bot: update RSS feed
This commit is contained in:
github-actions[bot]
299
feed.xml
299
feed.xml
@@ -7,216 +7,209 @@
|
||||
<docs>http://www.rssboard.org/rss-specification</docs>
|
||||
<generator>python-feedgen</generator>
|
||||
<language>en</language>
|
||||
<lastBuildDate>Thu, 12 Mar 2026 00:04:04 +0000</lastBuildDate>
|
||||
<lastBuildDate>Fri, 13 Mar 2026 00:04:06 +0000</lastBuildDate>
|
||||
<item>
|
||||
<title>Multi-Head Low-Rank Attention</title>
|
||||
<link>https://arxiv.org/abs/2603.02188</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.02188.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Songtao Liu, Hongwu Peng, Zhiwei Zhang, Zhengyu Chen, Yue Guo</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Long-context inference in large language models is bottlenecked by Key--Value (KV) cache loading during the decoding stage, where the sequential nature of generation requires repeatedly transferring the KV cache from off-chip High-Bandwidth Memory (HBM) to on-chip Static Random-Access Memory (SRAM) at each step. While Multi-Head Latent Attention (MLA) significantly reduces the total KV cache size, it suffers from a sharding bottleneck during distributed decoding via Tensor Parallelism (TP). Since its single latent head cannot be partitioned, each device is forced to redundantly load the complete KV cache for every token, consuming excessive memory traffic and diminishing TP benefits like weight sharding. In this work, we propose Multi-Head Low-Rank Attention (MLRA), which enables partitionable latent states for efficient 4-way TP decoding. Extensive experiments show that MLRA achieves state-of-the-art perplexity and downstream task performance, while also delivering a 2.8times decoding speedup over MLA. Code is available at https://github.com/SongtaoLiu0823/MLRA. Pretrained weights, along with the training and evaluation data, are available at https://huggingface.co/Soughing/MLRA.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.02188</guid>
|
||||
<pubDate>Mon, 02 Mar 2026 18:52:38 +0000</pubDate>
|
||||
<title>According to Me: Long-Term Personalized Referential Memory QA</title>
|
||||
<link>https://arxiv.org/abs/2603.01990</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.01990.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jingbiao Mei, Jinghong Chen, Guangyu Yang, Xinyu Hou, Margaret Li, Bill Byrne</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Personalized AI assistants must recall and reason over long-term user memory, which naturally spans multiple modalities and sources such as images, videos, and emails. However, existing Long-term Memory benchmarks focus primarily on dialogue history, failing to capture realistic personalized references grounded in lived experience. We introduce ATM-Bench, the first benchmark for multimodal, multi-source personalized referential Memory QA. ATM-Bench contains approximately four years of privacy-preserving personal memory data and human-annotated question-answer pairs with ground-truth memory evidence, including queries that require resolving personal references, multi-evidence reasoning from multi-source and handling conflicting evidence. We propose Schema-Guided Memory (SGM) to structurally represent memory items originated from different sources. In experiments, we implement 5 state-of-the-art memory systems along with a standard RAG baseline and evaluate variants with different memory ingestion, retrieval, and answer generation techniques. We find poor performance (under 20\% accuracy) on the ATM-Bench-Hard set, and that SGM improves performance over Descriptive Memory commonly adopted in prior works. Code available at: https://github.com/JingbiaoMei/ATM-Bench</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.01990</guid>
|
||||
<pubDate>Mon, 02 Mar 2026 15:42:29 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>BrandFusion: A Multi-Agent Framework for Seamless Brand Integration in Text-to-Video Generation</title>
|
||||
<link>https://arxiv.org/abs/2603.02816</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.02816.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zihao Zhu, Ruotong Wang, Siwei Lyu, Min Zhang, Baoyuan Wu</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> The rapid advancement of text-to-video (T2V) models has revolutionized content creation, yet their commercial potential remains largely untapped. We introduce, for the first time, the task of seamless brand integration in T2V: automatically embedding advertiser brands into prompt-generated videos while preserving semantic fidelity to user intent. This task confronts three core challenges: maintaining prompt fidelity, ensuring brand recognizability, and achieving contextually natural integration. To address them, we propose BrandFusion, a novel multi-agent framework comprising two synergistic phases. In the offline phase (advertiser-facing), we construct a Brand Knowledge Base by probing model priors and adapting to novel brands via lightweight fine-tuning. In the online phase (user-facing), five agents jointly refine user prompts through iterative refinement, leveraging the shared knowledge base and real-time contextual tracking to ensure brand visibility and semantic alignment. Experiments on 18 established and 2 custom brands across multiple state-of-the-art T2V models demonstrate that BrandFusion significantly outperforms baselines in semantic preservation, brand recognizability, and integration naturalness. Human evaluations further confirm higher user satisfaction, establishing a practical pathway for sustainable T2V monetization.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.02816</guid>
|
||||
<pubDate>Tue, 03 Mar 2026 10:10:41 +0000</pubDate>
|
||||
<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> 5</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>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> 121</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>
|
||||
<title>Any to Full: Prompting Depth Anything for Depth Completion in One Stage</title>
|
||||
