bot: update RSS feed
This commit is contained in:
github-actions[bot]
464
feed.xml
464
feed.xml
@@ -7,342 +7,300 @@
|
||||
<docs>http://www.rssboard.org/rss-specification</docs>
|
||||
<generator>python-feedgen</generator>
|
||||
<language>en</language>
|
||||
<lastBuildDate>Thu, 09 Oct 2025 00:02:35 +0000</lastBuildDate>
|
||||
<lastBuildDate>Fri, 10 Oct 2025 00:02:54 +0000</lastBuildDate>
|
||||
<item>
|
||||
<title>On Code-Induced Reasoning in LLMs</title>
|
||||
<link>https://arxiv.org/abs/2509.21499</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.21499.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Abdul Waheed, Zhen Wu, Carolyn Rosé, Daphne Ippolito</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Code data has been shown to enhance the reasoning capabilities of large language models (LLMs), but it remains unclear which aspects of code are most responsible. We investigate this question with a systematic, data-centric framework. We construct parallel instruction datasets in ten programming languages and apply controlled perturbations that selectively disrupt structural or semantic properties of code. We then finetune LLMs from five model families and eight scales on each variant and evaluate their performance on natural language, math, and code tasks. Across 3,331 experiments, our results show that LLMs are more vulnerable to structural perturbations than semantic ones, particularly on math and code tasks. Appropriate abstractions like pseudocode and flowcharts can be as effective as code, while encoding the same information with fewer tokens without adhering to original syntax can often retain or even improve performance. Remarkably, even corrupted code with misleading signals remains competitive when surface-level regularities persist. Finally, syntactic styles also shape task-specific gains with Python favoring natural language reasoning and lower-level languages such as Java and Rust favoring math. Through our systematic framework, we aim to provide insight into how different properties of code influence reasoning and inform the design of training data for enhancing LLM reasoning capabilities.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.21499</guid>
|
||||
<pubDate>Thu, 25 Sep 2025 19:57:36 +0000</pubDate>
|
||||
<title>DeepTravel: An End-to-End Agentic Reinforcement Learning Framework for Autonomous Travel Planning Agents</title>
|
||||
<link>https://arxiv.org/abs/2509.21842</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.21842.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yansong Ning, Rui Liu, Jun Wang, Kai Chen, Wei Li, Jun Fang, Kan Zheng, Naiqiang Tan, Hao Liu</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Travel planning (TP) agent has recently worked as an emerging building block to interact with external tools and resources for travel itinerary generation, ensuring enjoyable user experience. Despite its benefits, existing studies rely on hand craft prompt and fixed agent workflow, hindering more flexible and autonomous TP agent. This paper proposes DeepTravel, an end to end agentic reinforcement learning framework for building autonomous travel planning agent, capable of autonomously planning, executing tools, and reflecting on tool responses to explore, verify, and refine intermediate actions in multi step reasoning. To achieve this, we first construct a robust sandbox environment by caching transportation, accommodation and POI data, facilitating TP agent training without being constrained by real world APIs limitations (e.g., inconsistent outputs). Moreover, we develop a hierarchical reward modeling system, where a trajectory level verifier first checks spatiotemporal feasibility and filters unsatisfied travel itinerary, and then the turn level verifier further validate itinerary detail consistency with tool responses, enabling efficient and precise reward service. Finally, we propose the reply augmented reinforcement learning method that enables TP agent to periodically replay from a failures experience buffer, emerging notable agentic capacity. We deploy trained TP agent on DiDi Enterprise Solutions App and conduct comprehensive online and offline evaluations, demonstrating that DeepTravel enables small size LLMs (e.g., Qwen3 32B) to significantly outperform existing frontier LLMs such as OpenAI o1, o3 and DeepSeek R1 in travel planning tasks.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.21842</guid>
|
||||
<pubDate>Fri, 26 Sep 2025 04:03:52 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>DRIFT: Learning from Abundant User Dissatisfaction in Real-World Preference Learning</title>
|
||||
<link>https://arxiv.org/abs/2510.02341</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.02341.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yifan Wang, Bolian Li, Junlin Wu, Zhaoxuan Tan, Zheli Liu, Ruqi Zhang, Ananth Grama, Qingkai Zeng</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Real-world large language model deployments (e.g., conversational AI systems, code generation assistants) naturally generate abundant implicit user dissatisfaction (DSAT) signals, as users iterate toward better answers through refinements, corrections, and expressed preferences, while explicit satisfaction (SAT) feedback is scarce. Existing preference learning approaches are poorly aligned with this data profile, as they rely on costly human annotations or assume plentiful positive responses. In this paper, we introduce DRIFT (Dissatisfaction-Refined Iterative preFerence Training), which anchors training on real-world DSAT signals and samples positives dynamically from the evolving policy. Empirically, DRIFT models trained on real-world WildFeedback datasets and synthetic UltraFeedback datasets achieve up to +6.23\% (7B) / +7.61\% (14B) on WildBench Task Score and up to +8.95\% (7B) / +12.29\% (14B) on AlpacaEval2 win rate over base models, outperforming strong baseline methods such as iterative DPO and SPIN. At larger scales, the improvements are particularly pronounced: 14B models trained with DRIFT surpass GPT-4o-mini on WildBench. Further analysis shows that DRIFT also preserves exploratory capacity, yielding more diverse high-reward solutions rather than collapsing to narrow subsets. Theoretically, we demonstrate that this design preserves preference margins and avoids the gradient degeneration. These results show that DRIFT is an effective and scalable recipe for real-world post-training that leverages the most abundant and informative signal. The code and data are available at https://github.com/cacayaya/DRIFT.git.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.02341</guid>
|
||||
<pubDate>Sat, 27 Sep 2025 03:06:27 +0000</pubDate>
|
||||
<title>Reinforcement Mid-Training</title>
|
||||
<link>https://arxiv.org/abs/2509.24375</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.24375.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yijun Tian, Shaoyu Chen, Zhichao Xu, Yawei Wang, Jinhe Bi, Peng Han, Wei Wang</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> The development of state-of-the-art large language models is commonly understood as a two-stage process involving pre-training and post-training. We point out the need for an additional intermediate stage called reinforcement mid-training with potential for strong performance gains. In this paper, we formally define the problem and identify three key challenges: (1) inefficient training due to excessive reasoning steps, (2) disregard of the imbalanced token entropy distribution, and (3) underutilization of token information. To address these challenges, we propose RMT, a framework for efficient, adaptive, and unified reinforcement mid-training with various innovative components. In particular, we first introduce a dynamic token budget mechanism that constrains unnecessary reasoning steps and mitigates model overthinking. Next, we design a curriculum-based adaptive sampling method that fosters a progressive learning trajectory from easy to hard tokens. Finally, we present a dual training strategy that combines reinforcement learning with next-token prediction, ensuring targeted learning on key tokens and full exploitation of all token information. Extensive experiments demonstrate the superiority of RMT over state-of-the-art methods, achieving up to +64.91% performance improvement with only 21% of the reasoning length in language modeling. We also show that checkpoints obtained after reinforcement mid-training can benefit the subsequent post-training, yielding up to +18.76% improvement in the mathematical domain.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.24375</guid>
|
||||
<pubDate>Mon, 29 Sep 2025 07:21:24 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>CoDA: Coding LM via Diffusion Adaptation</title>
|
||||
<link>https://arxiv.org/abs/2510.03270</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.03270.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haolin Chen, Shiyu Wang, Can Qin, Bo Pang, Zuxin Liu, Jielin Qiu, Jianguo Zhang, Yingbo Zhou, Zeyuan Chen, Ran Xu, Shelby Heinecke, Silvio Savarese, Caiming Xiong, Huan Wang, Weiran Yao</p><p><b>Upvotes:</b> 25</p><p><b>Summary:</b> Diffusion language models promise bidirectional context and infilling capabilities that autoregressive coders lack, yet practical systems remain heavyweight. We introduce CoDA, a 1.7B-parameter diffusion coder trained on TPU with a fully open-source training pipeline. CoDA pairs large-scale diffusion pre-training with code-centric mid-training and instruction tuning, enabling confidence-guided sampling that keeps inference latency competitive. On Humaneval, MBPP, and EvalPlus, CoDA-1.7B-Instruct matches or surpasses diffusion models up to 7B parameters. Our release includes model checkpoints, evaluation harnesses, and TPU training pipelines to accelerate research on lightweight diffusion-based coding assistants.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.03270</guid>
|
||||
<pubDate>Sat, 27 Sep 2025 05:41:55 +0000</pubDate>
|
||||
<title>Patch-as-Decodable-Token: Towards Unified Multi-Modal Vision Tasks in MLLMs</title>
|
||||
<link>https://arxiv.org/abs/2510.01954</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.01954.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yongyi Su, Haojie Zhang, Shijie Li, Nanqing Liu, Jingyi Liao, Junyi Pan, Yuan Liu, Xiaofen Xing, Chong Sun, Chen Li, Nancy F. Chen, Shuicheng Yan, Xulei Yang, Xun Xu</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Multimodal large language models (MLLMs) have advanced rapidly in recent years. However, existing approaches for vision tasks often rely on indirect representations, such as generating coordinates as text for detection, which limits performance and prevents dense prediction tasks like segmentation. To overcome these challenges, we introduce Patch-as-Decodable Token (PaDT), a unified paradigm that enables MLLMs to directly generate both textual and diverse visual outputs. Central to PaDT are Visual Reference Tokens (VRTs), derived from visual patch embeddings of query images and interleaved seamlessly with LLM's output textual tokens. A lightweight decoder then transforms LLM's outputs into detection, segmentation, and grounding predictions. Unlike prior methods, PaDT processes VRTs independently at each forward pass and dynamically expands the embedding table, thus improving localization and differentiation among similar objects. We further tailor a training strategy for PaDT by randomly selecting VRTs for supervised fine-tuning and introducing a robust per-token cross-entropy loss. Our empirical studies across four visual perception and understanding tasks suggest PaDT consistently achieving state-of-the-art performance, even compared with significantly larger MLLM models. The code is available at https://github.com/Gorilla-Lab-SCUT/PaDT.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.01954</guid>
|
||||
<pubDate>Thu, 02 Oct 2025 12:23:57 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>CCD: Mitigating Hallucinations in Radiology MLLMs via Clinical Contrastive Decoding</title>
|
||||
<link>https://arxiv.org/abs/2509.23379</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.23379.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xi Zhang, Zaiqiao Meng, Jake Lever, Edmond S. L. Ho</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Multimodal large language models (MLLMs) have recently achieved remarkable progress in radiology by integrating visual perception with natural language understanding. However, they often generate clinically unsupported descriptions, known as medical hallucinations, which pose serious risks in medical applications that demand accuracy and image-grounded outputs. Through empirical analysis, we find that prompt-induced hallucinations remain prevalent in radiology MLLMs, largely due to over-sensitivity to clinical sections. To address this, we introduce Clinical Contrastive Cecoding (CCD), a training-free and retrieval-free inference framework that integrates structured clinical signals from task-specific radiology expert models. CCD introduces a dual-stage contrastive mechanism to refine token-level logits during generation, thereby enhancing clinical fidelity without modifying the base MLLM. Experiments on three datasets and multiple models demonstrate that CCD consistently improves overall performance on radiology report generation (RRG). On the MIMIC-CXR dataset, it yields up to a 17% improvement in RadGraph-F1 when applied to state-of-the-art RRG models. Our approach provides a lightweight and generalisable solution for mitigating medical hallucinations, effectively bridging expert models and MLLMs in radiology.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.23379</guid>
|
||||
<pubDate>Sat, 27 Sep 2025 16:01:09 +0000</pubDate>
|
||||
<title>G^2RPO: Granular GRPO for Precise Reward in Flow Models</title>
|
||||
<link>https://arxiv.org/abs/2510.01982</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.01982.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yujie Zhou, Pengyang Ling, Jiazi Bu, Yibin Wang, Yuhang Zang, Jiaqi Wang, Li Niu, Guangtao Zhai</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> The integration of online reinforcement learning (RL) into diffusion and flow models has recently emerged as a promising approach for aligning generative models with human preferences. Stochastic sampling via Stochastic Differential Equations (SDE) is employed during the denoising process to generate diverse denoising directions for RL exploration. While existing methods effectively explore potential high-value samples, they suffer from sub-optimal preference alignment due to sparse and narrow reward signals. To address these challenges, we propose a novel Granular-GRPO (G^2RPO ) framework that achieves precise and comprehensive reward assessments of sampling directions in reinforcement learning of flow models. Specifically, a Singular Stochastic Sampling strategy is introduced to support step-wise stochastic exploration while enforcing a high correlation between the reward and the injected noise, thereby facilitating a faithful reward for each SDE perturbation. Concurrently, to eliminate the bias inherent in fixed-granularity denoising, we introduce a Multi-Granularity Advantage Integration module that aggregates advantages computed at multiple diffusion scales, producing a more comprehensive and robust evaluation of the sampling directions. Experiments conducted on various reward models, including both in-domain and out-of-domain evaluations, demonstrate that our G^2RPO significantly outperforms existing flow-based GRPO baselines,highlighting its effectiveness and robustness.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.01982</guid>
|
||||
<pubDate>Thu, 02 Oct 2025 12:57:12 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Fathom-DeepResearch: Unlocking Long Horizon Information Retrieval and Synthesis for SLMs</title>
|
||||
<link>https://arxiv.org/abs/2509.24107</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.24107.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shreyas Singh, Kunal Singh, Pradeep Moturi</p><p><b>Upvotes:</b> 57</p><p><b>Summary:</b> Tool-integrated reasoning has emerged as a key focus for enabling agentic applications. Among these, DeepResearch Agents have gained significant attention for their strong performance on complex, open-ended information-seeking tasks. We introduce Fathom-DeepResearch, an agentic system composed of two specialized models. The first is Fathom-Search-4B, a DeepSearch model trained from Qwen3-4B and optimized for evidence-based investigation through live web search and targeted webpage querying. Its training combines three advances: (i) DUETQA, a 5K-sample dataset generated via multi-agent self-play that enforces strict web-search dependence and heterogeneous source grounding; (ii) RAPO, a zero-overhead extension of GRPO that stabilizes multi-turn Reinforcement Learning with Verifiable Rewards through curriculum pruning, reward-aware advantage scaling, and per-prompt replay buffers; and (iii) a steerable step-level reward that classifies each tool call by cognitive behavior and marginal utility, enabling explicit control over search trajectory breadth, depth, and horizon. These improvements enable reliable extension of tool-calling beyond 20 calls when warranted. The second is Fathom-Synthesizer-4B, trained from Qwen3-4B, which converts multi-turn DeepSearch traces into structured, citation-dense DeepResearch Reports for comprehensive synthesis. Evaluated on DeepSearch benchmarks (SimpleQA, FRAMES, WebWalker, Seal0, MuSiQue) and DeepResearch-Bench, the system achieves state-of-the-art performance in the open-weights category while demonstrating strong generalization to diverse reasoning tasks including HLE, AIME-25, GPQA-Diamond, and MedQA.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.24107</guid>
|
||||
<pubDate>Sun, 28 Sep 2025 22:58:11 +0000</pubDate>
|
||||
<title>A Single Character can Make or Break Your LLM Evals</title>
|
||||
<link>https://arxiv.org/abs/2510.05152</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.05152.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jingtong Su, Jianyu Zhang, Karen Ullrich, Léon Bottou, Mark Ibrahim</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Common Large Language model (LLM) evaluations rely on demonstration examples to steer models' responses to the desired style. While the number of examples used has been studied and standardized, the choice of how to format examples is less investigated. In evaluation protocols and real world usage, users face the choice how to separate in-context examples: use a comma? new line? semi-colon? hashtag? etc.? Surprisingly, we find this seemingly minor choice can dramatically alter model response quality. Across leading model families (Llama, Qwen, Gemma), performance on MMLU for example can vary by pm 23% depending on the choice of delimiter. In fact, one can manipulate model rankings to put any model in the lead by only modifying the single character separating examples. We find LLMs' brittleness pervades topics, model families, and doesn't improve with scale. By probing attention head scores, we find that good-performing delimiters steer attention towards key tokens in the input. Finally, we explore methods to improve LLMs' robustness to the choice of delimiter. We find specifying the selected delimiter in the prompt boosts robustness and offer practical recommendations for the best-performing delimiters to select.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.05152</guid>
|
||||
<pubDate>Thu, 02 Oct 2025 13:27:28 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>CARE: Cognitive-reasoning Augmented Reinforcement for Emotional Support Conversation</title>
|
||||
<link>https://arxiv.org/abs/2510.05122</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.05122.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jie Zhu, Yuanchen Zhou, Shuo Jiang, Junhui Li, Lifan Guo, Feng Chen, Chi Zhang, Fang Kong</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Emotional Support Conversation (ESC) plays a vital role in alleviating psychological stress and providing emotional value through dialogue. While recent studies have largely focused on data augmentation and synthetic corpus construction, they often overlook the deeper cognitive reasoning processes that underpin effective emotional support. To address this gap, we propose CARE, a novel framework that strengthens reasoning in ESC without relying on large-scale synthetic data. CARE leverages the original ESC training set to guide models in generating logically coherent and supportive responses, thereby explicitly enhancing cognitive reasoning. Building on this foundation, we further employ reinforcement learning to refine and reinforce the reasoning process. Experimental results demonstrate that CARE significantly improves both the logical soundness and supportive quality of responses, advancing the development of empathetic, cognitively robust, and human-like emotional support systems.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.05122</guid>
|
||||
<pubDate>Tue, 30 Sep 2025 03:19:50 +0000</pubDate>
|
||||
<title>Cache-to-Cache: Direct Semantic Communication Between Large Language Models</title>
|
||||
