748 lines
242 KiB
XML
748 lines
242 KiB
XML
<?xml version='1.0' encoding='UTF-8'?>
|
|
<rss xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/" version="2.0">
|
|
<channel>
|
|
<title>Hugging Face Daily Papers</title>
|
|
<link>https://huggingface.co/papers</link>
|
|
<description>Daily research papers curated by the Hugging Face community.</description>
|
|
<docs>http://www.rssboard.org/rss-specification</docs>
|
|
<generator>python-feedgen</generator>
|
|
<language>en</language>
|
|
<lastBuildDate>Wed, 01 Oct 2025 00:13:26 +0000</lastBuildDate>
|
|
<item>
|
|
<title>A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code</title>
|
|
<link>https://arxiv.org/abs/2508.18106</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.18106.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Keke Lian, Bin Wang, Lei Zhang, Libo Chen, Junjie Wang, Ziming Zhao, Yujiu Yang, Haotong Duan, Haoran Zhao, Shuang Liao, Mingda Guo, Jiazheng Quan, Yilu Zhong, Chenhao He, Zichuan Chen, Jie Wu, Haoling Li, Zhaoxuan Li, Jiongchi Yu, Hui Li, Dong Zhang</p><p><b>Upvotes:</b> 342</p><p><b>Summary:</b> The increasing adoption of large language models (LLMs) in software engineering necessitates rigorous security evaluation of their generated code. However, existing benchmarks often lack relevance to real-world AI programming scenarios, making them inadequate for assessing the practical security risks associated with AI-generated code in production environments. To address this gap, we introduce A.S.E (AI Code Generation Security Evaluation), a repository-level evaluation benchmark designed to closely mirror real-world AI programming tasks, offering a comprehensive and reliable framework for assessing the security of AI-generated code. Our evaluation of leading LLMs on A.S.E reveals several key findings. In particular, current LLMs still struggle with secure coding. The complexity in repository-level scenarios presents challenges for LLMs that typically perform well on snippet-level tasks. Morever, a larger reasoning budget does not necessarily lead to better code generation. These observations offer valuable insights into the current state of AI code generation, assisting developers in selecting the most appropriate models for practical tasks, while laying the foundation for refining LLMs to generate secure and efficient code in real-world applications.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2508.18106</guid>
|
|
<pubDate>Mon, 25 Aug 2025 15:11:11 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Droplet3D: Commonsense Priors from Videos Facilitate 3D Generation</title>
|
|
<link>https://arxiv.org/abs/2508.20470</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.20470.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiaochuan Li, Guoguang Du, Runze Zhang, Liang Jin, Qi Jia, Lihua Lu, Zhenhua Guo, Yaqian Zhao, Haiyang Liu, Tianqi Wang, Changsheng Li, Xiaoli Gong, Rengang Li, Baoyu Fan</p><p><b>Upvotes:</b> 73</p><p><b>Summary:</b> Scaling laws have validated the success and promise of large-data-trained models in creative generation across text, image, and video domains. However, this paradigm faces data scarcity in the 3D domain, as there is far less of it available on the internet compared to the aforementioned modalities. Fortunately, there exist adequate videos that inherently contain commonsense priors, offering an alternative supervisory signal to mitigate the generalization bottleneck caused by limited native 3D data. On the one hand, videos capturing multiple views of an object or scene provide a spatial consistency prior for 3D generation. On the other hand, the rich semantic information contained within the videos enables the generated content to be more faithful to the text prompts and semantically plausible. This paper explores how to apply the video modality in 3D asset generation, spanning datasets to models. We introduce Droplet3D-4M, the first large-scale video dataset with multi-view level annotations, and train Droplet3D, a generative model supporting both image and dense text input. Extensive experiments validate the effectiveness of our approach, demonstrating its ability to produce spatially consistent and semantically plausible content. Moreover, in contrast to the prevailing 3D solutions, our approach exhibits the potential for extension to scene-level applications. This indicates that the commonsense priors from the videos significantly facilitate 3D creation. We have open-sourced all resources including the dataset, code, technical framework, and model weights: https://dropletx.github.io/.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2508.20470</guid>
|
|
<pubDate>Thu, 28 Aug 2025 06:39:41 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>EmbodiedOneVision: Interleaved Vision-Text-Action Pretraining for General Robot Control</title>
|
|