<link>https://arxiv.org/abs/2603.05711</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.05711.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhiyuan Zhou, Ruofeng Liu, Taichi Liu, Weijian Zuo, Shanshan Wang, Zhiqing Hong, Desheng Zhang</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Accurate, dense depth estimation is crucial for robotic perception, but commodity sensors often yield sparse or incomplete measurements due to hardware limitations. Existing RGBD-fused depth completion methods learn priors jointly conditioned on training RGB distribution and specific depth patterns, limiting domain generalization and robustness to various depth patterns. Recent efforts leverage monocular depth estimation (MDE) models to introduce domain-general geometric priors, but current two-stage integration strategies relying on explicit relative-to-metric alignment incur additional computation and introduce structured distortions. To this end, we present Any2Full, a one-stage, domain-general, and pattern-agnostic framework that reformulates completion as a scale-prompting adaptation of a pretrained MDE model. To address varying depth sparsity levels and irregular spatial distributions, we design a Scale-Aware Prompt Encoder. It distills scale cues from sparse inputs into unified scale prompts, guiding the MDE model toward globally scale-consistent predictions while preserving its geometric priors. Extensive experiments demonstrate that Any2Full achieves superior robustness and efficiency. It outperforms OMNI-DC by 32.2\% in average AbsREL and delivers a 1.4times speedup over PriorDA with the same MDE backbone, establishing a new paradigm for universal depth completion. Codes and checkpoints are available at https://github.com/zhiyuandaily/Any2Full.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.05711</guid>
|
||||
<pubDate>Thu, 05 Mar 2026 22:08:40 +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> 1</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>
|
||||
<title>EmboAlign: Aligning Video Generation with Compositional Constraints for Zero-Shot Manipulation</title>
|
||||
<link>https://arxiv.org/abs/2603.05757</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.05757.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Gehao Zhang, Zhenyang Ni, Payal Mohapatra, Han Liu, Ruohan Zhang, Qi Zhu</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Video generative models (VGMs) pretrained on large-scale internet data can produce temporally coherent rollout videos that capture rich object dynamics, offering a compelling foundation for zero-shot robotic manipulation. However, VGMs often produce physically implausible rollouts, and converting their pixel-space motion into robot actions through geometric retargeting further introduces cumulative errors from imperfect depth estimation and keypoint tracking. To address these challenges, we present , a data-free framework that aligns VGM outputs with compositional constraints generated by vision-language models (VLMs) at inference time. The key insight is that VLMs offer a capability complementary to VGMs: structured spatial reasoning that can identify the physical constraints critical to the success and safety of manipulation execution. Given a language instruction, uses a VLM to automatically extract a set of compositional constraints capturing task-specific requirements, which are then applied at two stages: (1) constraint-guided rollout selection, which scores and filters a batch of VGM rollouts to retain the most physically plausible candidate, and (2) constraint-based trajectory optimization, which uses the selected rollout as initialization and refines the robot trajectory under the same constraint set to correct retargeting errors. We evaluate on six real-robot manipulation tasks requiring precise, constraint-sensitive execution, improving the overall success rate by 43.3\% points over the strongest baseline without any task-specific training data.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.05757</guid>
|
||||
<pubDate>Thu, 05 Mar 2026 23:31:56 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>SAHOO: Safeguarded Alignment for High-Order Optimization Objectives in Recursive Self-Improvement</title>
|
||||
<link>https://arxiv.org/abs/2603.06333</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.06333.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> 1</p><p><b>Summary:</b> Recursive self-improvement is moving from theory to practice: modern systems can critique, revise, and evaluate their own outputs, yet iterative self-modification risks subtle alignment drift. We introduce SAHOO, a practical framework to monitor and control drift through three safeguards: (i) the Goal Drift Index (GDI), a learned multi-signal detector combining semantic, lexical, structural, and distributional measures; (ii) constraint preservation checks that enforce safety-critical invariants such as syntactic correctness and non-hallucination; and (iii) regression-risk quantification to flag improvement cycles that undo prior gains. Across 189 tasks in code generation, mathematical reasoning, and truthfulness, SAHOO produces substantial quality gains, including 18.3 percent improvement in code tasks and 16.8 percent in reasoning, while preserving constraints in two domains and maintaining low violations in truthfulness. Thresholds are calibrated on a small validation set of 18 tasks across three cycles. We further map the capability-alignment frontier, showing efficient early improvement cycles but rising alignment costs later and exposing domain-specific tensions such as fluency versus factuality. SAHOO therefore makes alignment preservation during recursive self-improvement measurable, deployable, and systematically validated at scale.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.06333</guid>
|
||||
<pubDate>Fri, 06 Mar 2026 14:44:51 +0000</pubDate>
|
||||
<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> 3</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>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> 37</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>
|
||||
<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> 13</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>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> 9</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>
|
||||
<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> 19</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>Bolbosh: Script-Aware Flow Matching for Kashmiri Text-to-Speech</title>
|
||||
