive evaluations across diverse benchmarks (e.g., Maze, TSP, VSP, and Sudoku) achieve an average accuracy of 92.1%, outperforming the strongest baseline by 8.3 percentage points.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.12252</guid>
|
|
<pubDate>Thu, 12 Mar 2026 17:58:48 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training</title>
|
|
<link>https://arxiv.org/abs/2603.12255</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.12255.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fangfu Liu, Diankun Wu, Jiawei Chi, Yimo Cai, Yi-Hsin Hung, Xumin Yu, Hao Li, Han Hu, Yongming Rao, Yueqi Duan</p><p><b>Upvotes:</b> 73</p><p><b>Summary:</b> Humans perceive and understand real-world spaces through a stream of visual observations. Therefore, the ability to streamingly maintain and update spatial evidence from potentially unbounded video streams is essential for spatial intelligence. The core challenge is not simply longer context windows but how spatial information is selected, organized, and retained over time. In this paper, we propose Spatial-TTT towards streaming visual-based spatial intelligence with test-time training (TTT), which adapts a subset of parameters (fast weights) to capture and organize spatial evidence over long-horizon scene videos. Specifically, we design a hybrid architecture and adopt large-chunk updates parallel with sliding-window attention for efficient spatial video processing. To further promote spatial awareness, we introduce a spatial-predictive mechanism applied to TTT layers with 3D spatiotemporal convolution, which encourages the model to capture geometric correspondence and temporal continuity across frames. Beyond architecture design, we construct a dataset with dense 3D spatial descriptions, which guides the model to update its fast weights to memorize and organize global 3D spatial signals in a structured manner. Extensive experiments demonstrate that Spatial-TTT improves long-horizon spatial understanding and achieves state-of-the-art performance on video spatial benchmarks. Project page: https://liuff19.github.io/Spatial-TTT.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.12255</guid>
|
|
<pubDate>Thu, 12 Mar 2026 17:58:58 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>DreamVideo-Omni: Omni-Motion Controlled Multi-Subject Video Customization with Latent Identity Reinforcement Learning</title>
|
|
<link>https://arxiv.org/abs/2603.12257</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.12257.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yujie Wei, Xinyu Liu, Shiwei Zhang, Hangjie Yuan, Jinbo Xing, Zhekai Chen, Xiang Wang, Haonan Qiu, Rui Zhao, Yutong Feng, Ruihang Chu, Yingya Zhang, Yike Guo, Xihui Liu, Hongming Shan</p><p><b>Upvotes:</b> 26</p><p><b>Summary:</b> While large-scale diffusion models have revolutionized video synthesis, achieving precise control over both multi-subject identity and multi-granularity motion remains a significant challenge. Recent attempts to bridge this gap often suffer from limited motion granularity, control ambiguity, and identity degradation, leading to suboptimal performance on identity preservation and motion control. In this work, we present DreamVideo-Omni, a unified framework enabling harmonious multi-subject customization with omni-motion control via a progressive two-stage training paradigm. In the first stage, we integrate comprehensive control signals for joint training, encompassing subject appearances, global motion, local dynamics, and camera movements. To ensure robust and precise controllability, we introduce a condition-aware 3D rotary positional embedding to coordinate heterogeneous inputs and a hierarchical motion injection strategy to enhance global motion guidance. Furthermore, to resolve multi-subject ambiguity, we introduce group and role embeddings to explicitly anchor motion signals to specific identities, effectively disentangling complex scenes into independent controllable instances. In the second stage, to mitigate identity degradation, we design a latent identity reward feedback learning paradigm by training a latent identity reward model upon a pretrained video diffusion backbone. This provides motion-aware identity rewards in the latent space, prioritizing identity preservation aligned with human preferences. Supported by our curated large-scale dataset and the comprehensive DreamOmni Bench for multi-subject and omni-motion control evaluation, DreamVideo-Omni demonstrates superior performance in generating high-quality videos with precise controllability.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.12257</guid>
|
|
<pubDate>Thu, 12 Mar 2026 17:59:12 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>GRADE: Benchmarking Discipline-Informed Reasoning in Image Editing</title>
|
|