<link>https://arxiv.org/abs/2510.03215</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.03215.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tianyu Fu, Zihan Min, Hanling Zhang, Jichao Yan, Guohao Dai, Wanli Ouyang, Yu Wang</p><p><b>Upvotes:</b> 63</p><p><b>Summary:</b> Multi-LLM systems harness the complementary strengths of diverse Large Language Models, achieving performance and efficiency gains unattainable by a single model. In existing designs, LLMs communicate through text, forcing internal representations to be transformed into output token sequences. This process both loses rich semantic information and incurs token-by-token generation latency. Motivated by these limitations, we ask: Can LLMs communicate beyond text? Oracle experiments show that enriching the KV-Cache semantics can improve response quality without increasing cache size, supporting KV-Cache as an effective medium for inter-model communication. Thus, we propose Cache-to-Cache (C2C), a new paradigm for direct semantic communication between LLMs. C2C uses a neural network to project and fuse the source model's KV-cache with that of the target model to enable direct semantic transfer. A learnable gating mechanism selects the target layers that benefit from cache communication. Compared with text communication, C2C utilizes the deep, specialized semantics from both models, while avoiding explicit intermediate text generation. Experiments show that C2C achieves 8.5-10.5% higher average accuracy than individual models. It further outperforms the text communication paradigm by approximately 3.0-5.0%, while delivering an average 2.0x speedup in latency. Our code is available at https://github.com/thu-nics/C2C.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.03215</guid>
|
||||
<pubDate>Fri, 03 Oct 2025 17:52:32 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Fast-dLLM v2: Efficient Block-Diffusion LLM</title>
|
||||
<link>https://arxiv.org/abs/2509.26328</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.26328.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chengyue Wu, Hao Zhang, Shuchen Xue, Shizhe Diao, Yonggan Fu, Zhijian Liu, Pavlo Molchanov, Ping Luo, Song Han, Enze Xie</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> Autoregressive (AR) large language models (LLMs) have achieved remarkable performance across a wide range of natural language tasks, yet their inherent sequential decoding limits inference efficiency. In this work, we propose Fast-dLLM v2, a carefully designed block diffusion language model (dLLM) that efficiently adapts pretrained AR models into dLLMs for parallel text generation, requiring only approximately 1B tokens of fine-tuning. This represents a 500x reduction in training data compared to full-attention diffusion LLMs such as Dream (580B tokens), while preserving the original model's performance. Our approach introduces a novel training recipe that combines a block diffusion mechanism with a complementary attention mask, enabling blockwise bidirectional context modeling without sacrificing AR training objectives. To further accelerate decoding, we design a hierarchical caching mechanism: a block-level cache that stores historical context representations across blocks, and a sub-block cache that enables efficient parallel generation within partially decoded blocks. Coupled with our parallel decoding pipeline, Fast-dLLM v2 achieves up to 2.5x speedup over standard AR decoding without compromising generation quality. Extensive experiments across diverse benchmarks demonstrate that Fast-dLLM v2 matches or surpasses AR baselines in accuracy, while delivering state-of-the-art efficiency among dLLMs - marking a significant step toward the practical deployment of fast and accurate LLMs. Code and model will be publicly released.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.26328</guid>
|
||||
<pubDate>Tue, 30 Sep 2025 14:40:18 +0000</pubDate>
|
||||
<title>CALM Before the STORM: Unlocking Native Reasoning for Optimization Modeling</title>
|
||||
<link>https://arxiv.org/abs/2510.04204</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.04204.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhengyang Tang, Zihan Ye, Chenyu Huang, Xuhan Huang, Chengpeng Li, Sihang Li, Guanhua Chen, Ming Yan, Zizhuo Wang, Hongyuan Zha, Dayiheng Liu, Benyou Wang</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Large Reasoning Models (LRMs) have demonstrated strong capabilities in complex multi-step reasoning, opening new opportunities for automating optimization modeling. However, existing domain adaptation methods, originally designed for earlier instruction-tuned models, often fail to exploit the advanced reasoning patterns of modern LRMs -- In particular, we show that direct fine-tuning on traditional non-reflective datasets leads to limited gains. To fully leverage LRMs' inherent reasoning abilities, we propose CALM (Corrective Adaptation with Lightweight Modification), a framework that progressively refines LRMs within their native reasoning modes for optimization modeling tasks. In CALM, an expert intervener identifies reasoning flaws and provides concise corrective hints, which the LRM incorporates to produce improved reasoning trajectories. These interventions modify fewer than 2.6\% of generated tokens, but generate high-quality data for soft adaptation through supervised fine-tuning. The adapted model is then further improved through reinforcement learning. Building on CALM, we develop STORM (Smart Thinking Optimization Reasoning Model), a 4B-parameter LRM that achieves a new state-of-the-art average accuracy of 68.9\% across five popular optimization modeling benchmarks, matching the performance of a 671B LRM. These results demonstrate that dynamic, hint-based data synthesis both preserves and amplifies the native reasoning patterns of modern LRMs, offering a more effective and scalable path towards expert-level performance on challenging optimization modeling tasks.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.04204</guid>
|
||||
<pubDate>Sun, 05 Oct 2025 13:38:31 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Demystifying deep search: a holistic evaluation with hint-free multi-hop questions and factorised metrics</title>
|
||||
<link>https://arxiv.org/abs/2510.05137</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.05137.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Maojia Song, Renhang Liu, Xinyu Wang, Yong Jiang, Pengjun Xie, Fei Huang, Soujanya Poria, Jingren Zhou</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> RAG (Retrieval-Augmented Generation) systems and web agents are increasingly evaluated on multi-hop deep search tasks, yet current practice suffers from two major limitations. First, most benchmarks leak the reasoning path in the question text, allowing models to follow surface cues rather than discover reasoning chains autonomously. Second, evaluation is typically reduced to a single pass rate, which collapses diverse behaviours into one score and obscures whether failures stem from inadequate search, poor knowledge use, or inappropriate refusal. To address these issues, we present WebDetective, a benchmark of hint-free multi-hop questions paired with a controlled Wikipedia sandbox that ensures full traceability of model actions, and a holistic evaluation framework that separates search sufficiency, knowledge utilisation, and refusal behaviour. Our evaluation of 25 state-of-the-art models reveals systematic weaknesses across all architectures: models struggle with knowledge utilisation despite having sufficient evidence and demonstrate near-absent appropriate refusal when evidence is lacking. These patterns expose a fundamental gap: today's systems excel at executing given reasoning paths but fail when required to discover them. We develop an agentic workflow, EvidenceLoop, that explicitly targets the challenges our benchmark identifies, incorporating verification loops and systematic evidence tracking that improve both search and synthesis capabilities. This baseline demonstrates that WebDetective's diagnostic framework can guide concrete architectural improvements, establishing our benchmark as a critical tool for developing genuinely autonomous reasoning systems rather than pattern-following agents.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.05137</guid>
|
||||
<pubDate>Wed, 01 Oct 2025 07:59:03 +0000</pubDate>
|
||||
<title>Why Low-Precision Transformer Training Fails: An Analysis on Flash Attention</title>
|
||||
<link>https://arxiv.org/abs/2510.04212</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.04212.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haiquan Qiu, Quanming Yao</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> The pursuit of computational efficiency has driven the adoption of low-precision formats for training transformer models. However, this progress is often hindered by notorious training instabilities. This paper provides the first mechanistic explanation for a long-standing and unresolved failure case where training with flash attention in low-precision settings leads to catastrophic loss explosions. Our in-depth analysis reveals that the failure is not a random artifact but caused by two intertwined phenomena: the emergence of similar low-rank representations within the attention mechanism and the compounding effect of biased rounding errors inherent in low-precision arithmetic. We demonstrate how these factors create a vicious cycle of error accumulation that corrupts weight updates, ultimately derailing the training dynamics. To validate our findings, we introduce a minimal modification to the flash attention that mitigates the bias in rounding errors. This simple change stabilizes the training process, confirming our analysis and offering a practical solution to this persistent problem.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.04212</guid>
|
||||
<pubDate>Sun, 05 Oct 2025 14:01:24 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>HalluGuard: Evidence-Grounded Small Reasoning Models to Mitigate Hallucinations in Retrieval-Augmented Generation</title>
|
||||
<link>https://arxiv.org/abs/2510.00880</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.00880.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Loris Bergeron, Ioana Buhnila, Jérôme François, Radu State</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Large Language Models (LLMs) excel in many NLP tasks but remain prone to hallucinations, limiting trust in real-world applications. We present HalluGuard, a 4B-parameter Small Reasoning Model (SRM) for mitigating hallucinations in Retrieval-Augmented Generation (RAG). HalluGuard classifies document-claim pairs as grounded or hallucinated and produces evidence-grounded justifications for transparency. Our approach combines (i) a domain-agnostic synthetic dataset derived from FineWeb and refined through multi-stage curation and data reformation, (ii) synthetic grounded and hallucinated claims, and (iii) preference-based fine-tuning with Odds Ratio Preference Optimization to distill large-model reasoning into a smaller backbone. On the RAGTruth subset of the LLM-AggreFact benchmark, HalluGuard achieves 84.0% balanced accuracy (BAcc), rivaling specialized models, MiniCheck (7B; 84.0%) and Granite Guardian 3.3 (8B; 82.2%) while using roughly half their parameters. Over the full benchmark it reaches 75.7% BAcc, matching larger general-purpose LLMs such as GPT-4o (75.9%). We will release HalluGuard and datasets under Apache 2.0 upon acceptance.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.00880</guid>
|
||||
<pubDate>Wed, 01 Oct 2025 13:28:20 +0000</pubDate>
|
||||
<title>Pushing on Multilingual Reasoning Models with Language-Mixed Chain-of-Thought</title>
|
||||
<link>https://arxiv.org/abs/2510.04230</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.04230.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Guijin Son, Donghun Yang, Hitesh Laxmichand Patel, Amit Agarwal, Hyunwoo Ko, Chanuk Lim, Srikant Panda, Minhyuk Kim, Nikunj Drolia, Dasol Choi, Kyong-Ha Lee, Youngjae Yu</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Recent frontier models employ long chain-of-thought reasoning to explore solution spaces in context and achieve stonger performance. While many works study distillation to build smaller yet capable models, most focus on English and little is known about language-specific reasoning. To bridge this gap, we first introduct **Language-Mixed CoT**, a reasoning schema that switches between English and a target language, using English as an anchor to excel in reasoning while minimizing translation artificats. As a Korean case study, we curate **Yi-Sang**: 5.79M native-Korean prompts from web Q&A, exams, STEM, and code; 3.7M long reasoning traces generated from Qwen3-32B; and a targeted 260k high-yield subset. We train ninve models (4B-35B) across six families (Qwen2.5, Llama-3.1, Gemma-3, etc). Our best model, **KO-REAson-35B**, achieves state-of-the-art performance, with the highest overall average score (64.0 \pm 25), ranking first on 5/9 benchmarks and second on the remainder. Samller and mid-sized models also benefit substantially, with an average improvement of +18.6 points across teh evaluated nine benchmarks. Ablations show **Language-Mixed CoT** is more effective than monolingual CoT, also resulting in cross-lingual and mult-modal performance gains. We release our data-curation pipeline, evaluation system, datasets, and models to advance research on language-specific reasoning. Data and model collection: https://huggingface.co/KOREAson.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.04230</guid>
|
||||
<pubDate>Sun, 05 Oct 2025 14:39:41 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>MEMTRACK: Evaluating Long-Term Memory and State Tracking in Multi-Platform Dynamic Agent Environments</title>
|
||||
<link>https://arxiv.org/abs/2510.01353</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.01353.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Darshan Deshpande, Varun Gangal, Hersh Mehta, Anand Kannappan, Rebecca Qian, Peng Wang</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Recent works on context and memory benchmarking have primarily focused on conversational instances but the need for evaluating memory in dynamic enterprise environments is crucial for its effective application. We introduce MEMTRACK, a benchmark designed to evaluate long-term memory and state tracking in multi-platform agent environments. MEMTRACK models realistic organizational workflows by integrating asynchronous events across multiple communication and productivity platforms such as Slack, Linear and Git. Each benchmark instance provides a chronologically platform-interleaved timeline, with noisy, conflicting, cross-referring information as well as potential codebase/file-system comprehension and exploration. Consequently, our benchmark tests memory capabilities such as acquistion, selection and conflict resolution. We curate the MEMTRACK dataset through both manual expert driven design and scalable agent based synthesis, generating ecologically valid scenarios grounded in real world software development processes. We introduce pertinent metrics for Correctness, Efficiency, and Redundancy that capture the effectiveness of memory mechanisms beyond simple QA performance. Experiments across SoTA LLMs and memory backends reveal challenges in utilizing memory across long horizons, handling cross-platform dependencies, and resolving contradictions. Notably, the best performing GPT-5 model only achieves a 60\% Correctness score on MEMTRACK. This work provides an extensible framework for advancing evaluation research for memory-augmented agents, beyond existing focus on conversational setups, and sets the stage for multi-agent, multi-platform memory benchmarking in complex organizational settings</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.01353</guid>
|
||||
<pubDate>Wed, 01 Oct 2025 18:34:03 +0000</pubDate>
|
||||
<title>AlphaApollo: Orchestrating Foundation Models and Professional Tools into a Self-Evolving System for Deep Agentic Reasoning</title>
|
||||
<link>https://arxiv.org/abs/2510.06261</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.06261.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhanke Zhou, Chentao Cao, Xiao Feng, Xuan Li, Zongze Li, Xiangyu Lu, Jiangchao Yao, Weikai Huang, Linrui Xu, Tian Cheng, Guanyu Jiang, Yiming Zheng, Brando Miranda, Tongliang Liu, Sanmi Koyejo, Masashi Sugiyama, Bo Han</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> We present AlphaApollo, a self-evolving agentic reasoning system that aims to address two bottlenecks in foundation model (FM) reasoning-limited model-intrinsic capacity and unreliable test-time iteration. AlphaApollo orchestrates multiple models with professional tools to enable deliberate, verifiable reasoning. It couples (i) a computation tool (Python with numerical and symbolic libraries) and (ii) a retrieval tool (task-relevant external information) to execute exact calculations and ground decisions. The system further supports multi-round, multi-model solution evolution via a shared state map that records candidates, executable checks, and feedback for iterative refinement. In evaluations on AIME 2024/2025 across multiple models, AlphaApollo delivers consistent gains: +5.15% Average@32 and +23.34% Pass@32 for Qwen2.5-14B-Instruct, and +8.91% Average@32 with +26.67% Pass@32 for Llama-3.3-70B-Instruct. Tool-use analysis shows that more than 80% of tool calls are successfully executed, with consistent outperformance of non-tool baselines, thereby lifting the capability ceiling of FMs. More empirical results and implementation details will be updated at https://github.com/tmlr-group/AlphaApollo.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.06261</guid>
|
||||
<pubDate>Sun, 05 Oct 2025 15:42:24 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Equilibrium Matching: Generative Modeling with Implicit Energy-Based Models</title>
|
||||
<link>https://arxiv.org/abs/2510.02300</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.02300.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Runqian Wang, Yilun Du</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> We introduce Equilibrium Matching (EqM), a generative modeling framework built from an equilibrium dynamics perspective. EqM discards the non-equilibrium, time-conditional dynamics in traditional diffusion and flow-based generative models and instead learns the equilibrium gradient of an implicit energy landscape. Through this approach, we can adopt an optimization-based sampling process at inference time, where samples are obtained by gradient descent on the learned landscape with adjustable step sizes, adaptive optimizers, and adaptive compute. EqM surpasses the generation performance of diffusion/flow models empirically, achieving an FID of 1.90 on ImageNet 256times256. EqM is also theoretically justified to learn and sample from the data manifold. Beyond generation, EqM is a flexible framework that naturally handles tasks including partially noised image denoising, OOD detection, and image composition. By replacing time-conditional velocities with a unified equilibrium landscape, EqM offers a tighter bridge between flow and energy-based models and a simple route to optimization-driven inference.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.02300</guid>
|
||||
<pubDate>Thu, 02 Oct 2025 17:59:06 +0000</pubDate>
|
||||
<title>Multi-Agent Tool-Integrated Policy Optimization</title>
|
||||
<link>https://arxiv.org/abs/2510.04678</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.04678.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhanfeng Mo, Xingxuan Li, Yuntao Chen, Lidong Bing</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> Large language models (LLMs) increasingly rely on multi-turn tool-integrated planning for knowledge-intensive and complex reasoning tasks. Existing implementations typically rely on a single agent, but they suffer from limited context length and noisy tool responses. A natural solution is to adopt a multi-agent framework with planner- and worker-agents to manage context. However, no existing methods support effective reinforcement learning post-training of tool-integrated multi-agent frameworks. To address this gap, we propose Multi-Agent Tool-Integrated Policy Optimization (MATPO), which enables distinct roles (planner and worker) to be trained within a single LLM instance using role-specific prompts via reinforcement learning. MATPO is derived from a principled credit assignment mechanism across planner and worker rollouts. This design eliminates the need to deploy multiple LLMs, which would be memory-intensive, while preserving the benefits of specialization. Experiments on GAIA-text, WebWalkerQA, and FRAMES show that MATPO consistently outperforms single-agent baselines by an average of 18.38% relative improvement in performance and exhibits greater robustness to noisy tool outputs. Our findings highlight the effectiveness of unifying multiple agent roles within a single LLM and provide practical insights for stable and efficient multi-agent RL training.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.04678</guid>
|
||||
<pubDate>Mon, 06 Oct 2025 10:44:04 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>VeriGuard: Enhancing LLM Agent Safety via Verified Code Generation</title>
|
||||
<link>https://arxiv.org/abs/2510.05156</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.05156.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lesly Miculicich, Mihir Parmar, Hamid Palangi, Krishnamurthy Dj Dvijotham, Mirko Montanari, Tomas Pfister, Long T. Le</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> The deployment of autonomous AI agents in sensitive domains, such as healthcare, introduces critical risks to safety, security, and privacy. These agents may deviate from user objectives, violate data handling policies, or be compromised by adversarial attacks. Mitigating these dangers necessitates a mechanism to formally guarantee that an agent's actions adhere to predefined safety constraints, a challenge that existing systems do not fully address. We introduce VeriGuard, a novel framework that provides formal safety guarantees for LLM-based agents through a dual-stage architecture designed for robust and verifiable correctness. The initial offline stage involves a comprehensive validation process. It begins by clarifying user intent to establish precise safety specifications. VeriGuard then synthesizes a behavioral policy and subjects it to both testing and formal verification to prove its compliance with these specifications. This iterative process refines the policy until it is deemed correct. Subsequently, the second stage provides online action monitoring, where VeriGuard operates as a runtime monitor to validate each proposed agent action against the pre-verified policy before execution. This separation of the exhaustive offline validation from the lightweight online monitoring allows formal guarantees to be practically applied, providing a robust safeguard that substantially improves the trustworthiness of LLM agents.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.05156</guid>