<link>https://arxiv.org/abs/2603.07513</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.07513.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tajamul Ashraf, Burhaan Rasheed Zargar, Saeed Abdul Muizz, Ifrah Mushtaq, Nazima Mehdi, Iqra Altaf Gillani, Aadil Amin Kak, Janibul Bashir</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Kashmiri is spoken by around 7 million people but remains critically underserved in speech technology, despite its official status and rich linguistic heritage. The lack of robust Text-to-Speech (TTS) systems limits digital accessibility and inclusive human-computer interaction for native speakers. In this work, we present the first dedicated open-source neural TTS system designed for Kashmiri. We show that zero-shot multilingual baselines trained for Indic languages fail to produce intelligible speech, achieving a Mean Opinion Score (MOS) of only 1.86, largely due to inadequate modeling of Perso-Arabic diacritics and language-specific phonotactics. To address these limitations, we propose Bolbosh, a supervised cross-lingual adaptation strategy based on Optimal Transport Conditional Flow Matching (OT-CFM) within the Matcha-TTS framework. This enables stable alignment under limited paired data. We further introduce a three-stage acoustic enhancement pipeline consisting of dereverberation, silence trimming, and loudness normalization to unify heterogeneous speech sources and stabilize alignment learning. The model vocabulary is expanded to explicitly encode Kashmiri graphemes, preserving fine-grained vowel distinctions. Our system achieves a MOS of 3.63 and a Mel-Cepstral Distortion (MCD) of 3.73, substantially outperforming multilingual baselines and establishing a new benchmark for Kashmiri speech synthesis. Our results demonstrate that script-aware and supervised flow-based adaptation are critical for low-resource TTS in diacritic-sensitive languages. Code and data are available at: https://github.com/gaash-lab/Bolbosh.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.07513</guid>
|
||||
<pubDate>Sun, 08 Mar 2026 07:34:15 +0000</pubDate>
|
||||
<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>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>
|
||||
<title>SVG-EAR: Parameter-Free Linear Compensation for Sparse Video Generation via Error-aware Routing</title>
|
||||
<link>https://arxiv.org/abs/2603.08982</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.08982.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xuanyi Zhou, Qiuyang Mang, Shuo Yang, Haocheng Xi, Jintao Zhang, Huanzhi Mao, Joseph E. Gonzalez, Kurt Keutzer, Ion Stoica, Alvin Cheung</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Diffusion Transformers (DiTs) have become a leading backbone for video generation, yet their quadratic attention cost remains a major bottleneck. Sparse attention reduces this cost by computing only a subset of attention blocks. However, prior methods often either drop the remaining blocks, which incurs information loss, or rely on learned predictors to approximate them, introducing training overhead and potential output distribution shifting. In this paper, we show that the missing contributions can be recovered without training: after semantic clustering, keys and values within each block exhibit strong similarity and can be well summarized by a small set of cluster centroids. Based on this observation, we introduce SVG-EAR, a parameter-free linear compensation branch that uses the centroid to approximate skipped blocks and recover their contributions. While centroid compensation is accurate for most blocks, it can fail on a small subset. Standard sparsification typically selects blocks by attention scores, which indicate where the model places its attention mass, but not where the approximation error would be largest. SVG-EAR therefore performs error-aware routing: a lightweight probe estimates the compensation error for each block, and we compute exactly the blocks with the highest error-to-cost ratio while compensating for skipped blocks. We provide theoretical guarantees that relate attention reconstruction error to clustering quality, and empirically show that SVG-EAR improves the quality-efficiency trade-off and increases throughput at the same generation fidelity on video diffusion tasks. Overall, SVG-EAR establishes a clear Pareto frontier over prior approaches, achieving up to 1.77times and 1.93times speedups while maintaining PSNRs of up to 29.759 and 31.043 on Wan2.2 and HunyuanVideo, respectively.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.08982</guid>
|
||||
<pubDate>Mon, 09 Mar 2026 22:15:31 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>TALON: Test-time Adaptive Learning for On-the-Fly Category Discovery</title>
|
||||
<link>https://arxiv.org/abs/2603.08075</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.08075.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yanan Wu, Yuhan Yan, Tailai Chen, Zhixiang Chi, ZiZhang Wu, Yi Jin, Yang Wang, Zhenbo Li</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> On-the-fly category discovery (OCD) aims to recognize known categories while simultaneously discovering novel ones from an unlabeled online stream, using a model trained only on labeled data. Existing approaches freeze the feature extractor trained offline and employ a hash-based framework that quantizes features into binary codes as class prototypes. However, discovering novel categories with a fixed knowledge base is counterintuitive, as the learning potential of incoming data is entirely neglected. In addition, feature quantization introduces information loss, diminishes representational expressiveness, and amplifies intra-class variance. It often results in category explosion, where a single class is fragmented into multiple pseudo-classes. To overcome these limitations, we propose a test-time adaptation framework that enables learning through discovery. It incorporates two complementary strategies: a semantic-aware prototype update and a stable test-time encoder update. The former dynamically refines class prototypes to enhance classification, whereas the latter integrates new information directly into the parameter space. Together, these components allow the model to continuously expand its knowledge base with newly encountered samples. Furthermore, we introduce a margin-aware logit calibration in the offline stage to enlarge inter-class margins and improve intra-class compactness, thereby reserving embedding space for future class discovery. Experiments on standard OCD benchmarks demonstrate that our method substantially outperforms existing hash-based state-of-the-art approaches, yielding notable improvements in novel-class accuracy and effectively mitigating category explosion. The code is publicly available at blue{https://github.com/ynanwu/TALON}.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.08075</guid>