<link>https://arxiv.org/abs/2508.21112</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.21112.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Delin Qu, Haoming Song, Qizhi Chen, Zhaoqing Chen, Xianqiang Gao, Xinyi Ye, Qi Lv, Modi Shi, Guanghui Ren, Cheng Ruan, Maoqing Yao, Haoran Yang, Jiacheng Bao, Bin Zhao, Dong Wang</p><p><b>Upvotes:</b> 76</p><p><b>Summary:</b> The human ability to seamlessly perform multimodal reasoning and physical interaction in the open world is a core goal for general-purpose embodied intelligent systems. Recent vision-language-action (VLA) models, which are co-trained on large-scale robot and visual-text data, have demonstrated notable progress in general robot control. However, they still fail to achieve human-level flexibility in interleaved reasoning and interaction. In this work, introduce EO-Robotics, consists of EO-1 model and EO-Data1.5M dataset. EO-1 is a unified embodied foundation model that achieves superior performance in multimodal embodied reasoning and robot control through interleaved vision-text-action pre-training. The development of EO-1 is based on two key pillars: (i) a unified architecture that processes multimodal inputs indiscriminately (image, text, video, and action), and (ii) a massive, high-quality multimodal embodied reasoning dataset, EO-Data1.5M, which contains over 1.5 million samples with emphasis on interleaved vision-text-action comprehension. EO-1 is trained through synergies between auto-regressive decoding and flow matching denoising on EO-Data1.5M, enabling seamless robot action generation and multimodal embodied reasoning. Extensive experiments demonstrate the effectiveness of interleaved vision-text-action learning for open-world understanding and generalization, validated through a variety of long-horizon, dexterous manipulation tasks across multiple embodiments. This paper details the architecture of EO-1, the data construction strategy of EO-Data1.5M, and the training methodology, offering valuable insights for developing advanced embodied foundation models.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2508.21112</guid>
|
|
<pubDate>Thu, 28 Aug 2025 17:26:15 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Annealing and Reinforce Learning</title>
|
|
<link>https://arxiv.org/abs/2508.21113</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.21113.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jie Jiang, Qi Yang, Bolin Ni, Shiming Xiang, Han Hu, Houwen Peng</p><p><b>Upvotes:</b> 108</p><p><b>Summary:</b> Multimodal Large Language Models (MLLMs) equipped with step-by-step thinking capabilities have demonstrated remarkable performance on complex reasoning problems. However, this thinking process is redundant for simple problems solvable without complex reasoning. To address this inefficiency, we propose R-4B, an auto-thinking MLLM, which can adaptively decide when to think based on problem complexity. The central idea of R-4B is to empower the model with both thinking and non-thinking capabilities using bi-mode annealing, and apply Bi-mode Policy Optimization~(BPO) to improve the model's accuracy in determining whether to activate the thinking process. Specifically, we first train the model on a carefully curated dataset spanning various topics, which contains samples from both thinking and non-thinking modes. Then it undergoes a second phase of training under an improved GRPO framework, where the policy model is forced to generate responses from both modes for each input query. Experimental results show that R-4B achieves state-of-the-art performance across 25 challenging benchmarks. It outperforms Qwen2.5-VL-7B in most tasks and achieves performance comparable to larger models such as Kimi-VL-A3B-Thinking-2506 (16B) on reasoning-intensive benchmarks with lower computational cost.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2508.21113</guid>
|
|
<pubDate>Thu, 28 Aug 2025 17:48:19 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers</title>
|
|
<link>https://arxiv.org/abs/2508.21148</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.21148.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ming Hu, Chenglong Ma, Wei Li, Wanghan Xu, Jiamin Wu, Jucheng Hu, Tianbin Li, Guohang Zhuang, Jiaqi Liu, Yingzhou Lu, Ying Chen, Chaoyang Zhang, Cheng Tan, Jie Ying, Guocheng Wu, Shujian Gao, Pengcheng Chen, Jiashi Lin, Haitao Wu, Lulu Chen, Fengxiang Wang, Yuanyuan Zhang, Xiangyu Zhao, Feilong Tang, Encheng Su, Junzhi Ning, Xinyao Liu, Ye Du, Changkai Ji, Cheng Tang, Huihui Xu, Ziyang Chen, Ziyan Huang, Jiyao Liu, Pengfei Jiang, Yizhou Wang, Chen Tang, Jianyu Wu, Yuchen Ren, Siyuan Yan, Zhonghua Wang, Zhongxing Xu, Shiyan Su, Shangquan Sun, Runkai Zhao, Zhisheng Zhang, Yu Liu, Fudi Wang, Yuanfeng Ji, Yanzhou Su, Hongming Shan, Chunmei Feng, Jiahao Xu, Jiangtao Yan, Wenhao Tang, Diping Song, Lihao Liu, Yanyan Huang, Lequan Yu, Bin Fu, Shujun Wang, Xiaomeng Li, Xiaowei Hu, Yun Gu, Ben