|
||||
<pubDate>Fri, 03 Oct 2025 04:11:43 +0000</pubDate>
|
||||
<title>Glocal Information Bottleneck for Time Series Imputation</title>
|
||||
<link>https://arxiv.org/abs/2510.04910</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.04910.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jie Yang, Kexin Zhang, Guibin Zhang, Philip S. Yu, Kaize Ding</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Time Series Imputation (TSI), which aims to recover missing values in temporal data, remains a fundamental challenge due to the complex and often high-rate missingness in real-world scenarios. Existing models typically optimize the point-wise reconstruction loss, focusing on recovering numerical values (local information). However, we observe that under high missing rates, these models still perform well in the training phase yet produce poor imputations and distorted latent representation distributions (global information) in the inference phase. This reveals a critical optimization dilemma: current objectives lack global guidance, leading models to overfit local noise and fail to capture global information of the data. To address this issue, we propose a new training paradigm, Glocal Information Bottleneck (Glocal-IB). Glocal-IB is model-agnostic and extends the standard IB framework by introducing a Global Alignment loss, derived from a tractable mutual information approximation. This loss aligns the latent representations of masked inputs with those of their originally observed counterparts. It helps the model retain global structure and local details while suppressing noise caused by missing values, giving rise to better generalization under high missingness. Extensive experiments on nine datasets confirm that Glocal-IB leads to consistently improved performance and aligned latent representations under missingness. Our code implementation is available in https://github.com/Muyiiiii/NeurIPS-25-Glocal-IB.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.04910</guid>
|
||||
<pubDate>Mon, 06 Oct 2025 15:24:44 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>OneFlow: Concurrent Mixed-Modal and Interleaved Generation with Edit Flows</title>
|
||||
<link>https://arxiv.org/abs/2510.03506</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.03506.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> John Nguyen, Marton Havasi, Tariq Berrada, Luke Zettlemoyer, Ricky T. Q. Chen</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> We present OneFlow, the first non-autoregressive multimodal model that enables variable-length and concurrent mixed-modal generation. Unlike autoregressive models that enforce rigid causal ordering between text and image generation, OneFlow combines an insertion-based Edit Flow for discrete text tokens with Flow Matching for image latents. OneFlow enables concurrent text-image synthesis with hierarchical sampling that prioritizes content over grammar. Through controlled experiments across model sizes from 1B to 8B, we demonstrate that OneFlow outperforms autoregressive baselines on both generation and understanding tasks while using up to 50% fewer training FLOPs. OneFlow surpasses both autoregressive and diffusion-based approaches while unlocking new capabilities for concurrent generation, iterative refinement, and natural reasoning-like generation.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.03506</guid>
|
||||
<pubDate>Fri, 03 Oct 2025 20:40:30 +0000</pubDate>
|
||||
<title>Bridging Text and Video Generation: A Survey</title>
|
||||
<link>https://arxiv.org/abs/2510.04999</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.04999.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Nilay Kumar, Priyansh Bhandari, G. Maragatham</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Text-to-video (T2V) generation technology holds potential to transform multiple domains such as education, marketing, entertainment, and assistive technologies for individuals with visual or reading comprehension challenges, by creating coherent visual content from natural language prompts. From its inception, the field has advanced from adversarial models to diffusion-based models, yielding higher-fidelity, temporally consistent outputs. Yet challenges persist, such as alignment, long-range coherence, and computational efficiency. Addressing this evolving landscape, we present a comprehensive survey of text-to-video generative models, tracing their development from early GANs and VAEs to hybrid Diffusion-Transformer (DiT) architectures, detailing how these models work, what limitations they addressed in their predecessors, and why shifts toward new architectural paradigms were necessary to overcome challenges in quality, coherence, and control. We provide a systematic account of the datasets, which the surveyed text-to-video models were trained and evaluated on, and, to support reproducibility and assess the accessibility of training such models, we detail their training configurations, including their hardware specifications, GPU counts, batch sizes, learning rates, optimizers, epochs, and other key hyperparameters. Further, we outline the evaluation metrics commonly used for evaluating such models and present their performance across standard benchmarks, while also discussing the limitations of these metrics and the emerging shift toward more holistic, perception-aligned evaluation strategies. Finally, drawing from our analysis, we outline the current open challenges and propose a few promising future directions, laying out a perspective for future researchers to explore and build upon in advancing T2V research and applications.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.04999</guid>
|
||||
<pubDate>Mon, 06 Oct 2025 16:39:05 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>No Tokens Wasted: Leveraging Long Context in Biomedical Vision-Language Models</title>
|
||||
<link>https://arxiv.org/abs/2510.03978</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.03978.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Min Woo Sun, Alejandro Lozano, Javier Gamazo Tejero, Vishwesh Nath, Xiao Xiao Sun, James Burgess, Yuhui Zhang, Kun Yuan, Robert Tibshirani, Sean Huver, Serena Yeung-Levy</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Embedding vision-language models (VLMs) are typically pretrained with short text windows (<77 tokens), which forces the truncation of long-format captions. Yet, the distribution of biomedical captions from large-scale open source literature reveals that a huge portion of captions far exceed 77 tokens. To this end, we investigate the impact of pretraining on long-format biomedical captions by extending the context length of text encoders in VLMs. We find that longer context (thus, enabling additional supervision provided in long-format captions) correlates with better retrieval and classification performance. Given this finding, we introduce BIOMEDICA-LongCAP, a dataset of 1M image-caption pairs enriched with context-aware descriptions from full-text articles, providing longer and additional textual supervision. Using BIOMEDICA-LongCAP, we train BMC-LongCLIP, a long-context biomedical VLM with a text encoder supporting windows of up to 512 tokens. Our model extends context capacity by 6.6x, reducing token waste from 55% to just 2.2%. On long-caption retrieval benchmarks, BMC-LongCLIP achieves up to +30% absolute gains in Recall@1 and +2% average improvements in classification, while also converging faster than short-context. Our results demonstrate that long-context modeling is a promising direction for advancing biomedical VLMs.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.03978</guid>
|
||||
<pubDate>Sat, 04 Oct 2025 23:38:18 +0000</pubDate>
|
||||
<title>StaMo: Unsupervised Learning of Generalizable Robot Motion from Compact State Representation</title>
|
||||
<link>https://arxiv.org/abs/2510.05057</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.05057.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mingyu Liu, Jiuhe Shu, Hui Chen, Zeju Li, Canyu Zhao, Jiange Yang, Shenyuan Gao, Hao Chen, Chunhua Shen</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> A fundamental challenge in embodied intelligence is developing expressive and compact state representations for efficient world modeling and decision making. However, existing methods often fail to achieve this balance, yielding representations that are either overly redundant or lacking in task-critical information. We propose an unsupervised approach that learns a highly compressed two-token state representation using a lightweight encoder and a pre-trained Diffusion Transformer (DiT) decoder, capitalizing on its strong generative prior. Our representation is efficient, interpretable, and integrates seamlessly into existing VLA-based models, improving performance by 14.3% on LIBERO and 30% in real-world task success with minimal inference overhead. More importantly, we find that the difference between these tokens, obtained via latent interpolation, naturally serves as a highly effective latent action, which can be further decoded into executable robot actions. This emergent capability reveals that our representation captures structured dynamics without explicit supervision. We name our method StaMo for its ability to learn generalizable robotic Motion from compact State representation, which is encoded from static images, challenging the prevalent dependence to learning latent action on complex architectures and video data. The resulting latent actions also enhance policy co-training, outperforming prior methods by 10.4% with improved interpretability. Moreover, our approach scales effectively across diverse data sources, including real-world robot data, simulation, and human egocentric video.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.05057</guid>
|
||||
<pubDate>Mon, 06 Oct 2025 17:37:24 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Scaling Code-Assisted Chain-of-Thoughts and Instructions for Model Reasoning</title>
|
||||
<link>https://arxiv.org/abs/2510.04081</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.04081.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Honglin Lin, Qizhi Pei, Xin Gao, Zhuoshi Pan, Yu Li, Juntao Li, Conghui He, Lijun Wu</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> Reasoning capability is pivotal for Large Language Models (LLMs) to solve complex tasks, yet achieving reliable and scalable reasoning remains challenging. While Chain-of-Thought (CoT) prompting has become a mainstream approach, existing methods often suffer from uncontrolled generation, insufficient quality, and limited diversity in reasoning paths. Recent efforts leverage code to enhance CoT by grounding reasoning in executable steps, but such methods are typically constrained to predefined mathematical problems, hindering scalability and generalizability. In this work, we propose Caco (Code-Assisted Chain-of-ThOught), a novel framework that automates the synthesis of high-quality, verifiable, and diverse instruction-CoT reasoning data through code-driven augmentation. Unlike prior work, Caco first fine-tunes a code-based CoT generator on existing math and programming solutions in a unified code format, then scales the data generation to a large amount of diverse reasoning traces. Crucially, we introduce automated validation via code execution and rule-based filtering to ensure logical correctness and structural diversity, followed by reverse-engineering filtered outputs into natural language instructions and language CoTs to enrich task adaptability. This closed-loop process enables fully automated, scalable synthesis of reasoning data with guaranteed executability. Experiments on our created Caco-1.3M dataset demonstrate that Caco-trained models achieve strong competitive performance on mathematical reasoning benchmarks, outperforming existing strong baselines. Further analysis reveals that Caco's code-anchored verification and instruction diversity contribute to superior generalization across unseen tasks. Our work establishes a paradigm for building self-sustaining, trustworthy reasoning systems without human intervention.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.04081</guid>
|
||||
<pubDate>Sun, 05 Oct 2025 07:59:24 +0000</pubDate>
|
||||
<title>NorMuon: Making Muon more efficient and scalable</title>
|
||||
<link>https://arxiv.org/abs/2510.05491</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.05491.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zichong Li, Liming Liu, Chen Liang, Weizhu Chen, Tuo Zhao</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> The choice of optimizer significantly impacts the training efficiency and computational costs of large language models (LLMs). Recently, the Muon optimizer has demonstrated promising results by orthogonalizing parameter updates, improving optimization geometry through better conditioning. Despite Muon's emergence as a candidate successor to Adam, the potential for jointly leveraging their strengths has not been systematically explored. In this work, we bridge this gap by proposing NorMuon (Neuron-wise Normalized Muon), an optimizer that synergistically combines orthogonalization with neuron-level adaptive learning rates. Our analysis reveals that while Muon effectively reduces condition numbers, the resulting updates exhibit highly non-uniform neuron norms, causing certain neurons to dominate the optimization process. NorMuon addresses this imbalance by maintaining second-order momentum statistics for each neuron and applying row-wise normalization after orthogonalization, ensuring balanced parameter utilization while preserving Muon's conditioning benefits. To enable practical deployment at scale, we develop an efficient distributed implementation under the FSDP2 framework that strategically distributes orthogonalization computations across devices. Experiments across multiple model scales demonstrate that NorMuon consistently outperforms both Adam and Muon, achieving 21.74% better training efficiency than Adam and 11.31% improvement over Muon on 1.1 B pretraining setting, while maintaining a comparable memory footprint to Muon. Our findings suggest that orthogonalization and adaptive learning rates are complementary rather than competing approaches, opening new avenues for optimizer design in large-scale deep learning.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.05491</guid>
|
||||
<pubDate>Tue, 07 Oct 2025 01:13:41 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>A Contextual Quality Reward Model for Reliable and Efficient Best-of-N Sampling</title>
|
||||
<link>https://arxiv.org/abs/2510.04087</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.04087.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hyung Gyu Rho</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Modern preference alignment techniques, such as Best-of-N (BoN) sampling, rely on reward models trained with pairwise comparison data. While effective at learning relative preferences, this paradigm fails to capture a signal of response acceptability, leaving systems vulnerable to selecting the least bad of many unacceptable options. This is particularly problematic for hard prompts, where the risk of such false acceptances increases with the number of samples. In this paper, we address this critical reliability gap by introducing a new data collection and modeling framework. By augmenting preference data with an outside option, inspired by discrete choice models, we train a reward model that can distinguish not just what is better, but what is good enough. We leverage this capability to create an adaptive inference strategy, best of mini-N in-loop, which partitions the generation budget into sequential loops with a calibrated, early-exit condition. Our experiments show that when tuned as an alignment guardrail, it reduces reliability failures by 70\%, and when tuned as an inference accelerator, it improves average inference speed by over 22\% in IMDB-sentiment setting. We thus provide a principled and flexible framework for practitioners to explicitly manage the trade-off between reliability and computational efficiency.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.04087</guid>
|
||||
<pubDate>Sun, 05 Oct 2025 08:23:08 +0000</pubDate>
|
||||
<title>The African Languages Lab: A Collaborative Approach to Advancing Low-Resource African NLP</title>
|
||||
<link>https://arxiv.org/abs/2510.05644</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.05644.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sheriff Issaka, Keyi Wang, Yinka Ajibola, Oluwatumininu Samuel-Ipaye, Zhaoyi Zhang, Nicte Aguillon Jimenez, Evans Kofi Agyei, Abraham Lin, Rohan Ramachandran, Sadick Abdul Mumin, Faith Nchifor, Mohammed Shuraim, Lieqi Liu, Erick Rosas Gonzalez, Sylvester Kpei, Jemimah Osei, Carlene Ajeneza, Persis Boateng, Prisca Adwoa Dufie Yeboah, Saadia Gabriel</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Despite representing nearly one-third of the world's languages, African languages remain critically underserved by modern NLP technologies, with 88\% classified as severely underrepresented or completely ignored in computational linguistics. We present the African Languages Lab (All Lab), a comprehensive research initiative that addresses this technological gap through systematic data collection, model development, and capacity building. Our contributions include: (1) a quality-controlled data collection pipeline, yielding the largest validated African multi-modal speech and text dataset spanning 40 languages with 19 billion tokens of monolingual text and 12,628 hours of aligned speech data; (2) extensive experimental validation demonstrating that our dataset, combined with fine-tuning, achieves substantial improvements over baseline models, averaging +23.69 ChrF++, +0.33 COMET, and +15.34 BLEU points across 31 evaluated languages; and (3) a structured research program that has successfully mentored fifteen early-career researchers, establishing sustainable local capacity. Our comparative evaluation against Google Translate reveals competitive performance in several languages while identifying areas that require continued development.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.05644</guid>
|
||||
<pubDate>Tue, 07 Oct 2025 07:42:52 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Drax: Speech Recognition with Discrete Flow Matching</title>
|
||||
<link>https://arxiv.org/abs/2510.04162</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.04162.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Aviv Navon, Aviv Shamsian, Neta Glazer, Yael Segal-Feldman, Gill Hetz, Joseph Keshet, Ethan Fetaya</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> Diffusion and flow-based non-autoregressive (NAR) models have shown strong promise in large language modeling, however, their potential for automatic speech recognition (ASR) remains largely unexplored. We propose Drax, a discrete flow matching framework for ASR that enables efficient parallel decoding. To better align training with inference, we construct an audio-conditioned probability path that guides the model through trajectories resembling likely intermediate inference errors, rather than direct random noise to target transitions. Our theoretical analysis links the generalization gap to divergences between training and inference occupancies, controlled by cumulative velocity errors, thereby motivating our design choice. Empirical evaluation demonstrates that our approach attains recognition accuracy on par with state-of-the-art speech models while offering improved accuracy-efficiency trade-offs, highlighting discrete flow matching as a promising direction for advancing NAR ASR.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.04162</guid>
|
||||
<pubDate>Sun, 05 Oct 2025 11:38:01 +0000</pubDate>
|
||||
<title>Revisiting Long-context Modeling from Context Denoising Perspective</title>
|
||||
<link>https://arxiv.org/abs/2510.05862</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.05862.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zecheng Tang, Baibei Ji, Juntao Li, Lijun Wu, Haijia Gui, Min Zhang</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Long-context models (LCMs) have demonstrated great potential in processing long sequences, facilitating many real-world applications. The success of LCMs can be attributed to their ability to locate implicit critical information within the context for further prediction. However, recent research reveals that LCMs are often susceptible to contextual noise, i.e., irrelevant tokens, that can mislead model attention. In this paper, we conduct a fine-grained analysis of the context noise and propose an effective metric, the Integrated Gradient (IG) score, to detect and quantify the noise information within the context. Our findings reveal that even simple mitigation of detected context noise can substantially boost the model's attention on critical tokens and benefit subsequent predictions. Building on this insight, we propose Context Denoising Training (CDT), a straightforward yet effective training strategy that improves attention on critical tokens while reinforcing their influence on model predictions. Extensive experiments across four tasks, under both context window scaling and long-context alignment settings, demonstrate the superiority of CDT. Notably, when trained with CDT, an open-source 8B model can achieve performance (50.92) comparable to GPT-4o (51.00).</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.05862</guid>
|
||||
<pubDate>Tue, 07 Oct 2025 12:32:23 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>GRACE: Generative Representation Learning via Contrastive Policy Optimization</title>
|
||||