|
||||
<pubDate>Mon, 09 Mar 2026 08:14:58 +0000</pubDate>
|
||||
<title>Meissa: Multi-modal Medical Agentic Intelligence</title>
|
||||
<link>https://arxiv.org/abs/2603.09018</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.09018.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yixiong Chen, Xinyi Bai, Yue Pan, Zongwei Zhou, Alan Yuille</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Multi-modal large language models (MM-LLMs) have shown strong performance in medical image understanding and clinical reasoning. Recent medical agent systems extend them with tool use and multi-agent collaboration, enabling complex decision-making. However, these systems rely almost entirely on frontier models (e.g., GPT), whose API-based deployment incurs high cost, high latency, and privacy risks that conflict with on-premise clinical requirements. We present Meissa, a lightweight 4B-parameter medical MM-LLM that brings agentic capability offline. Instead of imitating static answers, Meissa learns both when to engage external interaction (strategy selection) and how to execute multi-step interaction (strategy execution) by distilling structured trajectories from frontier models. Specifically, we propose: (1) Unified trajectory modeling: trajectories (reasoning and action traces) are represented within a single state-action-observation formalism, allowing one model to generalize across heterogeneous medical environments. (2) Three-tier stratified supervision: the model's own errors trigger progressive escalation from direct reasoning to tool-augmented and multi-agent interaction, explicitly learning difficulty-aware strategy selection. (3) Prospective-retrospective supervision: pairing exploratory forward traces with hindsight-rationalized execution traces enables stable learning of effective interaction policies. Trained on 40K curated trajectories, Meissa matches or exceeds proprietary frontier agents in 10 of 16 evaluation settings across 13 medical benchmarks spanning radiology, pathology, and clinical reasoning. Using over 25x fewer parameters than typical frontier models like Gemini-3, Meissa operates fully offline with 22x lower end-to-end latency compared to API-based deployment. Data, models, and environments are released at https://github.com/Schuture/Meissa.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.09018</guid>
|
||||
<pubDate>Mon, 09 Mar 2026 23:22:55 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Micro-Diffusion Compression -- Binary Tree Tweedie Denoising for Online Probability Estimation</title>
|
||||
<link>https://arxiv.org/abs/2603.08771</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.08771.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Roberto Tacconelli</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> We present Midicoth, a lossless compression system that introduces a micro-diffusion denoising layer for improving probability estimates produced by adaptive statistical models. In compressors such as Prediction by Partial Matching (PPM), probability estimates are smoothed by a prior to handle sparse observations. When contexts have been seen only a few times, this prior dominates the prediction and produces distributions that are significantly flatter than the true source distribution, leading to compression inefficiency. Midicoth addresses this limitation by treating prior smoothing as a shrinkage process and applying a reverse denoising step that corrects predicted probabilities using empirical calibration statistics. To make this correction data-efficient, the method decomposes each byte prediction into a hierarchy of binary decisions along a bitwise tree. This converts a single 256-way calibration problem into a sequence of binary calibration tasks, enabling reliable estimation of correction terms from relatively small numbers of observations. The denoising process is applied in multiple successive steps, allowing each stage to refine residual prediction errors left by the previous one. The micro-diffusion layer operates as a lightweight post-blend calibration stage applied after all model predictions have been combined, allowing it to correct systematic biases in the final probability distribution. Midicoth combines five fully online components: an adaptive PPM model, a long-range match model, a trie-based word model, a high-order context model, and the micro-diffusion denoiser applied as the final stage.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.08771</guid>
|
||||
<pubDate>Mon, 09 Mar 2026 16:59:24 +0000</pubDate>
|
||||
<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> 45</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>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> 5</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>
|
||||
<title>StyleVLA: Driving Style-Aware Vision Language Action Model for Autonomous Driving</title>
|
||||
<link>https://arxiv.org/abs/2603.09482</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.09482.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuan Gao, Dengyuan Hua, Mattia Piccinini, Finn Rasmus Schäfer, Korbinian Moller, Lin Li, Johannes Betz</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Vision Language Models (VLMs) bridge visual perception and linguistic reasoning. In Autonomous Driving (AD), this synergy has enabled Vision Language Action (VLA) models, which translate high-level multimodal understanding into driving behaviors, typically represented as future trajectories. However, existing VLA models mainly generate generic collision-free trajectories. Beyond collision avoidance, adapting to diverse driving styles (e.g., sporty, comfortable) is essential for personalized driving. Moreover, many methods treat trajectory generation as naive token prediction, which can produce kinematically infeasible actions. To address these limitations, we present StyleVLA, a physics-informed VLA framework for generating diverse and physically plausible driving behaviors. We introduce a hybrid loss that combines a kinematic consistency constraint with a continuous regression head to improve trajectory feasibility. To train StyleVLA, built on Qwen3-VL-4B, we construct a large-scale instruction dataset with over 1.2k scenarios, 76k Bird's Eye View (BEV) samples, and 42k First Person View (FPV) samples, with ground-truth trajectories for five driving styles and natural-language instructions. Experiments show that our 4B-parameter StyleVLA significantly outperforms proprietary models (e.g., Gemini-3-Pro) and state-of-the-art VLA models. Using a composite driving score measuring success rate, physical feasibility, and style adherence, StyleVLA achieves 0.55 on BEV and 0.51 on FPV, versus 0.32 and 0.35 for Gemini-3-Pro. These results show that a specialized, physics-informed, lightweight model can surpass closed-source models on domain-specific tasks.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.09482</guid>