Fei, Zhongying Deng, Benyou Wang, Yuewen Cao, Minjie Shen, Haodong Duan, Jie Xu, Yirong Chen, Fang Yan, Hongxia Hao, Jielan Li, Jiajun Du, Yanbo Wang, Imran Razzak, Chi Zhang, Lijun Wu, Conghui He, Zhaohui Lu, Jinhai Huang, Yihao Liu, Fenghua Ling, Yuqiang Li, Aoran Wang, Qihao Zheng, Nanqing Dong, Tianfan Fu, Dongzhan Zhou, Yan Lu, Wenlong Zhang, Jin Ye, Jianfei Cai, Wanli Ouyang, Yu Qiao, Zongyuan Ge, Shixiang Tang, Junjun He, Chunfeng Song, Lei Bai, Bowen Zhou</p><p><b>Upvotes:</b> 141</p><p><b>Summary:</b> Scientific Large Language Models (Sci-LLMs) are transforming how knowledge is represented, integrated, and applied in scientific research, yet their progress is shaped by the complex nature of scientific data. This survey presents a comprehensive, data-centric synthesis that reframes the development of Sci-LLMs as a co-evolution between models and their underlying data substrate. We formulate a unified taxonomy of scientific data and a hierarchical model of scientific knowledge, emphasizing the multimodal, cross-scale, and domain-specific challenges that differentiate scientific corpora from general natural language processing datasets. We systematically review recent Sci-LLMs, from general-purpose foundations to specialized models across diverse scientific disciplines, alongside an extensive analysis of over 270 pre-/post-training datasets, showing why Sci-LLMs pose distinct demands -- heterogeneous, multi-scale, uncertainty-laden corpora that require representations preserving domain invariance and enabling cross-modal reasoning. On evaluation, we examine over 190 benchmark datasets and trace a shift from static exams toward process- and discovery-oriented assessments with advanced evaluation protocols. These data-centric analyses highlight persistent issues in scientific data development and discuss emerging solutions involving semi-automated annotation pipelines and expert validation. Finally, we outline a paradigm shift toward closed-loop systems where autonomous agents based on Sci-LLMs actively experiment, validate, and contribute to a living, evolving knowledge base. Collectively, this work provides a roadmap for building trustworthy, continually evolving artificial intelligence (AI) systems that function as a true partner in accelerating scientific discovery.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2508.21148</guid>
|
|
<pubDate>Thu, 28 Aug 2025 18:30:52 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Open Data Synthesis For Deep Research</title>
|
|
<link>https://arxiv.org/abs/2509.00375</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.00375.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ziyi Xia, Kun Luo, Hongjin Qian, Zheng Liu</p><p><b>Upvotes:</b> 68</p><p><b>Summary:</b> Large language models (LLMs) are increasingly expected to go beyond simple factual queries toward Deep Research-tasks that require decomposing questions into sub-problems, coordinating multi-step reasoning, and synthesizing evidence from diverse sources. We formalize Deep Research tasks with verifiable answers as Hierarchical Constraint Satisfaction Problems (HCSPs), which are fundamentally different from single-constraint, multi-hop, or flat CSP formulations. However, existing benchmarks (e.g., Natural Questions, HotpotQA) fail to capture this complexity, while recent synthetic datasets often introduce shortcut reasoning, knowledge leakage, or lack sufficient structural depth. To address this gap, we introduce InfoSeek, a scalable framework for synthesizing complex Deep Research tasks. InfoSeek uses a dual-agent system to recursively build a Research Tree from large-scale webpages, blurring intermediate nodes into valid sub-problems, and converting these trees into natural language questions that require traversing the full hierarchy. It also enables rapid scaling, yielding over 50K training examples, a curated test set, and reasoning trajectories generated via reject sampling. Experiments show that models trained on InfoSeek consistently outperform strong baselines. On a challenging benchmark BrowseComp-Plus, 3B LLMs optimized with InfoSeek surpass much larger 32B models and lightweight commercial APIs (e.g., Gemini2.5-Flash), while achieving performance comparable to stronger APIs (e.g., Gemini2.5-Pro). By preserving meta-information such as intermediate steps and retrieval labels, InfoSeek further supports advanced optimization strategies, including compound reward design and trajectory-level exploration. We provide our codes and datasets in https://github.com/VectorSpaceLab/InfoSeek{this repository}.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.00375</guid>
|
|
<pubDate>Sat, 30 Aug 2025 06:02:56 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Gated Associative Memory: A Parallel O(N) Architecture for Efficient Sequence Modeling</title>
|
|