<link>https://arxiv.org/abs/2510.04506</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.04506.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiashuo Sun, Shixuan Liu, Zhaochen Su, Xianrui Zhong, Pengcheng Jiang, Bowen Jin, Peiran Li, Weijia Shi, Jiawei Han</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Prevailing methods for training Large Language Models (LLMs) as text encoders rely on contrastive losses that treat the model as a black box function, discarding its generative and reasoning capabilities in favor of static embeddings. We introduce GRACE (Generative Representation Learning via Contrastive Policy Optimization), a novel framework that reimagines contrastive signals not as losses to be minimized, but as rewards that guide a generative policy. In GRACE, the LLM acts as a policy that produces explicit, human-interpretable rationales--structured natural language explanations of its semantic understanding. These rationales are then encoded into high-quality embeddings via mean pooling. Using policy gradient optimization, we train the model with a multi-component reward function that maximizes similarity between query positive pairs and minimizes similarity with negatives. This transforms the LLM from an opaque encoder into an interpretable agent whose reasoning process is transparent and inspectable. On MTEB benchmark, GRACE yields broad cross category gains: averaged over four backbones, the supervised setting improves overall score by 11.5% over base models, and the unsupervised variant adds 6.9%, while preserving general capabilities. This work treats contrastive objectives as rewards over rationales, unifying representation learning with generation to produce stronger embeddings and transparent rationales. The model, data and code are available at https://github.com/GasolSun36/GRACE.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.04506</guid>
|
||||
<pubDate>Mon, 06 Oct 2025 05:46:56 +0000</pubDate>
|
||||
<title>D^3QE: Learning Discrete Distribution Discrepancy-aware Quantization Error for Autoregressive-Generated Image Detection</title>
|
||||
<link>https://arxiv.org/abs/2510.05891</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.05891.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yanran Zhang, Bingyao Yu, Yu Zheng, Wenzhao Zheng, Yueqi Duan, Lei Chen, Jie Zhou, Jiwen Lu</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> The emergence of visual autoregressive (AR) models has revolutionized image generation while presenting new challenges for synthetic image detection. Unlike previous GAN or diffusion-based methods, AR models generate images through discrete token prediction, exhibiting both marked improvements in image synthesis quality and unique characteristics in their vector-quantized representations. In this paper, we propose to leverage Discrete Distribution Discrepancy-aware Quantization Error (D^3QE) for autoregressive-generated image detection that exploits the distinctive patterns and the frequency distribution bias of the codebook existing in real and fake images. We introduce a discrete distribution discrepancy-aware transformer that integrates dynamic codebook frequency statistics into its attention mechanism, fusing semantic features and quantization error latent. To evaluate our method, we construct a comprehensive dataset termed ARForensics covering 7 mainstream visual AR models. Experiments demonstrate superior detection accuracy and strong generalization of D^3QE across different AR models, with robustness to real-world perturbations. Code is available at https://github.com/Zhangyr2022/D3QE{https://github.com/Zhangyr2022/D3QE}.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.05891</guid>
|
||||
<pubDate>Tue, 07 Oct 2025 13:02:27 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>ChartAgent: A Multimodal Agent for Visually Grounded Reasoning in Complex Chart Question Answering</title>
|
||||
<link>https://arxiv.org/abs/2510.04514</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.04514.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Rachneet Kaur, Nishan Srishankar, Zhen Zeng, Sumitra Ganesh, Manuela Veloso</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Recent multimodal LLMs have shown promise in chart-based visual question answering, but their performance declines sharply on unannotated charts, those requiring precise visual interpretation rather than relying on textual shortcuts. To address this, we introduce ChartAgent, a novel agentic framework that explicitly performs visual reasoning directly within the chart's spatial domain. Unlike textual chain-of-thought reasoning, ChartAgent iteratively decomposes queries into visual subtasks and actively manipulates and interacts with chart images through specialized actions such as drawing annotations, cropping regions (e.g., segmenting pie slices, isolating bars), and localizing axes, using a library of chart-specific vision tools to fulfill each subtask. This iterative reasoning process closely mirrors human cognitive strategies for chart comprehension. ChartAgent achieves state-of-the-art accuracy on the ChartBench and ChartX benchmarks, surpassing prior methods by up to 16.07% absolute gain overall and 17.31% on unannotated, numerically intensive queries. Furthermore, our analyses show that ChartAgent is (a) effective across diverse chart types, (b) achieve the highest scores across varying visual and reasoning complexity levels, and (c) serves as a plug-and-play framework that boosts performance across diverse underlying LLMs. Our work is among the first to demonstrate visually grounded reasoning for chart understanding using tool-augmented multimodal agents.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.04514</guid>
|
||||
<pubDate>Mon, 06 Oct 2025 06:05:36 +0000</pubDate>
|
||||
<title>Lumina-DiMOO: An Omni Diffusion Large Language Model for Multi-Modal Generation and Understanding</title>
|
||||
<link>https://arxiv.org/abs/2510.06308</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.06308.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yi Xin, Qi Qin, Siqi Luo, Kaiwen Zhu, Juncheng Yan, Yan Tai, Jiayi Lei, Yuewen Cao, Keqi Wang, Yibin Wang, Jinbin Bai, Qian Yu, Dengyang Jiang, Yuandong Pu, Haoxing Chen, Le Zhuo, Junjun He, Gen Luo, Tianbin Li, Ming Hu, Jin Ye, Shenglong Ye, Bo Zhang, Chang Xu, Wenhai Wang, Hongsheng Li, Guangtao Zhai, Tianfan Xue, Bin Fu, Xiaohong Liu, Yu Qiao, Yihao Liu</p><p><b>Upvotes:</b> 39</p><p><b>Summary:</b> We introduce Lumina-DiMOO, an open-source foundational model for seamless multi-modal generation and understanding. Lumina-DiMOO sets itself apart from prior unified models by utilizing a fully discrete diffusion modeling to handle inputs and outputs across various modalities. This innovative approach allows Lumina-DiMOO to achieve higher sampling efficiency compared to previous autoregressive (AR) or hybrid AR-Diffusion paradigms and adeptly support a broad spectrum of multi-modal tasks, including text-to-image generation, image-to-image generation (e.g., image editing, subject-driven generation, and image inpainting, etc.), as well as image understanding. Lumina-DiMOO achieves state-of-the-art performance on multiple benchmarks, surpassing existing open-source unified multi-modal models. To foster further advancements in multi-modal and discrete diffusion model research, we release our code and checkpoints to the community. Project Page: https://synbol.github.io/Lumina-DiMOO.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.06308</guid>
|
||||
<pubDate>Tue, 07 Oct 2025 17:59:20 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Less is More: Recursive Reasoning with Tiny Networks</title>
|
||||
<link>https://arxiv.org/abs/2510.04871</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.04871.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Alexia Jolicoeur-Martineau</p><p><b>Upvotes:</b> 76</p><p><b>Summary:</b> Hierarchical Reasoning Model (HRM) is a novel approach using two small neural networks recursing at different frequencies. This biologically inspired method beats Large Language models (LLMs) on hard puzzle tasks such as Sudoku, Maze, and ARC-AGI while trained with small models (27M parameters) on small data (around 1000 examples). HRM holds great promise for solving hard problems with small networks, but it is not yet well understood and may be suboptimal. We propose Tiny Recursive Model (TRM), a much simpler recursive reasoning approach that achieves significantly higher generalization than HRM, while using a single tiny network with only 2 layers. With only 7M parameters, TRM obtains 45% test-accuracy on ARC-AGI-1 and 8% on ARC-AGI-2, higher than most LLMs (e.g., Deepseek R1, o3-mini, Gemini 2.5 Pro) with less than 0.01% of the parameters.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.04871</guid>
|
||||
<pubDate>Mon, 06 Oct 2025 14:58:08 +0000</pubDate>
|
||||
<title>FinLFQA: Evaluating Attributed Text Generation of LLMs in Financial Long-Form Question Answering</title>
|
||||
<link>https://arxiv.org/abs/2510.06426</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.06426.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yitao Long, Tiansheng Hu, Yilun Zhao, Arman Cohan, Chen Zhao</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Large Language Models (LLMs) frequently hallucinate to long-form questions, producing plausible yet factually incorrect answers. A common mitigation strategy is to provide attribution to LLM outputs. However, existing benchmarks primarily focus on simple attribution that retrieves supporting textual evidence as references. We argue that in real-world scenarios such as financial applications, attribution goes beyond reference retrieval. We introduce FinLFQA, a benchmark designed to evaluate the ability of LLMs to generate long-form answers to complex financial questions with reliable and nuanced attributions. FinLFQA evaluates three critical aspects of attribution through human annotations: (1) supporting evidence extracted from financial reports, (2) intermediate numerical reasoning steps, and (3) domain-specific financial knowledge that informs the reasoning process. We further provide an automatic evaluation framework covering both answer quality and attribution quality. Through extensive experiments on eight LLMs across multiple attribution-generation paradigms, we find that fine-grained metrics are important to distinguish model capabilities, that end-to-end generation achieves comparable performance to post-hoc approaches, and that iterative refinement only helps when guided by external feedback.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.06426</guid>
|
||||
<pubDate>Tue, 07 Oct 2025 20:06:15 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Let it Calm: Exploratory Annealed Decoding for Verifiable Reinforcement Learning</title>
|
||||
<link>https://arxiv.org/abs/2510.05251</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.05251.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chenghao Yang, Lin Gui, Chenxiao Yang, Victor Veitch, Lizhu Zhang, Zhuokai Zhao</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Reinforcement learning with verifiable rewards (RLVR) is a powerful paradigm for enhancing the reasoning capabilities of large language models (LLMs), yet its success hinges on effective exploration. An ideal exploration strategy must navigate two fundamental challenges: it must preserve sample quality while also ensuring training stability. While standard fixed-temperature sampling is simple, it struggles to balance these competing demands, as high temperatures degrade sample quality and low temperatures limit discovery. In this work, we propose a simpler and more effective strategy, Exploratory Annealed Decoding (EAD), grounded in the insight that exploration is most impactful on early tokens which define a sequence's semantic direction. EAD implements an intuitive **explore-at-the-beginning, exploit-at-the-end** strategy by annealing the sampling temperature from high to low during generation. This dynamic schedule encourages meaningful, high-level diversity at the start, then gradually lowers the temperature to preserve sample quality and keep the sampling distribution close to the target policy, which is essential for stable training. We demonstrate that EAD is a lightweight, plug-and-play method that significantly improves sample efficiency, consistently outperforming fixed-temperature sampling across various RLVR algorithms and model sizes. Our work suggests that aligning exploration with the natural dynamics of sequential generation offers a robust path to improving LLM reasoning.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.05251</guid>
|
||||
<pubDate>Mon, 06 Oct 2025 18:15:43 +0000</pubDate>
|
||||
<title>PuzzlePlex: Benchmarking Foundation Models on Reasoning and Planning with Puzzles</title>
|
||||
<link>https://arxiv.org/abs/2510.06475</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.06475.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yitao Long, Yuru Jiang, Hongjun Liu, Yilun Zhao, Jingchen Sun, Yiqiu Shen, Chen Zhao, Arman Cohan, Dennis Shasha</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> This work investigates the reasoning and planning capabilities of foundation models and their scalability in complex, dynamic environments. We introduce PuzzlePlex, a benchmark designed to assess these capabilities through a diverse set of puzzles. PuzzlePlex consists of 15 types of puzzles, including deterministic and stochastic games of varying difficulty, as well as single-player and two-player scenarios. The PuzzlePlex framework provides a comprehensive environment for each game, and supports extensibility to generate more challenging instances as foundation models evolve. Additionally, we implement customized game-playing strategies for comparison. Building on this benchmark, we develop fine-grained metrics to measure performance and conduct an in-depth analysis of frontier foundation models across two settings: instruction-based and code-based. Furthermore, we systematically investigate their scaling limits. Our findings show that reasoning models outperform others in instruction-based settings, while code-based execution presents greater challenges but offers a scalable and efficient alternative. PuzzlePlex enables targeted evaluation and guides future improvements in reasoning, planning, and generalization for foundation models.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.06475</guid>
|
||||
<pubDate>Tue, 07 Oct 2025 21:24:29 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>BIRD-INTERACT: Re-imagining Text-to-SQL Evaluation for Large Language Models via Lens of Dynamic Interactions</title>
|
||||
<link>https://arxiv.org/abs/2510.05318</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.05318.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Nan Huo, Xiaohan Xu, Jinyang Li, Per Jacobsson, Shipei Lin, Bowen Qin, Binyuan Hui, Xiaolong Li, Ge Qu, Shuzheng Si, Linheng Han, Edward Alexander, Xintong Zhu, Rui Qin, Ruihan Yu, Yiyao Jin, Feige Zhou, Weihao Zhong, Yun Chen, Hongyu Liu, Chenhao Ma, Fatma Ozcan, Yannis Papakonstantinou, Reynold Cheng</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Large language models (LLMs) have demonstrated remarkable performance on single-turn text-to-SQL tasks, but real-world database applications predominantly require multi-turn interactions to handle ambiguous queries, execution errors, and evolving user requirements. Existing multi-turn benchmarks fall short by treating conversation histories as static context or limiting evaluation to read-only operations, failing to reflect production-grade database assistant challenges. We introduce BIRD-INTERACT, a benchmark that restores this realism through: (1) a comprehensive interaction environment coupling each database with a hierarchical knowledge base, metadata files, and a function-driven user simulator, enabling models to solicit clarifications, retrieve knowledge, and recover from errors without human supervision; (2) two evaluation settings consisting of a pre-defined conversational protocol (c-Interact) and an open-ended agentic setting (a-Interact) where models autonomously decide when to query the user simulator or explore the environment; (3) a challenging task suite covering the full CRUD spectrum for business-intelligence and operational use cases, guarded by executable test cases. Each task features ambiguous and follow-up sub-tasks requiring dynamic interaction. The suite comprises BIRD-INTERACT-FULL (600 tasks, up to 11,796 interactions) for comprehensive performance assessment, and BIRD-INTERACT-LITE (300 tasks with simplified databases) for detailed behavioral analysis and rapid method development. Our empirical results highlight BIRD-INTERACT's difficulty: GPT-5 completes only 8.67% of tasks in c-Interact and 17.00% in a-Interact. Analysis via memory grafting and Interaction Test-time Scaling validates the importance of effective interaction for complex, dynamic text-to-SQL tasks.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.05318</guid>
|
||||
<pubDate>Mon, 06 Oct 2025 19:31:47 +0000</pubDate>
|
||||
<title>The Markovian Thinker</title>
|
||||
<link>https://arxiv.org/abs/2510.06557</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.06557.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Milad Aghajohari, Kamran Chitsaz, Amirhossein Kazemnejad, Sarath Chandar, Alessandro Sordoni, Aaron Courville, Siva Reddy</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Reinforcement learning (RL) has recently become a strong recipe for training reasoning LLMs that produce long chains of thought (LongCoT). Yet the standard RL "thinking environment", where the state is the prompt plus all prior reasoning tokens, makes the state unbounded and forces attention-based policies to pay quadratic compute as thoughts lengthen. We revisit the environment itself. We propose Markovian Thinking, a paradigm in which the policy advances reasoning while conditioning on a constant-size state, decoupling thinking length from context size. As an immediate consequence this yields linear compute with constant memory. We instantiate this idea with Delethink, an RL environment that structures reasoning into fixed-size chunks. Within each chunk, the model thinks as usual; at the boundary, the environment resets the context and reinitializes the prompt with a short carryover. Through RL, the policy learns to write a textual state near the end of each chunk sufficient for seamless continuation of reasoning after reset. Trained in this environment, an R1-Distill 1.5B model reasons in 8K-token chunks yet thinks up to 24K tokens, matching or surpassing LongCoT-RL trained with a 24K budget. With test-time scaling, Delethink continues to improve where LongCoT plateaus. The effect of linear compute is substantial: we empirically estimate at 96K average thinking length LongCoT-RL costs 27 H100-months vs. 7 for Delethink. Analysis at RL initialization shows off-the-shelf reasoning models (1.5B-120B) often sample Markovian traces zero-shot across diverse benchmarks, providing positive samples that make RL effective at scale. Our results show that redesigning the thinking environment is a powerful lever: it enables very long reasoning without quadratic overhead and opens a path toward efficient, scalable reasoning LLMs.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.06557</guid>
|
||||
<pubDate>Wed, 08 Oct 2025 01:18:13 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Margin Adaptive DPO: Leveraging Reward Model for Granular Control in Preference Optimization</title>
|
||||
<link>https://arxiv.org/abs/2510.05342</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.05342.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hyung Gyu Rho</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Direct Preference Optimization (DPO) has emerged as a simple and effective method for aligning large language models. However, its reliance on a fixed temperature parameter leads to suboptimal training on diverse preference data, causing overfitting on easy examples and under-learning from informative ones. Recent methods have emerged to counter this. While IPO addresses general overfitting, its uniform regularization can be overly conservative. The more targeted approach of beta-DPO suffers from its own limitations: its batch-level adaptation applies a single, compromised temperature to mixed-margin pairs, its linear update rule can produce unstable negative beta values, and its filtering mechanism discards potentially useful training signals. In this work, we introduce Margin-Adaptive Direct Preference Optimization (MADPO), a method that provides a stable, data-preserving, and instance-level solution. MADPO employs a practical two-step approach: it first trains a reward model to estimate preference margins and then uses these margins to apply a continuous, adaptive weight to the DPO loss for each individual training sample. This re-weighting scheme creates an effective target margin that is amplified for hard pairs and dampened for easy pairs, allowing for granular control over the learning signal. We provide a comprehensive theoretical analysis, proving that MADPO has a well-behaved optimization landscape and is robust to reward model estimation errors. We validate our theory with experiments on a sentiment generation task, where MADPO consistently and significantly outperforms strong baselines across datasets of varying quality. It achieves performance gains of up to +33.3\% on High Quality data and +10.5\% on Low Quality data over the next-best method. Our results establish MADPO as a more robust and principled approach to preference alignment.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.05342</guid>
|
||||
<pubDate>Mon, 06 Oct 2025 20:09:37 +0000</pubDate>
|
||||
<title>Ming-UniVision: Joint Image Understanding and Generation with a Unified Continuous Tokenizer</title>
|
||||