|
||||
<pubDate>Tue, 10 Mar 2026 10:33:58 +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> 11</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>
|
||||
<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>ConFu: Contemplate the Future for Better Speculative Sampling</title>
|
||||
<link>https://arxiv.org/abs/2603.08899</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.08899.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zongyue Qin, Raghavv Goel, Mukul Gagrani, Risheek Garrepalli, Mingu Lee, Yizhou Sun</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Speculative decoding has emerged as a powerful approach to accelerate large language model (LLM) inference by employing lightweight draft models to propose candidate tokens that are subsequently verified by the target model. The effectiveness of this paradigm critically depends on the quality of the draft model. While recent advances such as the EAGLE series achieve state-of-the-art speedup, existing draft models remain limited by error accumulation: they condition only on the current prefix, causing their predictions to drift from the target model over steps. In this work, we propose ConFu (Contemplate the Future), a novel speculative decoding framework that enables draft models to anticipate the future direction of generation. ConFu introduces (i) contemplate tokens and soft prompts that allow the draft model to leverage future-oriented signals from the target model at negligible cost, (ii) a dynamic contemplate token mechanism with MoE to enable context-aware future prediction, and (iii) a training framework with anchor token sampling and future prediction replication that learns robust future prediction. Experiments demonstrate that ConFu improves token acceptance rates and generation speed over EAGLE-3 by 8--11% across various downstream tasks with Llama-3 3B and 8B models. We believe our work is the first to bridge speculative decoding with continuous reasoning tokens, offering a new direction for accelerating LLM inference.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.08899</guid>
|
||||
<pubDate>Mon, 09 Mar 2026 20:11:06 +0000</pubDate>
|
||||
<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> 22</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>BiCLIP: Domain Canonicalization via Structured Geometric Transformation</title>
|
||||
<link>https://arxiv.org/abs/2603.08942</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.08942.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Pranav Mantini, Shishir K. Shah</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Recent advances in vision-language models (VLMs) have demonstrated remarkable zero-shot capabilities, yet adapting these models to specialized domains remains a significant challenge. Building on recent theoretical insights suggesting that independently trained VLMs are related by a canonical transformation, we extend this understanding to the concept of domains. We hypothesize that image features across disparate domains are related by a canonicalized geometric transformation that can be recovered using a small set of anchors. Few-shot classification provides a natural setting for this alignment, as the limited labeled samples serve as the anchors required to estimate this transformation. Motivated by this hypothesis, we introduce BiCLIP, a framework that applies a targeted transformation to multimodal features to enhance cross-modal alignment. Our approach is characterized by its extreme simplicity and low parameter footprint. Extensive evaluations across 11 standard benchmarks, including EuroSAT, DTD, and FGVCAircraft, demonstrate that BiCLIP consistently achieves state-of-the-art results. Furthermore, we provide empirical verification of existing geometric findings by analyzing the orthogonality and angular distribution of the learned transformations, confirming that structured alignment is the key to robust domain adaptation. Code is available at https://github.com/QuantitativeImagingLaboratory/BilinearCLIP</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.08942</guid>
|
||||
<pubDate>Mon, 09 Mar 2026 21:26:15 +0000</pubDate>
|
||||
<title>Code-Space Response Oracles: Generating Interpretable Multi-Agent Policies with Large Language Models</title>
|
||||
<link>https://arxiv.org/abs/2603.10098</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.10098.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Daniel Hennes, Zun Li, John Schultz, Marc Lanctot</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Recent advances in multi-agent reinforcement learning, particularly Policy-Space Response Oracles (PSRO), have enabled the computation of approximate game-theoretic equilibria in increasingly complex domains. However, these methods rely on deep reinforcement learning oracles that produce `black-box' neural network policies, making them difficult to interpret, trust or debug. We introduce Code-Space Response Oracles (CSRO), a novel framework that addresses this challenge by replacing RL oracles with Large Language Models (LLMs). CSRO reframes the best response computation as a code generation task, prompting an LLM to generate policies directly as human-readable code. This approach not only yields inherently interpretable policies but also leverages the LLM's pretrained knowledge to discover complex, human-like strategies. We explore multiple ways to construct and enhance an LLM-based oracle: zero-shot prompting, iterative refinement and AlphaEvolve, a distributed LLM-based evolutionary system. We demonstrate that CSRO achieves performance competitive with baselines while producing a diverse set of explainable policies. Our work presents a new perspective on multi-agent learning, shifting the focus from optimizing opaque policy parameters to synthesizing interpretable algorithmic behavior.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.10098</guid>