<link>https://arxiv.org/abs/2509.00605</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.00605.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Rishiraj Acharya</p><p><b>Upvotes:</b> 42</p><p><b>Summary:</b> The Transformer architecture, underpinned by the self-attention mechanism, has become the de facto standard for sequence modeling tasks. However, its core computational primitive scales quadratically with sequence length (O(N^2)), creating a significant bottleneck for processing long contexts. In this paper, we propose the Gated Associative Memory (GAM) network, a novel, fully parallel architecture for sequence modeling that exhibits linear complexity (O(N)) with respect to sequence length. The GAM block replaces the self-attention layer with two parallel pathways: a causal convolution to efficiently capture local, position-dependent context, and a parallel associative memory retrieval mechanism to model global, content-based patterns. These pathways are dynamically fused using a gating mechanism, allowing the model to flexibly combine local and global information for each token. We implement GAM from scratch and conduct a rigorous comparative analysis against a standard Transformer model and a modern linear-time baseline (Mamba) on the WikiText-2 benchmark, as well as against the Transformer on the TinyStories dataset. Our experiments demonstrate that GAM is consistently faster, outperforming both baselines on training speed, and achieves a superior or competitive final validation perplexity across all datasets, establishing it as a promising and efficient alternative for sequence modeling.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.00605</guid>
|
|
<pubDate>Sat, 30 Aug 2025 20:59:46 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>LLaVA-Critic-R1: Your Critic Model is Secretly a Strong Policy Model</title>
|
|
<link>https://arxiv.org/abs/2509.00676</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.00676.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiyao Wang, Chunyuan Li, Jianwei Yang, Kai Zhang, Bo Liu, Tianyi Xiong, Furong Huang</p><p><b>Upvotes:</b> 83</p><p><b>Summary:</b> In vision-language modeling, critic models are typically trained to evaluate outputs -- assigning scalar scores or pairwise preferences -- rather than to generate responses. This separation from policy models, which produce the responses, is so entrenched that critics are rarely considered for direct policy use. In this work, we challenge this convention. We propose to reorganize preference-labeled critic datasets into verifiable training signals and perform reinforcement learning directly on a base generative model, producing LLaVA-Critic-R1, a multimodal critic trained to optimize preference judgments while retaining full generation ability. Surprisingly, LLaVA-Critic-R1 emerges not only as a top-performing critic but also as a competitive policy model -- matching or surpassing specialized reasoning VLMs trained with in-domain data across 26 visual reasoning and understanding benchmarks, with an average gain of +5.7% over its base model (Qwen-2.5-VL-7B). Extending this approach to existing strong reasoning VLMs yields LLaVA-Critic-R1+, which further advances policy performance without sacrificing critic quality, achieving a SoTA performance of 71.9 on MMMU at the 7B scale. Finally, we show that the enhanced critic ability benefits inference: applying self-critique at test time yields an average +13.8% improvement on five representative reasoning tasks without additional training. Our results reveal that RL training on critic data can produce a unified model excelling at both evaluation and generation, offering a simple path toward scalable, self-improving multimodal systems.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.00676</guid>
|
|
<pubDate>Sun, 31 Aug 2025 03:08:02 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use</title>
|
|
<link>https://arxiv.org/abs/2509.01055</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.01055.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dongfu Jiang, Yi Lu, Zhuofeng Li, Zhiheng Lyu, Ping Nie, Haozhe Wang, Alex Su, Hui Chen, Kai Zou, Chao Du, Tianyu Pang, Wenhu Chen</p><p><b>Upvotes:</b> 70</p><p><b>Summary:</b> Reinforcement Learning with Verifiable Rewards (RLVR) has demonstrated success in enhancing LLM reasoning capabilities, but remains limited to single-turn interactions without tool integration. While recent Agentic Reinforcement Learning with Tool use (ARLT) approaches have emerged to address multi-turn tool interactions, existing works develop task-specific codebases that suffer from fragmentation, synchronous execution bottlenecks, and limited extensibility across domains. These inefficiencies hinder broader community adoption and algorithmic innovation. We introduce VerlTool, a unified and modular framework that addresses these limitations through systematic design principles. VerlTool provides