<link>https://arxiv.org/abs/2510.06590</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.06590.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ziyuan Huang, DanDan Zheng, Cheng Zou, Rui Liu, Xiaolong Wang, Kaixiang Ji, Weilong Chai, Jianxin Sun, Libin Wang, Yongjie Lv, Taozhi Huang, Jiajia Liu, Qingpei Guo, Ming Yang, Jingdong Chen, Jun Zhou</p><p><b>Upvotes:</b> 58</p><p><b>Summary:</b> Visual tokenization remains a core challenge in unifying visual understanding and generation within the autoregressive paradigm. Existing methods typically employ tokenizers in discrete latent spaces to align with the tokens from large language models, where the quantization errors can limit semantic expressiveness and degrade the capability of vision-language understanding. To address this, we introduce MingTok, a new family of visual tokenizers with a continuous latent space, for unified autoregressive generation and understanding. While understanding tasks favor discriminative high-dimensional features, generation tasks prefer compact low-level codes. Thus, to reconcile these competing demands, MingTok adopts a three-stage sequential architecture involving low-level encoding, semantic expansion, and visual reconstruction. Built on top of it, Ming-UniVision eliminates the need for task-specific visual representations, and unifies diverse vision-language tasks under a single autoregrsssive prediction paradigm. By formulating both understanding and generation as next-token prediction in a shared continuous space, it seamlessly supports multi-round, in-context tasks such as iterative understanding, generation and editing. Empirically, we find that using a unified continuous visual representation reconciles the competing requirements on the tokenizers by the understanding and generation tasks, thereby leading to state-of-the-art level performance across both domains. We hope our findings will facilitate unified visual tokenization in the continuous domain. Inference code and model weights are released to benefit community.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.06590</guid>
|
||||
<pubDate>Wed, 08 Oct 2025 02:50:14 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>LightCache: Memory-Efficient, Training-Free Acceleration for Video Generation</title>
|
||||
<link>https://arxiv.org/abs/2510.05367</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.05367.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yang Xiao, Gen Li, Kaiyuan Deng, Yushu Wu, Zheng Zhan, Yanzhi Wang, Xiaolong Ma, Bo Hui</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Training-free acceleration has emerged as an advanced research area in video generation based on diffusion models. The redundancy of latents in diffusion model inference provides a natural entry point for acceleration. In this paper, we decompose the inference process into the encoding, denoising, and decoding stages, and observe that cache-based acceleration methods often lead to substantial memory surges in the latter two stages. To address this problem, we analyze the characteristics of inference across different stages and propose stage-specific strategies for reducing memory consumption: 1) Asynchronous Cache Swapping. 2) Feature chunk. 3) Slicing latents to decode. At the same time, we ensure that the time overhead introduced by these three strategies remains lower than the acceleration gains themselves. Compared with the baseline, our approach achieves faster inference speed and lower memory usage, while maintaining quality degradation within an acceptable range. The Code is available at https://github.com/NKUShaw/LightCache .</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.05367</guid>
|
||||
<pubDate>Mon, 06 Oct 2025 20:54:44 +0000</pubDate>
|
||||
<title>Code Agent can be an End-to-end System Hacker: Benchmarking Real-world Threats of Computer-use Agent</title>
|
||||
<link>https://arxiv.org/abs/2510.06607</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.06607.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weidi Luo, Qiming Zhang, Tianyu Lu, Xiaogeng Liu, Bin Hu, Hung-Chun Chiu, Siyuan Ma, Yizhe Zhang, Xusheng Xiao, Yinzhi Cao, Zhen Xiang, Chaowei Xiao</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Computer-use agent (CUA) frameworks, powered by large language models (LLMs) or multimodal LLMs (MLLMs), are rapidly maturing as assistants that can perceive context, reason, and act directly within software environments. Among their most critical applications is operating system (OS) control. As CUAs in the OS domain become increasingly embedded in daily operations, it is imperative to examine their real-world security implications, specifically whether CUAs can be misused to perform realistic, security-relevant attacks. Existing works exhibit four major limitations: Missing attacker-knowledge model on tactics, techniques, and procedures (TTP), Incomplete coverage for end-to-end kill chains, unrealistic environment without multi-host and encrypted user credentials, and unreliable judgment dependent on LLM-as-a-Judge. To address these gaps, we propose AdvCUA, the first benchmark aligned with real-world TTPs in MITRE ATT&CK Enterprise Matrix, which comprises 140 tasks, including 40 direct malicious tasks, 74 TTP-based malicious tasks, and 26 end-to-end kill chains, systematically evaluates CUAs under a realistic enterprise OS security threat in a multi-host environment sandbox by hard-coded evaluation. We evaluate the existing five mainstream CUAs, including ReAct, AutoGPT, Gemini CLI, Cursor CLI, and Cursor IDE based on 8 foundation LLMs. The results demonstrate that current frontier CUAs do not adequately cover OS security-centric threats. These capabilities of CUAs reduce dependence on custom malware and deep domain expertise, enabling even inexperienced attackers to mount complex enterprise intrusions, which raises social concern about the responsibility and security of CUAs.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.06607</guid>
|
||||
<pubDate>Wed, 08 Oct 2025 03:35:23 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Scalable In-context Ranking with Generative Models</title>
|
||||
<link>https://arxiv.org/abs/2510.05396</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.05396.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Nilesh Gupta, Chong You, Srinadh Bhojanapalli, Sanjiv Kumar, Inderjit Dhillon, Felix Yu</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> In-context Ranking (ICR) is an emerging paradigm for Information Retrieval (IR), which leverages contextual understanding of LLMs by directly incorporating the task description, candidate documents, and the query into the model's input prompt and tasking the LLM to identify relevant document(s). While it is effective, efficiency is a significant challenge in this paradigm, especially as the candidate list grows due to quadratic/super-linear scaling of attention operation with context length. To this end, this paper first identifies inherent and exploitable structures in the attention of LLMs finetuned for ICR: (1) inter-document block sparsity: attention is dense within each document block but sparse across different documents in the context; and (2) query-document block relevance: the attention scores from certain query tokens to a document block in middle layers strongly correlate with that document's actual relevance. Motivated by these observations, we introduce BlockRank (Blockwise In-context Ranking), a novel method that adapts the attention operation in an LLM by (a) architecturally enforcing the observed inter-document block sparsity, reducing attention complexity from quadratic to linear without loss in performance, and (b) optimizing query-document block relevance for true relevant documents during fine-tuning using an auxiliary contrastive training objective, improving retrieval in attention. Experiments on BEIR, MSMarco and NQ with Mistral-7B demonstrate that FLARE Mistral matches or outperforms existing SOTA listwise rankers and controlled fine-tuned baseline while being significantly more efficient at inference (4.7x for 100 MSMarco documents in context) and scaling gracefully to long-context shortlists, around 500 documents in-context (approximately 100K context length) within a second, presenting a scalable and effective solution for ICR.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.05396</guid>
|
||||
<pubDate>Mon, 06 Oct 2025 21:41:58 +0000</pubDate>
|
||||
<title>Heptapod: Language Modeling on Visual Signals</title>
|
||||
<link>https://arxiv.org/abs/2510.06673</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.06673.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yongxin Zhu, Jiawei Chen, Yuanzhe Chen, Zhuo Chen, Dongya Jia, Jian Cong, Xiaobin Zhuang, Yuping Wang, Yuxuan Wang</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> We introduce Heptapod, an image autoregressive model that adheres to the foundational principles of language modeling. Heptapod employs causal attention, eliminates reliance on CFG, and eschews the trend of semantic tokenizers. Our key innovation is next 2D distribution prediction: a causal Transformer with reconstruction-focused visual tokenizer, learns to predict the distribution over the entire 2D spatial grid of images at each timestep. This learning objective unifies the sequential modeling of autoregressive framework with the holistic self-supervised learning of masked autoencoding, enabling the model to capture comprehensive image semantics via generative training. On the ImageNet generation benchmark, Heptapod achieves an FID of 2.70, significantly outperforming previous causal autoregressive approaches. We hope our work inspires a principled rethinking of language modeling on visual signals and beyond.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.06673</guid>
|
||||
<pubDate>Wed, 08 Oct 2025 05:54:46 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>AInstein: Assessing the Feasibility of AI-Generated Approaches to Research Problems</title>
|
||||
<link>https://arxiv.org/abs/2510.05432</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.05432.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shambhavi Mishra, Gaurav Sahu, Marco Pedersoli, Laurent Charlin, Jose Dolz, Christopher Pal</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Large language models (LLMs) demonstrate impressive capabilities across a wide range of tasks, yet it remains unclear whether such success reflects genuine reasoning or sophisticated recall. We introduce AInstein, a framework for testing whether LLMs can generate valid solutions to AI research problems using only their pretrained parametric knowledge -- without domain-specific fine-tuning, retrieval augmentation, or other external aids. Our approach extracts distilled problem statements from high-quality ICLR 2025 submissions, then tasks specialized solver agents with proposing and refining technical solutions through iterative critique loops, mimicking the cycles of proposal, review, and revision central to scientific inquiry. We evaluate AInstein on 1,214 ICLR papers stratified by acceptance tier (Oral, Spotlight, Poster), using an LLM-as-a-judge paradigm guided by a structured rubric, complemented by targeted manual checks. Performance is assessed with three metrics: Success Rate (does the solution address the problem?), Rediscovery (does it align with human-proposed methods?), and Novelty (does it yield valid, original approaches?). Our results reveal that while LLMs can rediscover feasible solutions and occasionally propose creative alternatives, their problem-solving ability remains fragile and highly sensitive to framing. These findings provide the first large-scale evidence on the extent to which LLMs can act as autonomous scientific problem-solvers, highlighting both their latent potential and their current limitations.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.05432</guid>
|
||||
<pubDate>Mon, 06 Oct 2025 22:50:41 +0000</pubDate>
|
||||
<title>RLinf-VLA: A Unified and Efficient Framework for VLA+RL Training</title>
|
||||
<link>https://arxiv.org/abs/2510.06710</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.06710.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hongzhi Zang, Mingjie Wei, Si Xu, Yongji Wu, Zhen Guo, Yuanqing Wang, Hao Lin, Liangzhi Shi, Yuqing Xie, Zhexuan Xu, Zhihao Liu, Kang Chen, Wenhao Tang, Quanlu Zhang, Weinan Zhang, Chao Yu, Yu Wang</p><p><b>Upvotes:</b> 29</p><p><b>Summary:</b> Recent progress in vision and language foundation models has significantly advanced multimodal understanding, reasoning, and generation, inspiring a surge of interest in extending such capabilities to embodied settings through vision-language-action (VLA) models. Yet, most VLA models are still trained with supervised fine-tuning (SFT), which struggles to generalize under distribution shifts due to error accumulation. Reinforcement learning (RL) offers a promising alternative by directly optimizing task performance through interaction, but existing attempts remain fragmented and lack a unified platform for fair and systematic comparison across model architectures and algorithmic designs. To address this gap, we introduce RLinf-VLA, a unified and efficient framework for scalable RL training of VLA models. The system adopts a highly flexible resource allocation design that addresses the challenge of integrating rendering, training, and inference in RL+VLA training. In particular, for GPU-parallelized simulators, RLinf-VLA implements a novel hybrid fine-grained pipeline allocation mode, achieving a 1.61x-1.88x speedup in training. Through a unified interface, RLinf-VLA seamlessly supports diverse VLA architectures (e.g., OpenVLA, OpenVLA-OFT), multiple RL algorithms (e.g., PPO, GRPO), and various simulators (e.g., ManiSkill, LIBERO). In simulation, a unified model achieves 98.11\% across 130 LIBERO tasks and 97.66\% across 25 ManiSkill tasks. Beyond empirical performance, our study distills a set of best practices for applying RL to VLA training and sheds light on emerging patterns in this integration. Furthermore, we present preliminary deployment on a real-world Franka robot, where RL-trained policies exhibit stronger generalization than those trained with SFT. We envision RLinf-VLA as a foundation to accelerate and standardize research on embodied intelligence.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.06710</guid>
|
||||
<pubDate>Wed, 08 Oct 2025 07:05:13 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>TensorBLEU: Vectorized GPU-based BLEU Score Implementation for Per-Sentence In-Training Evaluation</title>
|
||||
<link>https://arxiv.org/abs/2510.05485</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.05485.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Adam Filipek</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Modern natural language processing models have achieved unprecedented scale, yet the tools for their evaluation often remain a computational bottleneck, limiting the pace of research. This is particularly acute for in-training evaluation metrics, such as per-sentence reward signals in Reinforcement Learning, which must operate efficiently on batches of token IDs directly on the GPU. In this paper, we introduce TensorBLEU, a novel implementation of the BLEU metric designed from the ground up for this specific use case. Our approach is fully vectorized for GPU-accelerated, per-sentence computation within PyTorch and introduces a memory-efficient counting mechanism. By creating a compact, batch-specific dictionary of n-grams using torch.unique, our method avoids the prohibitive memory costs of traditional hashing-based vectorization, making it practical for large-vocabulary models. We benchmark TensorBLEU against NLTK, the standard library for token-ID-based BLEU calculation on the CPU. Experiments show that TensorBLEU provides speedups of over 13x on consumer-grade GPUs (NVIDIA T4) and exceeding 40x on data-center-class hardware (NVIDIA A100). This performance transforms a significant bottleneck into a negligible part of the training loop. By clearly defining its role as a "Token-ID BLEU" for development purposes and open-sourcing our implementation, we provide a powerful tool for accelerating research in areas like RL-based model fine-tuning.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.05485</guid>
|
||||
<pubDate>Tue, 07 Oct 2025 01:02:46 +0000</pubDate>
|
||||
<title>OBS-Diff: Accurate Pruning For Diffusion Models in One-Shot</title>
|
||||
<link>https://arxiv.org/abs/2510.06751</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.06751.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junhan Zhu, Hesong Wang, Mingluo Su, Zefang Wang, Huan Wang</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Large-scale text-to-image diffusion models, while powerful, suffer from prohibitive computational cost. Existing one-shot network pruning methods can hardly be directly applied to them due to the iterative denoising nature of diffusion models. To bridge the gap, this paper presents OBS-Diff, a novel one-shot pruning framework that enables accurate and training-free compression of large-scale text-to-image diffusion models. Specifically, (i) OBS-Diff revitalizes the classic Optimal Brain Surgeon (OBS), adapting it to the complex architectures of modern diffusion models and supporting diverse pruning granularity, including unstructured, N:M semi-structured, and structured (MHA heads and FFN neurons) sparsity; (ii) To align the pruning criteria with the iterative dynamics of the diffusion process, by examining the problem from an error-accumulation perspective, we propose a novel timestep-aware Hessian construction that incorporates a logarithmic-decrease weighting scheme, assigning greater importance to earlier timesteps to mitigate potential error accumulation; (iii) Furthermore, a computationally efficient group-wise sequential pruning strategy is proposed to amortize the expensive calibration process. Extensive experiments show that OBS-Diff achieves state-of-the-art one-shot pruning for diffusion models, delivering inference acceleration with minimal degradation in visual quality.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.06751</guid>
|
||||
<pubDate>Wed, 08 Oct 2025 08:19:15 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>HoloScene: Simulation-Ready Interactive 3D Worlds from a Single Video</title>
|
||||
<link>https://arxiv.org/abs/2510.05560</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.05560.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hongchi Xia, Chih-Hao Lin, Hao-Yu Hsu, Quentin Leboutet, Katelyn Gao, Michael Paulitsch, Benjamin Ummenhofer, Shenlong Wang</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Digitizing the physical world into accurate simulation-ready virtual environments offers significant opportunities in a variety of fields such as augmented and virtual reality, gaming, and robotics. However, current 3D reconstruction and scene-understanding methods commonly fall short in one or more critical aspects, such as geometry completeness, object interactivity, physical plausibility, photorealistic rendering, or realistic physical properties for reliable dynamic simulation. To address these limitations, we introduce HoloScene, a novel interactive 3D reconstruction framework that simultaneously achieves these requirements. HoloScene leverages a comprehensive interactive scene-graph representation, encoding object geometry, appearance, and physical properties alongside hierarchical and inter-object relationships. Reconstruction is formulated as an energy-based optimization problem, integrating observational data, physical constraints, and generative priors into a unified, coherent objective. Optimization is efficiently performed via a hybrid approach combining sampling-based exploration with gradient-based refinement. The resulting digital twins exhibit complete and precise geometry, physical stability, and realistic rendering from novel viewpoints. Evaluations conducted on multiple benchmark datasets demonstrate superior performance, while practical use-cases in interactive gaming and real-time digital-twin manipulation illustrate HoloScene's broad applicability and effectiveness. Project page: https://xiahongchi.github.io/HoloScene.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.05560</guid>
|
||||
<pubDate>Tue, 07 Oct 2025 04:12:18 +0000</pubDate>
|
||||
<title>TTRV: Test-Time Reinforcement Learning for Vision Language Models</title>
|
||||
<link>https://arxiv.org/abs/2510.06783</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.06783.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Akshit Singh, Shyam Marjit, Wei Lin, Paul Gavrikov, Serena Yeung-Levy, Hilde Kuehne, Rogerio Feris, Sivan Doveh, James Glass, M. Jehanzeb Mirza</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Existing methods for extracting reward signals in Reinforcement Learning typically rely on labeled data and dedicated training splits, a setup that contrasts with how humans learn directly from their environment. In this work, we propose TTRV to enhance vision language understanding by adapting the model on the fly at inference time, without the need for any labeled data. Concretely, we enhance the Group Relative Policy Optimization (GRPO) framework by designing rewards based on the frequency of the base model's output, while inferring on each test sample multiple times. Further, we also propose to control the diversity of the model's output by simultaneously rewarding the model for obtaining low entropy of the output empirical distribution. Our approach delivers consistent gains across both object recognition and visual question answering (VQA), with improvements of up to 52.4% and 29.8%, respectively, and average boosts of 24.6% and 10.0% across 16 datasets.Remarkably, on image recognition, TTRV applied to InternVL 8B surpasses GPT-4o by an average of 2.3% over 8 benchmarks, while remaining highly competitive on VQA, demonstrating that test-time reinforcement learning can match or exceed the strongest proprietary models. Finally, we find many interesting properties of test-time RL for VLMs: for example, even in extremely data-constrained scenarios, where adaptation is performed on a single randomly chosen unlabeled test example, TTRV still yields non-trivial improvements of up to 5.5% in recognition tasks.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.06783</guid>