|
||||
<pubDate>Tue, 10 Mar 2026 17:37:06 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>A Text-Native Interface for Generative Video Authoring</title>
|
||||
<link>https://arxiv.org/abs/2603.09072</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.09072.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xingyu Bruce Liu, Mira Dontcheva, Dingzeyu Li</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Everyone can write their stories in freeform text format -- it's something we all learn in school. Yet storytelling via video requires one to learn specialized and complicated tools. In this paper, we introduce Doki, a text-native interface for generative video authoring, aligning video creation with the natural process of text writing. In Doki, writing text is the primary interaction: within a single document, users define assets, structure scenes, create shots, refine edits, and add audio. We articulate the design principles of this text-first approach and demonstrate Doki's capabilities through a series of examples. To evaluate its real-world use, we conducted a week-long deployment study with participants of varying expertise in video authoring. This work contributes a fundamental shift in generative video interfaces, demonstrating a powerful and accessible new way to craft visual stories.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.09072</guid>
|
||||
<pubDate>Tue, 10 Mar 2026 01:33:41 +0000</pubDate>
|
||||
<title>CLIPO: Contrastive Learning in Policy Optimization Generalizes RLVR</title>
|
||||
<link>https://arxiv.org/abs/2603.10101</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.10101.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sijia Cui, Pengyu Cheng, Jiajun Song, Yongbo Gai, Guojun Zhang, Zhechao Yu, Jianhe Lin, Xiaoxi Jiang, Guanjun Jiang</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Reinforcement Learning with Verifiable Rewards (RLVR) has significantly advanced the reasoning capacity of Large Language Models (LLMs). However, RLVR solely relies on final answers as outcome rewards, neglecting the correctness of intermediate reasoning steps. Training on these process-wrong but outcome-correct rollouts can lead to hallucination and answer-copying, severely undermining the model's generalization and robustness. To address this, we incorporate a Contrastive Learning mechanism into the Policy Optimization (CLIPO) to generalize the RLVR process. By optimizing a contrastive loss over successful rollouts, CLIPO steers the LLM to capture the invariant structure shared across correct reasoning paths. This provides a more robust cross-trajectory regularization than the original single-path supervision in RLVR, effectively mitigating step-level reasoning inconsistencies and suppressing hallucinatory artifacts. In experiments, CLIPO consistently improves multiple RLVR baselines across diverse reasoning benchmarks, demonstrating uniform improvements in generalization and robustness for policy optimization of LLMs. Our code and training recipes are available at https://github.com/Qwen-Applications/CLIPO.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.10101</guid>
|
||||
<pubDate>Tue, 10 Mar 2026 17:59:54 +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> 21</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>
|
||||
<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> 3</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>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> 3</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>
|
||||
<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> 19</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>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> 2</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>
|
||||
<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> 59</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>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> 33</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>
|
||||
<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> 10</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>Beyond Test-Time Training: Learning to Reason via Hardware-Efficient Optimal Control</title>
|
||||
<link>https://arxiv.org/abs/2603.09221</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.09221.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Peihao Wang, Shan Yang, Xijun Wang, Tesi Xiao, Xin Liu, Changlong Yu, Yu Lou, Pan Li, Zhangyang Wang, Ming Lin, René Vidal</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Associative memory has long underpinned the design of sequential models. Beyond recall, humans reason by projecting future states and selecting goal-directed actions, a capability that modern language models increasingly require but do not natively encode. While prior work uses reinforcement learning or test-time training, planning remains external to the model architecture. We formulate reasoning as optimal control and introduce the Test-Time Control (TTC) layer, which performs finite-horizon LQR planning over latent states at inference time, represents a value function within neural architectures, and leverages it as the nested objective to enable planning before prediction. To ensure scalability, we derive a hardware-efficient LQR solver based on a symplectic formulation and implement it as a fused CUDA kernel, enabling parallel execution with minimal overhead. Integrated as an adapter into pretrained LLMs, TTC layers improve mathematical reasoning performance by up to +27.8% on MATH-500 and 2-3x Pass@8 improvements on AMC and AIME, demonstrating that embedding optimal control as an architectural component provides an effective and scalable mechanism for reasoning beyond test-time training.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.09221</guid>
|
||||
<pubDate>Tue, 10 Mar 2026 05:42:13 +0000</pubDate>
|
||||
<title>Causal Concept Graphs in LLM Latent Space for Stepwise Reasoning</title>
|
||||