four key contributions: (1) upstream alignment with VeRL ensuring compatibility and simplified maintenance, (2) unified tool management via standardized APIs supporting diverse modalities including code execution, search, SQL databases, and vision processing, (3) asynchronous rollout execution achieving near 2times speedup by eliminating synchronization bottlenecks, and (4) comprehensive evaluation demonstrating competitive performance across 6 ARLT domains. Our framework formalizes ARLT as multi-turn trajectories with multi-modal observation tokens (text/image/video), extending beyond single-turn RLVR paradigms. We train and evaluate models on mathematical reasoning, knowledge QA, SQL generation, visual reasoning, web search, and software engineering tasks, achieving results comparable to specialized systems while providing unified training infrastructure. The modular plugin architecture enables rapid tool integration requiring only lightweight Python definitions, significantly reducing development overhead and providing a scalable foundation for tool-augmented RL research. Our code is open-sourced at https://github.com/TIGER-AI-Lab/verl-tool.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.01055</guid>
|
|
<pubDate>Mon, 01 Sep 2025 01:45:18 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Robix: A Unified Model for Robot Interaction, Reasoning and Planning</title>
|
|
<link>https://arxiv.org/abs/2509.01106</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.01106.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Huang Fang, Mengxi Zhang, Heng Dong, Wei Li, Zixuan Wang, Qifeng Zhang, Xueyun Tian, Yucheng Hu, Hang Li</p><p><b>Upvotes:</b> 47</p><p><b>Summary:</b> We introduce Robix, a unified model that integrates robot reasoning, task planning, and natural language interaction within a single vision-language architecture. Acting as the high-level cognitive layer in a hierarchical robot system, Robix dynamically generates atomic commands for the low-level controller and verbal responses for human interaction, enabling robots to follow complex instructions, plan long-horizon tasks, and interact naturally with human within an end-to-end framework. Robix further introduces novel capabilities such as proactive dialogue, real-time interruption handling, and context-aware commonsense reasoning during task execution. At its core, Robix leverages chain-of-thought reasoning and adopts a three-stage training strategy: (1) continued pretraining to enhance foundational embodied reasoning abilities including 3D spatial understanding, visual grounding, and task-centric reasoning; (2) supervised finetuning to model human-robot interaction and task planning as a unified reasoning-action sequence; and (3) reinforcement learning to improve reasoning-action consistency and long-horizon task coherence. Extensive experiments demonstrate that Robix outperforms both open-source and commercial baselines (e.g., GPT-4o and Gemini 2.5 Pro) in interactive task execution, demonstrating strong generalization across diverse instruction types (e.g., open-ended, multi-stage, constrained, invalid, and interrupted) and various user-involved tasks such as table bussing, grocery shopping, and dietary filtering.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.01106</guid>
|
|
<pubDate>Mon, 01 Sep 2025 03:53:47 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>POINTS-Reader: Distillation-Free Adaptation of Vision-Language Models for Document Conversion</title>
|
|
<link>https://arxiv.org/abs/2509.01215</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.01215.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuan Liu, Zhongyin Zhao, Le Tian, Haicheng Wang, Xubing Ye, Yangxiu You, Zilin Yu, Chuhan Wu, Xiao Zhou, Yang Yu, Jie Zhou</p><p><b>Upvotes:</b> 50</p><p><b>Summary:</b> High-quality labeled data is essential for training accurate document conversion models, particularly in domains with complex formats such as tables, formulas, and multi-column text. However, manual annotation is both costly and time-consuming, while automatic labeling using existing models often lacks accuracy in handling such challenging scenarios. Consequently, training student models by distilling outputs from teacher models can significantly limit their performance in real-world applications. In this paper, we propose a fully automated, distillation-free framework comprising two stages for constructing high-quality document extraction datasets and models capable of handling diverse document formats and layouts. In the first stage, we introduce a method for generating large-scale, diverse synthetic data, which enables a model to extract key elements in a unified format with strong initial performance. In the second stage, we present a self-improvement approach that further adapts the model, initially trained on synthetic data, to real-world documents. Specifically, we first use the fine-tuned model to annotate real documents, then apply a suite of filtering strategies to verify annotation quality, and finally retrain the model on the verified dataset. By iteratively repeating this process, we progressively enhance both the model's conversion capabilities and the quality of the generated data. We train a public POINTS-1.5 model to obtain POINTS-Reader, which surpasses many existing public and proprietary models of comparable or larger size. Our model is available at https://github.com/Tencent/POINTS-Reader.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.01215</guid>