|
||||
<pubDate>Wed, 08 Oct 2025 09:10:31 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Presenting a Paper is an Art: Self-Improvement Aesthetic Agents for Academic Presentations</title>
|
||||
<link>https://arxiv.org/abs/2510.05571</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.05571.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chengzhi Liu, Yuzhe Yang, Kaiwen Zhou, Zhen Zhang, Yue Fan, Yannan Xie, Peng Qi, Xin Eric Wang</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> The promotion of academic papers has become an important means of enhancing research visibility. However, existing automated methods struggle limited storytelling, insufficient aesthetic quality, and constrained self-adjustment, making it difficult to achieve efficient and engaging dissemination. At the heart of those challenges is a simple principle: there is no way to improve it when you cannot evaluate it right. To address this, we introduce EvoPresent, a self-improvement agent framework that unifies coherent narratives, aesthetic-aware designs, and realistic presentation delivery via virtual characters. Central to EvoPresent is PresAesth, a multi-task reinforcement learning (RL) aesthetic model that provides reliable aesthetic scoring, defect adjustment, and comparative feedback, enabling iterative self-improvement even under limited aesthetic training data. To systematically evaluate the methods, we introduce EvoPresent Benchmark, a comprehensive benchmark comprising: Presentation Generation Quality, built on 650 top-tier AI conference papers with multimodal resources (slides, videos and scripts) to assess both content and design; and Aesthetic Awareness, consisting of 2,000 slide pairs with varying aesthetic levels, supporting joint training and evaluation on scoring, defect adjustment, and comparison. Our findings highlight that (i) High-quality feedback is essential for agent self-improvement, while initial capability alone does not guarantee effective self-correction. (ii) Automated generation pipelines exhibit a trade-off between visual design and content construction. (iii) Multi-task RL training shows stronger generalization in aesthetic awareness tasks.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.05571</guid>
|
||||
<pubDate>Tue, 07 Oct 2025 04:24:26 +0000</pubDate>
|
||||
<title>Online Generic Event Boundary Detection</title>
|
||||
<link>https://arxiv.org/abs/2510.06855</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.06855.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hyungrok Jung, Daneul Kim, Seunggyun Lim, Jeany Son, Jonghyun Choi</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Generic Event Boundary Detection (GEBD) aims to interpret long-form videos through the lens of human perception. However, current GEBD methods require processing complete video frames to make predictions, unlike humans processing data online and in real-time. To bridge this gap, we introduce a new task, Online Generic Event Boundary Detection (On-GEBD), aiming to detect boundaries of generic events immediately in streaming videos. This task faces unique challenges of identifying subtle, taxonomy-free event changes in real-time, without the access to future frames. To tackle these challenges, we propose a novel On-GEBD framework, Estimator, inspired by Event Segmentation Theory (EST) which explains how humans segment ongoing activity into events by leveraging the discrepancies between predicted and actual information. Our framework consists of two key components: the Consistent Event Anticipator (CEA), and the Online Boundary Discriminator (OBD). Specifically, the CEA generates a prediction of the future frame reflecting current event dynamics based solely on prior frames. Then, the OBD measures the prediction error and adaptively adjusts the threshold using statistical tests on past errors to capture diverse, subtle event transitions. Experimental results demonstrate that Estimator outperforms all baselines adapted from recent online video understanding models and achieves performance comparable to prior offline-GEBD methods on the Kinetics-GEBD and TAPOS datasets.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.06855</guid>
|
||||
<pubDate>Wed, 08 Oct 2025 10:23:45 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>In-the-Flow Agentic System Optimization for Effective Planning and Tool Use</title>
|
||||
<link>https://arxiv.org/abs/2510.05592</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.05592.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhuofeng Li, Haoxiang Zhang, Seungju Han, Sheng Liu, Jianwen Xie, Yu Zhang, Yejin Choi, James Zou, Pan Lu</p><p><b>Upvotes:</b> 29</p><p><b>Summary:</b> Outcome-driven reinforcement learning has advanced reasoning in large language models (LLMs), but prevailing tool-augmented approaches train a single, monolithic policy that interleaves thoughts and tool calls under full context; this scales poorly with long horizons and diverse tools and generalizes weakly to new scenarios. Agentic systems offer a promising alternative by decomposing work across specialized modules, yet most remain training-free or rely on offline training decoupled from the live dynamics of multi-turn interaction. We introduce AgentFlow, a trainable, in-the-flow agentic framework that coordinates four modules (planner, executor, verifier, generator) through an evolving memory and directly optimizes its planner inside the multi-turn loop. To train on-policy in live environments, we propose Flow-based Group Refined Policy Optimization (Flow-GRPO), which tackles long-horizon, sparse-reward credit assignment by converting multi-turn optimization into a sequence of tractable single-turn policy updates. It broadcasts a single, verifiable trajectory-level outcome to every turn to align local planner decisions with global success and stabilizes learning with group-normalized advantages. Across ten benchmarks, AgentFlow with a 7B-scale backbone outperforms top-performing baselines with average accuracy gains of 14.9% on search, 14.0% on agentic, 14.5% on mathematical, and 4.1% on scientific tasks, even surpassing larger proprietary models like GPT-4o. Further analyses confirm the benefits of in-the-flow optimization, showing improved planning, enhanced tool-calling reliability, and positive scaling with model size and reasoning turns.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.05592</guid>
|
||||
<pubDate>Tue, 07 Oct 2025 05:32:44 +0000</pubDate>
|
||||
<title>M3Retrieve: Benchmarking Multimodal Retrieval for Medicine</title>
|
||||
<link>https://arxiv.org/abs/2510.06888</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.06888.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Arkadeep Acharya, Akash Ghosh, Pradeepika Verma, Kitsuchart Pasupa, Sriparna Saha, Priti Singh</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> With the increasing use of RetrievalAugmented Generation (RAG), strong retrieval models have become more important than ever. In healthcare, multimodal retrieval models that combine information from both text and images offer major advantages for many downstream tasks such as question answering, cross-modal retrieval, and multimodal summarization, since medical data often includes both formats. However, there is currently no standard benchmark to evaluate how well these models perform in medical settings. To address this gap, we introduce M3Retrieve, a Multimodal Medical Retrieval Benchmark. M3Retrieve, spans 5 domains,16 medical fields, and 4 distinct tasks, with over 1.2 Million text documents and 164K multimodal queries, all collected under approved licenses. We evaluate leading multimodal retrieval models on this benchmark to explore the challenges specific to different medical specialities and to understand their impact on retrieval performance. By releasing M3Retrieve, we aim to enable systematic evaluation, foster model innovation, and accelerate research toward building more capable and reliable multimodal retrieval systems for medical applications. The dataset and the baselines code are available in this github page https://github.com/AkashGhosh/M3Retrieve.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.06888</guid>
|
||||
<pubDate>Wed, 08 Oct 2025 11:08:47 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Verifier-free Test-Time Sampling for Vision Language Action Models</title>
|
||||
<link>https://arxiv.org/abs/2510.05681</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.05681.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Suhyeok Jang, Dongyoung Kim, Changyeon Kim, Youngsuk Kim, Jinwoo Shin</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Vision-Language-Action models (VLAs) have demonstrated remarkable performance in robot control. However, they remain fundamentally limited in tasks that require high precision due to their single-inference paradigm. While test-time scaling approaches using external verifiers have shown promise, they require additional training and fail to generalize to unseen conditions. We propose Masking Distribution Guided Selection (MG-Select), a novel test-time scaling framework for VLAs that leverages the model's internal properties without requiring additional training or external modules. Our approach utilizes KL divergence from a reference action token distribution as a confidence metric for selecting the optimal action from multiple candidates. We introduce a reference distribution generated by the same VLA but with randomly masked states and language conditions as inputs, ensuring maximum uncertainty while remaining aligned with the target task distribution. Additionally, we propose a joint training strategy that enables the model to learn both conditional and unconditional distributions by applying dropout to state and language conditions, thereby further improving the quality of the reference distribution. Our experiments demonstrate that MG-Select achieves significant performance improvements, including a 28%/35% improvement in real-world in-distribution/out-of-distribution tasks, along with a 168% relative gain on RoboCasa pick-and-place tasks trained with 30 demonstrations.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.05681</guid>
|
||||
<pubDate>Tue, 07 Oct 2025 08:38:08 +0000</pubDate>
|
||||
<title>SHANKS: Simultaneous Hearing and Thinking for Spoken Language Models</title>
|
||||
<link>https://arxiv.org/abs/2510.06917</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.06917.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Cheng-Han Chiang, Xiaofei Wang, Linjie Li, Chung-Ching Lin, Kevin Lin, Shujie Liu, Zhendong Wang, Zhengyuan Yang, Hung-yi Lee, Lijuan Wang</p><p><b>Upvotes:</b> 31</p><p><b>Summary:</b> Current large language models (LLMs) and spoken language models (SLMs) begin thinking and taking actions only after the user has finished their turn. This prevents the model from interacting during the user's turn and can lead to high response latency while it waits to think. Consequently, thinking after receiving the full input is not suitable for speech-to-speech interaction, where real-time, low-latency exchange is important. We address this by noting that humans naturally "think while listening." In this paper, we propose SHANKS, a general inference framework that enables SLMs to generate unspoken chain-of-thought reasoning while listening to the user input. SHANKS streams the input speech in fixed-duration chunks and, as soon as a chunk is received, generates unspoken reasoning based on all previous speech and reasoning, while the user continues speaking. SHANKS uses this unspoken reasoning to decide whether to interrupt the user and to make tool calls to complete the task. We demonstrate that SHANKS enhances real-time user-SLM interaction in two scenarios: (1) when the user is presenting a step-by-step solution to a math problem, SHANKS can listen, reason, and interrupt when the user makes a mistake, achieving 37.1% higher interruption accuracy than a baseline that interrupts without thinking; and (2) in a tool-augmented dialogue, SHANKS can complete 56.9% of the tool calls before the user finishes their turn. Overall, SHANKS moves toward models that keep thinking throughout the conversation, not only after a turn ends. Animated illustrations of Shanks can be found at https://d223302.github.io/SHANKS/</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.06917</guid>
|
||||
<pubDate>Wed, 08 Oct 2025 11:48:59 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Revisiting Modeling and Evaluation Approaches in Speech Emotion Recognition: Considering Subjectivity of Annotators and Ambiguity of Emotions</title>
|
||||
<link>https://arxiv.org/abs/2510.05934</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.05934.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Huang-Cheng Chou, Chi-Chun Lee</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Over the past two decades, speech emotion recognition (SER) has received growing attention. To train SER systems, researchers collect emotional speech databases annotated by crowdsourced or in-house raters who select emotions from predefined categories. However, disagreements among raters are common. Conventional methods treat these disagreements as noise, aggregating labels into a single consensus target. While this simplifies SER as a single-label task, it ignores the inherent subjectivity of human emotion perception. This dissertation challenges such assumptions and asks: (1) Should minority emotional ratings be discarded? (2) Should SER systems learn from only a few individuals' perceptions? (3) Should SER systems predict only one emotion per sample? Psychological studies show that emotion perception is subjective and ambiguous, with overlapping emotional boundaries. We propose new modeling and evaluation perspectives: (1) Retain all emotional ratings and represent them with soft-label distributions. Models trained on individual annotator ratings and jointly optimized with standard SER systems improve performance on consensus-labeled tests. (2) Redefine SER evaluation by including all emotional data and allowing co-occurring emotions (e.g., sad and angry). We propose an ``all-inclusive rule'' that aggregates all ratings to maximize diversity in label representation. Experiments on four English emotion databases show superior performance over majority and plurality labeling. (3) Construct a penalization matrix to discourage unlikely emotion combinations during training. Integrating it into loss functions further improves performance. Overall, embracing minority ratings, multiple annotators, and multi-emotion predictions yields more robust and human-aligned SER systems.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.05934</guid>
|
||||
<pubDate>Tue, 07 Oct 2025 13:45:09 +0000</pubDate>
|
||||
<title>Revisiting the Uniform Information Density Hypothesis in LLM Reasoning Traces</title>
|
||||
<link>https://arxiv.org/abs/2510.06953</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.06953.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Minju Gwak, Guijin Son, Jaehyung Kim</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> The Uniform Information Density (UID) hypothesis suggests that effective communication maintains a stable flow of information. In this work, we revisit this principle in the context of large language model (LLM) reasoning traces, asking whether step-level uniformity reflects reasoning quality. To this end, we propose an entropy-based stepwise information density metric and introduce two complementary measures of uniformity, local and global uniformity scores. Across the experiments on six different reasoning benchmarks, we find that step-level uniformity not only provides a strong theoretical lens but also yields practical performance benefits; for example, selecting reasoning traces with more uniform information density at the step-level improves accuracy by 10-32\% relative gains over baselines at AIME2025. Our analysis further reveals that correct reasoning traces tend to avoid sharp information density spikes, while incorrect traces exhibit irregular information bursts. These results demonstrate that UID-inspired information density measures outperform alternative internal signals as predictors of reasoning quality. Results highlight the uniformity of the information density as a robust diagnostic and selection criterion for building more reliable and accurate reasoning systems.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.06953</guid>
|
||||
<pubDate>Wed, 08 Oct 2025 12:37:04 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Adaptive Pruning for Increased Robustness and Reduced Computational Overhead in Gaussian Process Accelerated Saddle Point Searches</title>
|
||||
<link>https://arxiv.org/abs/2510.06030</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.06030.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Rohit Goswami, Hannes Jónsson</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Gaussian process (GP) regression provides a strategy for accelerating saddle point searches on high-dimensional energy surfaces by reducing the number of times the energy and its derivatives with respect to atomic coordinates need to be evaluated. The computational overhead in the hyperparameter optimization can, however, be large and make the approach inefficient. Failures can also occur if the search ventures too far into regions that are not represented well enough by the GP model. Here, these challenges are resolved by using geometry-aware optimal transport measures and an active pruning strategy using a summation over Wasserstein-1 distances for each atom-type in farthest-point sampling, selecting a fixed-size subset of geometrically diverse configurations to avoid rapidly increasing cost of GP updates as more observations are made. Stability is enhanced by permutation-invariant metric that provides a reliable trust radius for early-stopping and a logarithmic barrier penalty for the growth of the signal variance. These physically motivated algorithmic changes prove their efficacy by reducing to less than a half the mean computational time on a set of 238 challenging configurations from a previously published data set of chemical reactions. With these improvements, the GP approach is established as, a robust and scalable algorithm for accelerating saddle point searches when the evaluation of the energy and atomic forces requires significant computational effort.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.06030</guid>
|
||||
<pubDate>Tue, 07 Oct 2025 15:27:39 +0000</pubDate>
|
||||
<title>Native Hybrid Attention for Efficient Sequence Modeling</title>
|
||||
<link>https://arxiv.org/abs/2510.07019</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.07019.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jusen Du, Jiaxi Hu, Tao Zhang, Weigao Sun, Yu Cheng</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Transformers excel at sequence modeling but face quadratic complexity, while linear attention offers improved efficiency but often compromises recall accuracy over long contexts. In this work, we introduce Native Hybrid Attention (NHA), a novel hybrid architecture of linear and full attention that integrates both intra \& inter-layer hybridization into a unified layer design. NHA maintains long-term context in key-value slots updated by a linear RNN, and augments them with short-term tokens from a sliding window. A single softmax attention operation is then applied over all keys and values, enabling per-token and per-head context-dependent weighting without requiring additional fusion parameters. The inter-layer behavior is controlled through a single hyperparameter, the sliding window size, which allows smooth adjustment between purely linear and full attention while keeping all layers structurally uniform. Experimental results show that NHA surpasses Transformers and other hybrid baselines on recall-intensive and commonsense reasoning tasks. Furthermore, pretrained LLMs can be structurally hybridized with NHA, achieving competitive accuracy while delivering significant efficiency gains. Code is available at https://github.com/JusenD/NHA.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.07019</guid>
|
||||
<pubDate>Wed, 08 Oct 2025 13:44:57 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Refusal Falls off a Cliff: How Safety Alignment Fails in Reasoning?</title>
|
||||
<link>https://arxiv.org/abs/2510.06036</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.06036.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qingyu Yin, Chak Tou Leong, Linyi Yang, Wenxuan Huang, Wenjie Li, Xiting Wang, Jaehong Yoon, YunXing, XingYu, Jinjin Gu</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Large reasoning models (LRMs) with multi-step reasoning capabilities have shown remarkable problem-solving abilities, yet they exhibit concerning safety vulnerabilities that remain poorly understood. In this work, we investigate why safety alignment fails in reasoning models through a mechanistic interpretability lens. Using a linear probing approach to trace refusal intentions across token positions, we discover a striking phenomenon termed as refusal cliff: many poorly-aligned reasoning models correctly identify harmful prompts and maintain strong refusal intentions during their thinking process, but experience a sharp drop in refusal scores at the final tokens before output generation. This suggests that these models are not inherently unsafe; rather, their refusal intentions are systematically suppressed. Through causal intervention analysis, we identify a sparse set of attention heads that negatively contribute to refusal behavior. Ablating just 3\% of these heads can reduce attack success rates below 10\%. Building on these mechanistic insights, we propose Cliff-as-a-Judge, a novel data selection method that identifies training examples exhibiting the largest refusal cliff to efficiently repair reasoning models' safety alignment. This approach achieves comparable safety improvements using only 1.7\% of the vanilla safety training data, demonstrating a less-is-more effect in safety alignment.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.06036</guid>