<link>https://arxiv.org/abs/2603.10377</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.10377.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Md Muntaqim Meherab, Noor Islam S. Mohammad, Faiza Feroz</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Sparse autoencoders can localize where concepts live in language models, but not how they interact during multi-step reasoning. We propose Causal Concept Graphs (CCG): a directed acyclic graph over sparse, interpretable latent features, where edges capture learned causal dependencies between concepts. We combine task-conditioned sparse autoencoders for concept discovery with DAGMA-style differentiable structure learning for graph recovery and introduce the Causal Fidelity Score (CFS) to evaluate whether graph-guided interventions induce larger downstream effects than random ones. On ARC-Challenge, StrategyQA, and LogiQA with GPT-2 Medium, across five seeds (n{=}15 paired runs), CCG achieves CFS=5.654pm0.625, outperforming ROME-style tracing (3.382pm0.233), SAE-only ranking (2.479pm0.196), and a random baseline (1.032pm0.034), with p<0.0001 after Bonferroni correction. Learned graphs are sparse (5-6\% edge density), domain-specific, and stable across seeds.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.10377</guid>
|
||||
<pubDate>Wed, 11 Mar 2026 03:46:38 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Reward Prediction with Factorized World States</title>
|
||||
<link>https://arxiv.org/abs/2603.09400</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.09400.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yijun Shen, Delong Chen, Xianming Hu, Jiaming Mi, Hongbo Zhao, Kai Zhang, Pascale Fung</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Agents must infer action outcomes and select actions that maximize a reward signal indicating how close the goal is to being reached. Supervised learning of reward models could introduce biases inherent to training data, limiting generalization to novel goals and environments. In this paper, we investigate whether well-defined world state representations alone can enable accurate reward prediction across domains. To address this, we introduce StateFactory, a factorized representation method that transforms unstructured observations into a hierarchical object-attribute structure using language models. This structured representation allows rewards to be estimated naturally as the semantic similarity between the current state and the goal state under hierarchical constraint. Overall, the compact representation structure induced by StateFactory enables strong reward generalization capabilities. We evaluate on RewardPrediction, a new benchmark dataset spanning five diverse domains and comprising 2,454 unique action-observation trajectories with step-wise ground-truth rewards. Our method shows promising zero-shot results against both VLWM-critic and LLM-as-a-Judge reward models, achieving 60% and 8% lower EPIC distance, respectively. Furthermore, this superior reward quality successfully translates into improved agent planning performance, yielding success rate gains of +21.64% on AlfWorld and +12.40% on ScienceWorld over reactive system-1 policies and enhancing system-2 agent planning. Project Page: https://statefactory.github.io</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.09400</guid>
|
||||
<pubDate>Tue, 10 Mar 2026 09:12:20 +0000</pubDate>
|
||||
<title>UniCom: Unified Multimodal Modeling via Compressed Continuous Semantic Representations</title>
|
||||
<link>https://arxiv.org/abs/2603.10702</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.10702.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yaqi Zhao, Wang Lin, Zijian Zhang, Miles Yang, Jingyuan Chen, Wentao Zhang, Zhao Zhong, Liefeng Bo</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Current unified multimodal models typically rely on discrete visual tokenizers to bridge the modality gap. However, discretization inevitably discards fine-grained semantic information, leading to suboptimal performance in visual understanding tasks. Conversely, directly modeling continuous semantic representations (e.g., CLIP, SigLIP) poses significant challenges in high-dimensional generative modeling, resulting in slow convergence and training instability. To resolve this dilemma, we introduce UniCom, a unified framework that harmonizes multimodal understanding and generation via compressed continuous representation. We empirically demonstrate that reducing channel dimension is significantly more effective than spatial downsampling for both reconstruction and generation. Accordingly, we design an attention-based semantic compressor to distill dense features into a compact unified representation. Furthermore, we validate that the transfusion architecture surpasses query-based designs in convergence and consistency. Experiments demonstrate that UniCom achieves state-of-the-art generation performance among unified models. Notably, by preserving rich semantic priors, it delivers exceptional controllability in image editing and maintains image consistency even without relying on VAE.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.10702</guid>
|
||||
<pubDate>Wed, 11 Mar 2026 12:14:26 +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>
|
||||
<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>Compiler-First State Space Duality and Portable O(1) Autoregressive Caching for Inference</title>
|
||||
<link>https://arxiv.org/abs/2603.09555</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.09555.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Cosmo Santoni</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> State-space model releases are typically coupled to fused CUDA and Triton kernels, inheriting a hard dependency on NVIDIA hardware. We show that Mamba-2's state space duality algorithm -- diagonal state structure, chunkable recurrence, and einsum-dominated compute with static control flow -- maps cleanly onto what XLA's fusion and tiling passes actually optimise, making custom kernels optional rather than required. We implement the full inference path (prefill, cached autoregressive decoding) as shaped standard primitives under XLA, without hand-written kernels, and realise the architecture's theoretical O(1) state management as a compiled on-device cache requiring no host synchronisation during generation. The implementation runs unmodified on CPU, NVIDIA GPU, and Google Cloud TPU from a single JAX source. On TPU v6e across five model scales (130M--2.7B parameters), XLA-generated code reaches approximately 140 TFLOPS on single-stream prefill (15% MFU) and up to 64% bandwidth utilisation on decode. Greedy decoding matches the PyTorch/CUDA reference token-for-token across 64 steps, with hidden-state agreement within float32 rounding tolerance. The pattern transfers to any SSM recurrence satisfying the same structural conditions, on any platform with a mature XLA backend. The implementation is publicly available at https://github.com/CosmoNaught/mamba2-jax and merged into the Bonsai JAX model library.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.09555</guid>