<link>https://arxiv.org/abs/2603.12264</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.12264.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mingxin Liu, Ziqian Fan, Zhaokai Wang, Leyao Gu, Zirun Zhu, Yiguo He, Yuchen Yang, Changyao Tian, Xiangyu Zhao, Ning Liao, Shaofeng Zhang, Qibing Ren, Zhihang Zhong, Xuanhe Zhou, Junchi Yan, Xue Yang</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Unified multimodal models target joint understanding, reasoning, and generation, but current image editing benchmarks are largely confined to natural images and shallow commonsense reasoning, offering limited assessment of this capability under structured, domain-specific constraints. In this work, we introduce GRADE, the first benchmark to assess discipline-informed knowledge and reasoning in image editing. GRADE comprises 520 carefully curated samples across 10 academic domains, spanning from natural science to social science. To support rigorous evaluation, we propose a multi-dimensional evaluation protocol that jointly assesses Discipline Reasoning, Visual Consistency, and Logical Readability. Extensive experiments on 20 state-of-the-art open-source and closed-source models reveal substantial limitations in current models under implicit, knowledge-intensive editing settings, leading to large performance gaps. Beyond quantitative scores, we conduct rigorous analyses and ablations to expose model shortcomings and identify the constraints within disciplinary editing. Together, GRADE pinpoints key directions for the future development of unified multimodal models, advancing the research on discipline-informed image editing and reasoning. Our benchmark and evaluation code are publicly released.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.12264</guid>
|
|
<pubDate>Thu, 12 Mar 2026 17:59:52 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>OmniStream: Mastering Perception, Reconstruction and Action in Continuous Streams</title>
|
|
<link>https://arxiv.org/abs/2603.12265</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.12265.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yibin Yan, Jilan Xu, Shangzhe Di, Haoning Wu, Weidi Xie</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Modern visual agents require representations that are general, causal, and physically structured to operate in real-time streaming environments. However, current vision foundation models remain fragmented, specializing narrowly in image semantic perception, offline temporal modeling, or spatial geometry. This paper introduces OmniStream, a unified streaming visual backbone that effectively perceives, reconstructs, and acts from diverse visual inputs. By incorporating causal spatiotemporal attention and 3D rotary positional embeddings (3D-RoPE), our model supports efficient, frame-by-frame online processing of video streams via a persistent KV-cache. We pre-train OmniStream using a synergistic multi-task framework coupling static and temporal representation learning, streaming geometric reconstruction, and vision-language alignment on 29 datasets. Extensive evaluations show that, even with a strictly frozen backbone, OmniStream achieves consistently competitive performance with specialized experts across image and video probing, streaming geometric reconstruction, complex video and spatial reasoning, as well as robotic manipulation (unseen at training). Rather than pursuing benchmark-specific dominance, our work demonstrates the viability of training a single, versatile vision backbone that generalizes across semantic, spatial, and temporal reasoning, i.e., a more meaningful step toward general-purpose visual understanding for interactive and embodied agents.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.12265</guid>
|
|
<pubDate>Thu, 12 Mar 2026 17:59:55 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>EVATok: Adaptive Length Video Tokenization for Efficient Visual Autoregressive Generation</title>
|
|
<link>https://arxiv.org/abs/2603.12267</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.12267.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tianwei Xiong, Jun Hao Liew, Zilong Huang, Zhijie Lin, Jiashi Feng, Xihui Liu</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Autoregressive (AR) video generative models rely on video tokenizers that compress pixels into discrete token sequences. The length of these token sequences is crucial for balancing reconstruction quality against downstream generation computational cost. Traditional video tokenizers apply a uniform token assignment across temporal blocks of different videos, often wasting tokens on simple, static, or repetitive segments while underserving dynamic or complex ones. To address this inefficiency, we introduce EVATok, a framework to produce Efficient Video Adaptive Tokenizers. Our framework estimates optimal token assignments for each video to achieve the best quality-cost trade-off, develops lightweight routers for fast prediction of these optimal assignments, and trains adaptive tokenizers that encode videos based on the assignments predicted by routers. We demonstrate that EVATok delivers substantial improvements in efficiency and overall quality for video reconstruction and downstream AR generation. Enhanced by our advanced training recipe that integrates video semantic encoders, EVATok achieves superior reconstruction and state-of-the-art class-to-video generation on UCF-101, with at least 24.4% savings in average token usage compared to the prior state-of-the-art LARP and our fixed-length baseline.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.12267</guid>
|
|
<pubDate>Thu, 12 Mar 2026 17:59:59 +0000</pubDate>
|
|
</item>
|
|
</channel>
|
|
</rss>
|