|
||||
<pubDate>Tue, 07 Oct 2025 15:32:59 +0000</pubDate>
|
||||
<title>Beyond Monolingual Assumptions: A Survey of Code-Switched NLP in the Era of Large Language Models</title>
|
||||
<link>https://arxiv.org/abs/2510.07037</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.07037.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Rajvee Sheth, Samridhi Raj Sinha, Mahavir Patil, Himanshu Beniwal, Mayank Singh</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Code-switching (CSW), the alternation of languages and scripts within a single utterance, remains a fundamental challenge for multiling ual NLP, even amidst the rapid advances of large language models (LLMs). Most LLMs still struggle with mixed-language inputs, limited CSW datasets, and evaluation biases, hindering deployment in multilingual societies. This survey provides the first comprehensive analysis of CSW-aware LLM research, reviewing unique_references studies spanning five research areas, 12 NLP tasks, 30+ datasets, and 80+ languages. We classify recent advances by architecture, training strategy, and evaluation methodology, outlining how LLMs have reshaped CSW modeling and what challenges persist. The paper concludes with a roadmap emphasizing the need for inclusive datasets, fair evaluation, and linguistically grounded models to achieve truly multilingual intelligence. A curated collection of all resources is maintained at https://github.com/lingo-iitgn/awesome-code-mixing/.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.07037</guid>
|
||||
<pubDate>Wed, 08 Oct 2025 14:04:14 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>MixReasoning: Switching Modes to Think</title>
|
||||
<link>https://arxiv.org/abs/2510.06052</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.06052.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haiquan Lu, Gongfan Fang, Xinyin Ma, Qi Li, Xinchao Wang</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Reasoning models enhance performance by tackling problems in a step-by-step manner, decomposing them into sub-problems and exploring long chains of thought before producing an answer. However, applying extended reasoning to every step introduces substantial redundancy, as sub-problems vary widely in difficulty and complexity: a small number of pivotal steps are genuinely challenging and decisive for the final answer, while many others only involve straightforward revisions or simple computations. Therefore, a natural idea is to endow reasoning models with the ability to adaptively respond to this variation, rather than treating all steps with the same level of elaboration. To this end, we propose MixReasoning, a framework that dynamically adjusts the depth of reasoning within a single response. The resulting chain of thought then becomes a mixture of detailed reasoning on difficult steps and concise inference on simpler ones. Experiments on GSM8K, MATH-500, and AIME show that MixReasoning shortens reasoning length and substantially improves efficiency without compromising accuracy.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.06052</guid>
|
||||
<pubDate>Tue, 07 Oct 2025 15:46:34 +0000</pubDate>
|
||||
<title>U-Bench: A Comprehensive Understanding of U-Net through 100-Variant Benchmarking</title>
|
||||
<link>https://arxiv.org/abs/2510.07041</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.07041.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fenghe Tang, Chengqi Dong, Wenxin Ma, Zikang Xu, Heqin Zhu, Zihang Jiang, Rongsheng Wang, Yuhao Wang, Chenxu Wu, Shaohua Kevin Zhou</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Over the past decade, U-Net has been the dominant architecture in medical image segmentation, leading to the development of thousands of U-shaped variants. Despite its widespread adoption, there is still no comprehensive benchmark to systematically evaluate their performance and utility, largely because of insufficient statistical validation and limited consideration of efficiency and generalization across diverse datasets. To bridge this gap, we present U-Bench, the first large-scale, statistically rigorous benchmark that evaluates 100 U-Net variants across 28 datasets and 10 imaging modalities. Our contributions are threefold: (1) Comprehensive Evaluation: U-Bench evaluates models along three key dimensions: statistical robustness, zero-shot generalization, and computational efficiency. We introduce a novel metric, U-Score, which jointly captures the performance-efficiency trade-off, offering a deployment-oriented perspective on model progress. (2) Systematic Analysis and Model Selection Guidance: We summarize key findings from the large-scale evaluation and systematically analyze the impact of dataset characteristics and architectural paradigms on model performance. Based on these insights, we propose a model advisor agent to guide researchers in selecting the most suitable models for specific datasets and tasks. (3) Public Availability: We provide all code, models, protocols, and weights, enabling the community to reproduce our results and extend the benchmark with future methods. In summary, U-Bench not only exposes gaps in previous evaluations but also establishes a foundation for fair, reproducible, and practically relevant benchmarking in the next decade of U-Net-based segmentation models. The project can be accessed at: https://fenghetan9.github.io/ubench. Code is available at: https://github.com/FengheTan9/U-Bench.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.07041</guid>
|
||||
<pubDate>Wed, 08 Oct 2025 14:06:17 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Scientific Algorithm Discovery by Augmenting AlphaEvolve with Deep Research</title>
|
||||
<link>https://arxiv.org/abs/2510.06056</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.06056.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Gang Liu, Yihan Zhu, Jie Chen, Meng Jiang</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Large language models hold promise as scientific assistants, yet existing agents either rely solely on algorithm evolution or on deep research in isolation, both of which face critical limitations. Pure algorithm evolution, as in AlphaEvolve, depends only on the internal knowledge of LLMs and quickly plateaus in complex domains, while pure deep research proposes ideas without validation, resulting in unrealistic or unimplementable solutions. We present DeepEvolve, an agent that integrates deep research with algorithm evolution, uniting external knowledge retrieval, cross-file code editing, and systematic debugging under a feedback-driven iterative loop. Each iteration not only proposes new hypotheses but also refines, implements, and tests them, avoiding both shallow improvements and unproductive over-refinements. Across nine benchmarks in chemistry, mathematics, biology, materials, and patents, DeepEvolve consistently improves the initial algorithm, producing executable new algorithms with sustained gains. By bridging the gap between unguided evolution and research without grounding, DeepEvolve provides a reliable framework for advancing scientific algorithm discovery. Our code is available at https://github.com/liugangcode/deepevolve.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.06056</guid>
|
||||
<pubDate>Tue, 07 Oct 2025 15:49:51 +0000</pubDate>
|
||||
<title>Are We Using the Right Benchmark: An Evaluation Framework for Visual Token Compression Methods</title>
|
||||
<link>https://arxiv.org/abs/2510.07143</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.07143.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chenfei Liao, Wensong Wang, Zichen Wen, Xu Zheng, Yiyu Wang, Haocong He, Yuanhuiyi Lyu, Lutao Jiang, Xin Zou, Yuqian Fu, Bin Ren, Linfeng Zhang, Xuming Hu</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Recent endeavors to accelerate inference in Multimodal Large Language Models (MLLMs) have primarily focused on visual token compression. The effectiveness of these methods is typically assessed by measuring the accuracy drop on established benchmarks, comparing model performance before and after compression. However, these benchmarks are originally designed to assess the perception and reasoning capabilities of MLLMs, rather than to evaluate compression techniques. As a result, directly applying them to visual token compression introduces a task mismatch. Strikingly, our investigation reveals that simple image downsampling consistently outperforms many advanced compression methods across multiple widely used benchmarks. Through extensive experiments, we make the following observations: (i) Current benchmarks are noisy for the visual token compression task. (ii) Down-sampling is able to serve as a data filter to evaluate the difficulty of samples in the visual token compression task. Motivated by these findings, we introduce VTC-Bench, an evaluation framework that incorporates a data filtering mechanism to denoise existing benchmarks, thereby enabling fairer and more accurate assessment of visual token compression methods. All data and code are available at https://github.com/Chenfei-Liao/VTC-Bench.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.07143</guid>
|
||||
<pubDate>Wed, 08 Oct 2025 15:44:28 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>ASPO: Asymmetric Importance Sampling Policy Optimization</title>
|
||||
<link>https://arxiv.org/abs/2510.06062</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.06062.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiakang Wang, Runze Liu, Lei Lin, Wenping Hu, Xiu Li, Fuzheng Zhang, Guorui Zhou, Kun Gai</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Recent Large Language Model (LLM) post-training methods rely on token-level clipping mechanisms during Reinforcement Learning (RL). However, we identify a fundamental flaw in this Outcome-Supervised RL (OSRL) paradigm: the Importance Sampling (IS) ratios of positive-advantage tokens are mismatched, leading to unbalanced token weighting for positive and negative tokens. This mismatch suppresses the update of low-probability tokens while over-amplifying already high-probability ones. To address this, we propose Asymmetric Importance Sampling Policy Optimization (ASPO), which uses a simple yet effective strategy that flips the IS ratios of positive-advantage tokens, aligning their update direction with the learning dynamics of negative ones. AIS further incorporates a soft dual-clipping mechanism to stabilize extreme updates while maintaining gradient flow. Comprehensive experiments on coding and mathematical reasoning benchmarks demonstrate that ASPO significantly mitigates premature convergence, improves training stability, and enhances final performance over strong GRPO-based baselines. Our analysis provides new insights into the role of token-level weighting in OSRL and highlights the critical importance of correcting IS in LLM RL. The code and models of ASPO are available at https://github.com/wizard-III/Archer2.0.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.06062</guid>
|
||||
<pubDate>Tue, 07 Oct 2025 15:54:24 +0000</pubDate>
|
||||
<title>When Benchmarks Age: Temporal Misalignment through Large Language Model Factuality Evaluation</title>
|
||||
<link>https://arxiv.org/abs/2510.07238</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.07238.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xunyi Jiang, Dingyi Chang, Julian McAuley, Xin Xu</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> The rapid evolution of large language models (LLMs) and the real world has outpaced the static nature of widely used evaluation benchmarks, raising concerns about their reliability for evaluating LLM factuality. While substantial works continue to rely on the popular but old benchmarks, their temporal misalignment with real-world facts and modern LLMs, and their effects on LLM factuality evaluation remain underexplored. Therefore, in this work, we present a systematic investigation of this issue by examining five popular factuality benchmarks and eight LLMs released across different years. An up-to-date fact retrieval pipeline and three metrics are tailored to quantify benchmark aging and its impact on LLM factuality evaluation. Experimental results and analysis illustrate that a considerable portion of samples in the widely used factuality benchmarks are outdated, leading to unreliable assessments of LLM factuality. We hope our work can provide a testbed to assess the reliability of a benchmark for LLM factuality evaluation and inspire more research on the benchmark aging issue. Codes are available in https://github.com/JiangXunyi/BenchAge.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.07238</guid>
|
||||
<pubDate>Wed, 08 Oct 2025 17:06:07 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Benchmark It Yourself (BIY): Preparing a Dataset and Benchmarking AI Models for Scatterplot-Related Tasks</title>
|
||||
<link>https://arxiv.org/abs/2510.06071</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.06071.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> João Palmeiro, Diogo Duarte, Rita Costa, Pedro Bizarro</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> AI models are increasingly used for data analysis and visualization, yet benchmarks rarely address scatterplot-specific tasks, limiting insight into performance. To address this gap for one of the most common chart types, we introduce a synthetic, annotated dataset of over 18,000 scatterplots from six data generators and 17 chart designs, and a benchmark based on it. We evaluate proprietary models from OpenAI and Google using N-shot prompting on five distinct tasks derived from annotations of cluster bounding boxes, their center coordinates, and outlier coordinates. OpenAI models and Gemini 2.5 Flash, especially when prompted with examples, are viable options for counting clusters and, in Flash's case, outliers (90%+ Accuracy). However, the results for localization-related tasks are unsatisfactory: Precision and Recall are near or below 50%, except for Flash in outlier identification (65.01%). Furthermore, the impact of chart design on performance appears to be a secondary factor, but it is advisable to avoid scatterplots with wide aspect ratios (16:9 and 21:9) or those colored randomly. Supplementary materials are available at https://github.com/feedzai/biy-paper.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.06071</guid>
|
||||
<pubDate>Tue, 07 Oct 2025 15:59:19 +0000</pubDate>
|
||||
<title>MLE-Smith: Scaling MLE Tasks with Automated Multi-Agent Pipeline</title>
|
||||
<link>https://arxiv.org/abs/2510.07307</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.07307.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Rushi Qiang, Yuchen Zhuang, Anikait Singh, Percy Liang, Chao Zhang, Sherry Yang, Bo Dai</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> While Language Models (LMs) have made significant progress in automating machine learning engineering (MLE), the acquisition of high-quality MLE training data is significantly constrained. Current MLE benchmarks suffer from low scalability and limited applicability because they rely on static, manually curated tasks, demanding extensive time and manual effort to produce. We introduce MLE-Smith, a fully automated multi-agent pipeline, to transform raw datasets into competition-style MLE challenges through an efficient generate-verify-execute paradigm for scaling MLE tasks with verifiable quality, real-world usability, and rich diversity. The proposed multi-agent pipeline in MLE-Smith drives structured task design and standardized refactoring, coupled with a hybrid verification mechanism that enforces strict structural rules and high-level semantic soundness. It further validates empirical solvability and real-world fidelity through interactive execution. We apply MLE-Smith to 224 of real-world datasets and generate 606 tasks spanning multiple categories, objectives, and modalities, demonstrating that MLE-Smith can work effectively across a wide range of real-world datasets. Evaluation on the generated tasks shows that the performance of eight mainstream and cutting-edge LLMs on MLE-Smith tasks is strongly correlated with their performance on carefully human-designed tasks, highlighting the effectiveness of the MLE-Smith to scaling up MLE tasks, while maintaining task quality.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.07307</guid>
|
||||
<pubDate>Wed, 08 Oct 2025 17:57:19 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>The Valley of Code Reasoning: Scaling Knowledge Distillation of Large Language Models</title>
|
||||
<link>https://arxiv.org/abs/2510.06101</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.06101.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Muyu He, Muhammad Ali Shafique, Anand Kumar, Tsach Mackey, Nazneen Rajani</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Distilling the thinking traces of a Large Language Model (LLM) with reasoning capabilities into a smaller model has been proven effective. Yet, there is a scarcity of work done on how model performances scale with the quantity of distillation data. In this work, we study the scaling trend of distilling competitive coding skills on two small non-reasoning LLMs. We validate the hypothesis that there is a valley of code reasoning: downstream performance on competitive coding first drops as data quantity increases, then it steadily increases in a sharper-than-log-linear fashion. Having identified the trend, we further fine-tune the models at two different distillation stages on the same data to ground conclusions on their respective learning phases. We learn that across stages in the low and medium-low data regimes, small models benefit significantly from easier coding questions than from harder ones. We also find that, surprisingly, the correctness of outputs in training data makes no difference to distillation outcomes. Our work represents a step forward in understanding the training dynamics of code reasoning distillation outside intuition</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.06101</guid>
|
||||
<pubDate>Tue, 07 Oct 2025 16:32:09 +0000</pubDate>
|
||||
<title>MATRIX: Mask Track Alignment for Interaction-aware Video Generation</title>
|
||||
<link>https://arxiv.org/abs/2510.07310</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.07310.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Siyoon Jin, Seongchan Kim, Dahyun Chung, Jaeho Lee, Hyunwook Choi, Jisu Nam, Jiyoung Kim, Seungryong Kim</p><p><b>Upvotes:</b> 28</p><p><b>Summary:</b> Video DiTs have advanced video generation, yet they still struggle to model multi-instance or subject-object interactions. This raises a key question: How do these models internally represent interactions? To answer this, we curate MATRIX-11K, a video dataset with interaction-aware captions and multi-instance mask tracks. Using this dataset, we conduct a systematic analysis that formalizes two perspectives of video DiTs: semantic grounding, via video-to-text attention, which evaluates whether noun and verb tokens capture instances and their relations; and semantic propagation, via video-to-video attention, which assesses whether instance bindings persist across frames. We find both effects concentrate in a small subset of interaction-dominant layers. Motivated by this, we introduce MATRIX, a simple and effective regularization that aligns attention in specific layers of video DiTs with multi-instance mask tracks from the MATRIX-11K dataset, enhancing both grounding and propagation. We further propose InterGenEval, an evaluation protocol for interaction-aware video generation. In experiments, MATRIX improves both interaction fidelity and semantic alignment while reducing drift and hallucination. Extensive ablations validate our design choices. Codes and weights will be released.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.07310</guid>
|
||||
<pubDate>Wed, 08 Oct 2025 17:57:38 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Distributional Semantics Tracing: A Framework for Explaining Hallucinations in Large Language Models</title>
|
||||
<link>https://arxiv.org/abs/2510.06107</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.06107.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Gagan Bhatia, Somayajulu G Sripada, Kevin Allan, Jacobo Azcona</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Large Language Models (LLMs) are prone to hallucination, the generation of plausible yet factually incorrect statements. This work investigates the intrinsic, architectural origins of this failure mode through three primary contributions.First, to enable the reliable tracing of internal semantic failures, we propose Distributional Semantics Tracing (DST), a unified framework that integrates established interpretability techniques to produce a causal map of a model's reasoning, treating meaning as a function of context (distributional semantics). Second, we pinpoint the model's layer at which a hallucination becomes inevitable, identifying a specific commitment layer where a model's internal representations irreversibly diverge from factuality. Third, we identify the underlying mechanism for these failures. We observe a conflict between distinct computational pathways, which we interpret using the lens of dual-process theory: a fast, heuristic associative pathway (akin to System 1) and a slow, deliberate contextual pathway (akin to System 2), leading to predictable failure modes such as Reasoning Shortcut Hijacks. Our framework's ability to quantify the coherence of the contextual pathway reveals a strong negative correlation (rho = -0.863) with hallucination rates, implying that these failures are predictable consequences of internal semantic weakness. The result is a mechanistic account of how, when, and why hallucinations occur within the Transformer architecture.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.06107</guid>