|
||||
<pubDate>Tue, 10 Mar 2026 12:03:00 +0000</pubDate>
|
||||
<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> 5</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>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> 7</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>
|
||||
<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> 8</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>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> 24</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>
|
||||
<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> 6</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>Do What I Say: A Spoken Prompt Dataset for Instruction-Following</title>
|
||||
<link>https://arxiv.org/abs/2603.09881</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.09881.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Maike Züfle, Sara Papi, Fabian Retkowski, Szymon Mazurek, Marek Kasztelnik, Alexander Waibel, Luisa Bentivogli, Jan Niehues</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Speech Large Language Models (SLLMs) have rapidly expanded, supporting a wide range of tasks. These models are typically evaluated using text prompts, which may not reflect real-world scenarios where users interact with speech. To address this gap, we introduce DoWhatISay (DOWIS), a multilingual dataset of human-recorded spoken and written prompts designed to pair with any existing benchmark for realistic evaluation of SLLMs under spoken instruction conditions. Spanning 9 tasks and 11 languages, it provides 10 prompt variants per task-language pair, across five styles. Using DOWIS, we benchmark state-of-the-art SLLMs, analyzing the interplay between prompt modality, style, language, and task type. Results show that text prompts consistently outperform spoken prompts, particularly for low-resource and cross-lingual settings. Only for tasks with speech output, spoken prompts do close the gap, highlighting the need for speech-based prompting in SLLM evaluation.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.09881</guid>
|
||||
<pubDate>Tue, 10 Mar 2026 16:39:46 +0000</pubDate>
|
||||
<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> 21</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>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> 20</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>
|
||||
<title>V2M-Zero: Zero-Pair Time-Aligned Video-to-Music Generation</title>
|
||||
<link>https://arxiv.org/abs/2603.11042</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.11042.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yan-Bo Lin, Jonah Casebeer, Long Mai, Aniruddha Mahapatra, Gedas Bertasius, Nicholas J. Bryan</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Generating music that temporally aligns with video events is challenging for existing text-to-music models, which lack fine-grained temporal control. We introduce V2M-Zero, a zero-pair video-to-music generation approach that outputs time-aligned music for video. Our method is motivated by a key observation: temporal synchronization requires matching when and how much change occurs, not what changes. While musical and visual events differ semantically, they exhibit shared temporal structure that can be captured independently within each modality. We capture this structure through event curves computed from intra-modal similarity using pretrained music and video encoders. By measuring temporal change within each modality independently, these curves provide comparable representations across modalities. This enables a simple training strategy: fine-tune a text-to-music model on music-event curves, then substitute video-event curves at inference without cross-modal training or paired data. Across OES-Pub, MovieGenBench-Music, and AIST++, V2M-Zero achieves substantial gains over paired-data baselines: 5-21% higher audio quality, 13-15% better semantic alignment, 21-52% improved temporal synchronization, and 28% higher beat alignment on dance videos. We find similar results via a large crowd-source subjective listening test. Overall, our results validate that temporal alignment through within-modality features, rather than paired cross-modal supervision, is effective for video-to-music generation. Results are available at https://genjib.github.io/v2m_zero/</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.11042</guid>
|
||||
<pubDate>Wed, 11 Mar 2026 17:59:40 +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> 37</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> 1</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>
|
||||
<title>COMIC: Agentic Sketch Comedy Generation</title>
|
||||
<link>https://arxiv.org/abs/2603.11048</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.11048.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Susung Hong, Brian Curless, Ira Kemelmacher-Shlizerman, Steve Seitz</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> We propose a fully automated AI system that produces short comedic videos similar to sketch shows such as Saturday Night Live. Starting with character references, the system employs a population of agents loosely based on real production studio roles, structured to optimize the quality and diversity of ideas and outputs through iterative competition, evaluation, and improvement. A key contribution is the introduction of LLM critics aligned with real viewer preferences through the analysis of a corpus of comedy videos on YouTube to automatically evaluate humor. Our experiments show that our framework produces results approaching the quality of professionally produced sketches while demonstrating state-of-the-art performance in video generation.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.11048</guid>
|
||||
<pubDate>Wed, 11 Mar 2026 17:59:59 +0000</pubDate>
|
||||
</item>
|
||||
</channel>
|
||||
</rss>
|
||||
|
||||
Reference in New Issue
Block a user