|
|
<pubDate>Mon, 01 Sep 2025 07:54:18 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Reasoning Vectors: Transferring Chain-of-Thought Capabilities via Task Arithmetic</title>
|
|
<link>https://arxiv.org/abs/2509.01363</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.01363.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mohammad Zbeeb, Hasan Abed Al Kader Hammoud, Bernard Ghanem</p><p><b>Upvotes:</b> 57</p><p><b>Summary:</b> Large language models often require costly optimization, such as reinforcement learning, to master complex reasoning tasks. This work demonstrates that reasoning ability, once learned, can be extracted and transferred between models as a compact task vector. We source two publicly available, identically initialized Qwen2.5 models, one fine-tuned with supervised fine-tuning (SFT) and the other with group relative policy optimization (GRPO) on the same dataset. From these, we extract a reasoning vector: v_{reason} = theta_{GRPO} - theta_{SFT}. We hypothesize that this vector captures the reasoning capability instilled by reinforcement learning while factoring out shared knowledge from the SFT process. When added to compatible instruction-tuned models through simple arithmetic, this vector consistently improves performance across diverse reasoning benchmarks: GSM8K (+4.9%), HumanEval (+4.3%), SciQ (+1.7%), and BigBenchHard (+12.3% for the 1.5B model). The performance improvements persist under adversarial conditions. Conversely, subtracting the vector causes significant performance degradation (-11.8% on GSM8K), demonstrating the vector's strong contribution to the model's reasoning abilities. This work shows how reasoning capabilities, typically developed through expensive training, can be extracted from existing open-source models and reused through simple tensor arithmetic, offering a practical way to enhance models by recycling prior computational investments.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.01363</guid>
|
|
<pubDate>Mon, 01 Sep 2025 11:04:51 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>DeepResearch Arena: The First Exam of LLMs' Research Abilities via Seminar-Grounded Tasks</title>
|
|
<link>https://arxiv.org/abs/2509.01396</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.01396.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haiyuan Wan, Chen Yang, Junchi Yu, Meiqi Tu, Jiaxuan Lu, Di Yu, Jianbao Cao, Ben Gao, Jiaqing Xie, Aoran Wang, Wenlong Zhang, Philip Torr, Dongzhan Zhou</p><p><b>Upvotes:</b> 56</p><p><b>Summary:</b> Deep research agents have attracted growing attention for their potential to orchestrate multi-stage research workflows, spanning literature synthesis, methodological design, and empirical verification. Despite these strides, evaluating their research capability faithfully is rather challenging due to the difficulty of collecting frontier research questions that genuinely capture researchers' attention and intellectual curiosity. To address this gap, we introduce DeepResearch Arena, a benchmark grounded in academic seminars that capture rich expert discourse and interaction, better reflecting real-world research environments and reducing the risk of data leakage. To automatically construct DeepResearch Arena, we propose a Multi-Agent Hierarchical Task Generation (MAHTG) system that extracts research-worthy inspirations from seminar transcripts. The MAHTG system further translates research-worthy inspirations into high-quality research tasks, ensuring the traceability of research task formulation while filtering noise. With the MAHTG system, we curate DeepResearch Arena with over 10,000 high-quality research tasks from over 200 academic seminars, spanning 12 disciplines, such as literature, history, and science. Our extensive evaluation shows that DeepResearch Arena presents substantial challenges for current state-of-the-art agents, with clear performance gaps observed across different models.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.01396</guid>
|
|
<pubDate>Mon, 01 Sep 2025 11:42:47 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Kwai Keye-VL 1.5 Technical Report</title>
|
|