|
||||
<pubDate>Tue, 07 Oct 2025 16:40:31 +0000</pubDate>
|
||||
<title>WristWorld: Generating Wrist-Views via 4D World Models for Robotic Manipulation</title>
|
||||
<link>https://arxiv.org/abs/2510.07313</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.07313.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zezhong Qian, Xiaowei Chi, Yuming Li, Shizun Wang, Zhiyuan Qin, Xiaozhu Ju, Sirui Han, Shanghang Zhang</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Wrist-view observations are crucial for VLA models as they capture fine-grained hand-object interactions that directly enhance manipulation performance. Yet large-scale datasets rarely include such recordings, resulting in a substantial gap between abundant anchor views and scarce wrist views. Existing world models cannot bridge this gap, as they require a wrist-view first frame and thus fail to generate wrist-view videos from anchor views alone. Amid this gap, recent visual geometry models such as VGGT emerge with geometric and cross-view priors that make it possible to address extreme viewpoint shifts. Inspired by these insights, we propose WristWorld, the first 4D world model that generates wrist-view videos solely from anchor views. WristWorld operates in two stages: (i) Reconstruction, which extends VGGT and incorporates our Spatial Projection Consistency (SPC) Loss to estimate geometrically consistent wrist-view poses and 4D point clouds; (ii) Generation, which employs our video generation model to synthesize temporally coherent wrist-view videos from the reconstructed perspective. Experiments on Droid, Calvin, and Franka Panda demonstrate state-of-the-art video generation with superior spatial consistency, while also improving VLA performance, raising the average task completion length on Calvin by 3.81% and closing 42.4% of the anchor-wrist view gap.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.07313</guid>
|
||||
<pubDate>Wed, 08 Oct 2025 17:59:08 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Discrete Diffusion Models with MLLMs for Unified Medical Multimodal Generation</title>
|
||||
<link>https://arxiv.org/abs/2510.06131</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.06131.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiawei Mao, Yuhan Wang, Lifeng Chen, Can Zhao, Yucheng Tang, Dong Yang, Liangqiong Qu, Daguang Xu, Yuyin Zhou</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Recent advances in generative medical models are constrained by modality-specific scenarios that hinder the integration of complementary evidence from imaging, pathology, and clinical notes. This fragmentation limits their evolution into foundation models that can learn and reason across the full spectrum of biomedical data. We propose MeDiM, the first medical discrete diffusion model that learns shared distributions across modalities without modality-specific components. MeDiM unifies multiple generative tasks: translating between images and text, and jointly producing image-report pairs across domains in response to prompts. Built on a discrete diffusion framework, MeDiM bridges vision and language representations through a shared probabilistic space. To enable unified and flexible medical generation, we employ a multimodal large language model (MLLM) as the diffusion backbone, leveraging its prior knowledge and cross-modal reasoning. Two key designs are introduced: (1) removing the causal attention mask for bidirectional context, and (2) injecting continuous timestep embeddings for diffusion awareness. Experiments demonstrate high-fidelity medical generation (FID 16.60 on MIMIC-CXR and FID 24.19 on PathGen) and accurate report generation (METEOR 0.2650 and 0.2580). Jointly generated image-report pairs further enhance downstream performance (plus6.43 percent BLEU-1, plus18.57 percent BLEU-2, plus31.58 percent BLEU-3, plus4.80 percent METEOR), showing that MeDiM supports coherent and clinically grounded multimodal outputs.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.06131</guid>
|
||||
<pubDate>Tue, 07 Oct 2025 17:06:57 +0000</pubDate>
|
||||
<title>Vibe Checker: Aligning Code Evaluation with Human Preference</title>
|
||||
<link>https://arxiv.org/abs/2510.07315</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.07315.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ming Zhong, Xiang Zhou, Ting-Yun Chang, Qingze Wang, Nan Xu, Xiance Si, Dan Garrette, Shyam Upadhyay, Jeremiah Liu, Jiawei Han, Benoit Schillings, Jiao Sun</p><p><b>Upvotes:</b> 27</p><p><b>Summary:</b> Large Language Models (LLMs) have catalyzed vibe coding, where users leverage LLMs to generate and iteratively refine code through natural language interactions until it passes their vibe check. Vibe check is tied to real-world human preference and goes beyond functionality: the solution should feel right, read cleanly, preserve intent, and remain correct. However, current code evaluation remains anchored to pass@k and captures only functional correctness, overlooking the non-functional instructions that users routinely apply. In this paper, we hypothesize that instruction following is the missing piece underlying vibe check that represents human preference in coding besides functional correctness. To quantify models' code instruction following capabilities with measurable signals, we present VeriCode, a taxonomy of 30 verifiable code instructions together with corresponding deterministic verifiers. We use the taxonomy to augment established evaluation suites, resulting in Vibe Checker, a testbed to assess both code instruction following and functional correctness. Upon evaluating 31 leading LLMs, we show that even the strongest models struggle to comply with multiple instructions and exhibit clear functional regression. Most importantly, a composite score of functional correctness and instruction following correlates the best with human preference, with the latter emerging as the primary differentiator on real-world programming tasks. Our work identifies core factors of the vibe check, providing a concrete path for benchmarking and developing models that better align with user preferences in coding.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.07315</guid>
|
||||
<pubDate>Wed, 08 Oct 2025 17:59:19 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Deforming Videos to Masks: Flow Matching for Referring Video Segmentation</title>
|
||||
<link>https://arxiv.org/abs/2510.06139</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.06139.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zanyi Wang, Dengyang Jiang, Liuzhuozheng Li, Sizhe Dang, Chengzu Li, Harry Yang, Guang Dai, Mengmeng Wang, Jingdong Wang</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Referring Video Object Segmentation (RVOS) requires segmenting specific objects in a video guided by a natural language description. The core challenge of RVOS is to anchor abstract linguistic concepts onto a specific set of pixels and continuously segment them through the complex dynamics of a video. Faced with this difficulty, prior work has often decomposed the task into a pragmatic `locate-then-segment' pipeline. However, this cascaded design creates an information bottleneck by simplifying semantics into coarse geometric prompts (e.g, point), and struggles to maintain temporal consistency as the segmenting process is often decoupled from the initial language grounding. To overcome these fundamental limitations, we propose FlowRVS, a novel framework that reconceptualizes RVOS as a conditional continuous flow problem. This allows us to harness the inherent strengths of pretrained T2V models, fine-grained pixel control, text-video semantic alignment, and temporal coherence. Instead of conventional generating from noise to mask or directly predicting mask, we reformulate the task by learning a direct, language-guided deformation from a video's holistic representation to its target mask. Our one-stage, generative approach achieves new state-of-the-art results across all major RVOS benchmarks. Specifically, achieving a J&F of 51.1 in MeViS (+1.6 over prior SOTA) and 73.3 in the zero shot Ref-DAVIS17 (+2.7), demonstrating the significant potential of modeling video understanding tasks as continuous deformation processes.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.06139</guid>
|
||||
<pubDate>Tue, 07 Oct 2025 17:14:10 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Mixing Mechanisms: How Language Models Retrieve Bound Entities In-Context</title>
|
||||
<link>https://arxiv.org/abs/2510.06182</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.06182.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yoav Gur-Arieh, Mor Geva, Atticus Geiger</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> A key component of in-context reasoning is the ability of language models (LMs) to bind entities for later retrieval. For example, an LM might represent "Ann loves pie" by binding "Ann" to "pie", allowing it to later retrieve "Ann" when asked "Who loves pie?" Prior research on short lists of bound entities found strong evidence that LMs implement such retrieval via a positional mechanism, where "Ann" is retrieved based on its position in context. In this work, we find that this mechanism generalizes poorly to more complex settings; as the number of bound entities in context increases, the positional mechanism becomes noisy and unreliable in middle positions. To compensate for this, we find that LMs supplement the positional mechanism with a lexical mechanism (retrieving "Ann" using its bound counterpart "pie") and a reflexive mechanism (retrieving "Ann" through a direct pointer). Through extensive experiments on nine models and ten binding tasks, we uncover a consistent pattern in how LMs mix these mechanisms to drive model behavior. We leverage these insights to develop a causal model combining all three mechanisms that estimates next token distributions with 95% agreement. Finally, we show that our model generalizes to substantially longer inputs of open-ended text interleaved with entity groups, further demonstrating the robustness of our findings in more natural settings. Overall, our study establishes a more complete picture of how LMs bind and retrieve entities in-context.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.06182</guid>
|
||||
<pubDate>Tue, 07 Oct 2025 17:44:30 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>ShapeGen4D: Towards High Quality 4D Shape Generation from Videos</title>
|
||||
<link>https://arxiv.org/abs/2510.06208</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.06208.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiraphon Yenphraphai, Ashkan Mirzaei, Jianqi Chen, Jiaxu Zou, Sergey Tulyakov, Raymond A. Yeh, Peter Wonka, Chaoyang Wang</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Video-conditioned 4D shape generation aims to recover time-varying 3D geometry and view-consistent appearance directly from an input video. In this work, we introduce a native video-to-4D shape generation framework that synthesizes a single dynamic 3D representation end-to-end from the video. Our framework introduces three key components based on large-scale pre-trained 3D models: (i) a temporal attention that conditions generation on all frames while producing a time-indexed dynamic representation; (ii) a time-aware point sampling and 4D latent anchoring that promote temporally consistent geometry and texture; and (iii) noise sharing across frames to enhance temporal stability. Our method accurately captures non-rigid motion, volume changes, and even topological transitions without per-frame optimization. Across diverse in-the-wild videos, our method improves robustness and perceptual fidelity and reduces failure modes compared with the baselines.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.06208</guid>
|
||||
<pubDate>Tue, 07 Oct 2025 17:58:11 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Training Dynamics Impact Post-Training Quantization Robustness</title>
|
||||
<link>https://arxiv.org/abs/2510.06213</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.06213.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Albert Catalan-Tatjer, Niccolò Ajroldi, Jonas Geiping</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> While post-training quantization is widely adopted for efficient deployment of large language models, the mechanisms underlying quantization robustness remain unclear. We conduct a comprehensive analysis of quantization degradation across open-source language model training trajectories up to 32B parameters and 15T training tokens to accurately assess the relationship between training dynamics and quantization performance. Our key finding is that quantization errors in large-scale training runs are driven by a complex interplay between learning rate and other training hyperparameters. Specifically, once learning rates decay, validation loss and quantization error diverge, largely independent of training data scale. To investigate interventions on the training dynamics and identify specific configurations that can modulate quantization robustness favorably, we train our own models in controlled experiments up to 100B tokens. Our results challenge the assumption that increasing dataset scale inherently compromises quantization effectiveness, demonstrating instead that strategic training hyperparameter interventions can improve quantization quality at scale.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.06213</guid>
|
||||
<pubDate>Tue, 07 Oct 2025 17:59:07 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>TaTToo: Tool-Grounded Thinking PRM for Test-Time Scaling in Tabular Reasoning</title>
|
||||
<link>https://arxiv.org/abs/2510.06217</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.06217.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiaru Zou, Soumya Roy, Vinay Kumar Verma, Ziyi Wang, David Wipf, Pan Lu, Sumit Negi, James Zou, Jingrui He</p><p><b>Upvotes:</b> 55</p><p><b>Summary:</b> Process Reward Models (PRMs) have recently emerged as a powerful framework for enhancing the reasoning capabilities of large reasoning models (LRMs), particularly in the context of test-time scaling (TTS). However, their potential for supervising LRMs on tabular reasoning domains remains underexplored. Through detailed empirical analyses, we identify that existing PRMs, though widely adopted for supervising text-only reasoning steps, struggle with table-specific operations such as sub-table retrieval and schema interaction, leading to critical performance bottlenecks. To address this limitation, we propose TaTToo, a novel table-grounded PRM framework that (i) reasons explicitly over tabular reasoning steps and (ii) integrates tool-based verification to provide precise reward supervision. Concretely, we first design a scalable data curation pipeline that constructs over 60k high-quality step-level annotations by integrating table verification rationales with tool-based executions. Building on the collected data, we train TaTToo with a dual-stage paradigm: cold-start supervised fine-tuning to capture tool-use reasoning patterns, followed by reinforcement learning with tool-grounded reward shaping to align our model with table-based verification. We provide a comprehensive evaluation of the policy improvement induced by our newly designed PRM. Across 5 challenging tabular reasoning benchmarks covering numerical reasoning, fact-checking, and data analysis, TaTToo improves downstream policy LRMs by 30.9% at inference, surpasses strong PRM baselines such as Qwen-2.5-Math-PRM-72B with only 8B parameters, and demonstrates strong generalizability across diverse TTS strategies.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.06217</guid>
|
||||
<pubDate>Tue, 07 Oct 2025 17:59:41 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>EgoNight: Towards Egocentric Vision Understanding at Night with a Challenging Benchmark</title>
|
||||
<link>https://arxiv.org/abs/2510.06218</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.06218.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Deheng Zhang, Yuqian Fu, Runyi Yang, Yang Miao, Tianwen Qian, Xu Zheng, Guolei Sun, Ajad Chhatkuli, Xuanjing Huang, Yu-Gang Jiang, Luc Van Gool, Danda Pani Paudel</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Most existing benchmarks for egocentric vision understanding focus primarily on daytime scenarios, overlooking the low-light conditions that are inevitable in real-world applications. To investigate this gap, we present EgoNight, the first comprehensive benchmark for nighttime egocentric vision, with visual question answering (VQA) as the core task. A key feature of EgoNight is the introduction of day-night aligned videos, which enhance night annotation quality using the daytime data and reveal clear performance gaps between lighting conditions. To achieve this, we collect both synthetic videos rendered by Blender and real-world recordings, ensuring that scenes and actions are visually and temporally aligned. Leveraging these paired videos, we construct EgoNight-VQA, supported by a novel day-augmented night auto-labeling engine and refinement through extensive human verification. Each QA pair is double-checked by annotators for reliability. In total, EgoNight-VQA contains 3658 QA pairs across 90 videos, spanning 12 diverse QA types, with more than 300 hours of human work. Evaluations of state-of-the-art multimodal large language models (MLLMs) reveal substantial performance drops when transferring from day to night, underscoring the challenges of reasoning under low-light conditions. Beyond VQA, EgoNight also introduces two auxiliary tasks, day-night correspondence retrieval and egocentric depth estimation at night, that further explore the boundaries of existing models. We believe EgoNight-VQA provides a strong foundation for advancing application-driven egocentric vision research and for developing models that generalize across illumination domains. All the data and code will be made available upon acceptance.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.06218</guid>
|
||||
<pubDate>Tue, 07 Oct 2025 17:59:47 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Human3R: Everyone Everywhere All at Once</title>
|
||||
<link>https://arxiv.org/abs/2510.06219</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.06219.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yue Chen, Xingyu Chen, Yuxuan Xue, Anpei Chen, Yuliang Xiu, Gerard Pons-Moll</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> We present Human3R, a unified, feed-forward framework for online 4D human-scene reconstruction, in the world frame, from casually captured monocular videos. Unlike previous approaches that rely on multi-stage pipelines, iterative contact-aware refinement between humans and scenes, and heavy dependencies, e.g., human detection, depth estimation, and SLAM pre-processing, Human3R jointly recovers global multi-person SMPL-X bodies ("everyone"), dense 3D scene ("everywhere"), and camera trajectories in a single forward pass ("all-at-once"). Our method builds upon the 4D online reconstruction model CUT3R, and uses parameter-efficient visual prompt tuning, to strive to preserve CUT3R's rich spatiotemporal priors, while enabling direct readout of multiple SMPL-X bodies. Human3R is a unified model that eliminates heavy dependencies and iterative refinement. After being trained on the relatively small-scale synthetic dataset BEDLAM for just one day on one GPU, it achieves superior performance with remarkable efficiency: it reconstructs multiple humans in a one-shot manner, along with 3D scenes, in one stage, at real-time speed (15 FPS) with a low memory footprint (8 GB). Extensive experiments demonstrate that Human3R delivers state-of-the-art or competitive performance across tasks, including global human motion estimation, local human mesh recovery, video depth estimation, and camera pose estimation, with a single unified model. We hope that Human3R will serve as a simple yet strong baseline, be easily extended for downstream applications.Code available in https://fanegg.github.io/Human3R</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.06219</guid>
|
||||
<pubDate>Tue, 07 Oct 2025 17:59:52 +0000</pubDate>
|
||||
<title>Artificial Hippocampus Networks for Efficient Long-Context Modeling</title>
|
||||
<link>https://arxiv.org/abs/2510.07318</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.07318.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yunhao Fang, Weihao Yu, Shu Zhong, Qinghao Ye, Xuehan Xiong, Lai Wei</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Long-sequence modeling faces a fundamental trade-off between the efficiency of compressive fixed-size memory in RNN-like models and the fidelity of lossless growing memory in attention-based Transformers. Inspired by the Multi-Store Model in cognitive science, we introduce a memory framework of artificial neural networks. Our method maintains a sliding window of the Transformer's KV cache as lossless short-term memory, while a learnable module termed Artificial Hippocampus Network (AHN) recurrently compresses out-of-window information into a fixed-size compact long-term memory. To validate this framework, we instantiate AHNs using modern RNN-like architectures, including Mamba2, DeltaNet, and Gated DeltaNet. Extensive experiments on long-context benchmarks LV-Eval and InfiniteBench demonstrate that AHN-augmented models consistently outperform sliding window baselines and achieve performance comparable or even superior to full-attention models, while substantially reducing computational and memory requirements. For instance, augmenting the Qwen2.5-3B-Instruct with AHNs reduces inference FLOPs by 40.5% and memory cache by 74.0%, while improving its average score on LV-Eval (128k sequence length) from 4.41 to 5.88. Code is available at: https://github.com/ByteDance-Seed/AHN.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.07318</guid>
|
||||
<pubDate>Wed, 08 Oct 2025 17:59:55 +0000</pubDate>
|
||||
</item>
|
||||
</channel>
|
||||
</rss>
|
||||
|
||||
Reference in New Issue
Block a user