<link>https://arxiv.org/abs/2509.01563</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.01563.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Biao Yang, Bin Wen, Boyang Ding, Changyi Liu, Chenglong Chu, Chengru Song, Chongling Rao, Chuan Yi, Da Li, Dunju Zang, Fan Yang, Guorui Zhou, Guowang Zhang, Han Shen, Hao Peng, Haojie Ding, Hao Wang, Hengrui Ju, Jiaming Huang, Jiangxia Cao, Jiankang Chen, Jingyun Hua, Kaibing Chen, Kaiyu Jiang, Kaiyu Tang, Kun Gai, Muhao Wei, Qiang Wang, Ruitao Wang, Sen Na, Shengnan Zhang, Siyang Mao, Sui Huang, Tianke Zhang, Tingting Gao, Wei Chen, Wei Yuan, Xiangyu Wu, Xiao Hu, Xingyu Lu, Yi-Fan Zhang, Yiping Yang, Yulong Chen, Zeyi Lu, Zhenhua Wu, Zhixin Ling, Zhuoran Yang, Ziming Li, Di Xu, Haixuan Gao, Hang Li, Jing Wang, Lejian Ren, Qigen Hu, Qianqian Wang, Shiyao Wang, Xinchen Luo, Yan Li, Yuhang Hu, Zixing Zhang</p><p><b>Upvotes:</b> 36</p><p><b>Summary:</b> In recent years, the development of Large Language Models (LLMs) has significantly advanced, extending their capabilities to multimodal tasks through Multimodal Large Language Models (MLLMs). However, video understanding remains a challenging area due to the dynamic and information-dense nature of videos. Existing models struggle with the trade-off between spatial resolution and temporal coverage when processing video content. We present Keye-VL-1.5, which addresses fundamental challenges in video comprehension through three key innovations. First, we introduce a novel Slow-Fast video encoding strategy that dynamically allocates computational resources based on inter-frame similarity, processing key frames with significant visual changes at higher resolution (Slow pathway) while handling relatively static frames with increased temporal coverage at lower resolution (Fast pathway). Second, we implement a progressive four-stage pre-training methodology that systematically extends the model's context length from 8K to 128K tokens, enabling processing of longer videos and more complex visual content. Third, we develop a comprehensive post-training pipeline focusing on reasoning enhancement and human preference alignment, incorporating a 5-step chain-of-thought data construction process, iterative GSPO-based reinforcement learning with progressive prompt hinting for difficult cases, and alignment training. Through extensive evaluation on public benchmarks and rigorous internal human assessment, Keye-VL-1.5 demonstrates significant improvements over existing models, particularly excelling in video understanding tasks while maintaining competitive performance on general multimodal benchmarks.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.01563</guid>
|
|
<pubDate>Mon, 01 Sep 2025 15:46:58 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>OpenVision 2: A Family of Generative Pretrained Visual Encoders for Multimodal Learning</title>
|
|
<link>https://arxiv.org/abs/2509.01644</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.01644.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yanqing Liu, Xianhang Li, Letian Zhang, Zirui Wang, Zeyu Zheng, Yuyin Zhou, Cihang Xie</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> This paper provides a simplification on OpenVision's architecture and loss design for enhancing its training efficiency. Following the prior vision-language pretraining works CapPa and AIMv2, as well as modern multimodal designs like LLaVA, our changes are straightforward: we remove the text encoder (and therefore the contrastive loss), retaining only the captioning loss as a purely generative training signal. We name this new version OpenVision 2. The initial results are promising: despite this simplification, OpenVision 2 competitively matches the original model's performance on a broad set of multimodal benchmarks while substantially cutting both training time and memory consumption. For example, with ViT-L/14, it reduces training time by about 1.5x (from 83h to 57h), and memory usage by about 1.8x (from 24.5GB to 13.8GB, equivalently allowing the maximum batch size to grow from 2k to 8k). This superior training efficiency also allows us to scale far beyond the largest vision encoder used in OpenVision, reaching more than 1 billion parameters. We hold a strong belief that this lightweight, generative-only paradigm is compelling for future vision encoder development in multimodal foundation models.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.01644</guid>
|
|
<pubDate>Mon, 01 Sep 2025 17:38:21 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Baichuan-M2: Scaling Medical Capability with Large Verifier System</title>
|
|
<link>https://arxiv.org/abs/2509.02208</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.02208.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Baichuan-M2 Team, Chengfeng Dou, Chong Liu, Fan Yang, Fei Li, Jiyuan Jia, Mingyang Chen, Qiang Ju, Shuai Wang, Shunya Dang, Tianpeng Li, Xiangrong Zeng, Yijie Zhou, Chenzheng Zhu, Da Pan, Fei Deng, Guangwei Ai, Guosheng Dong, Hongda Zhang, Jinyang Tai, Jixiang Hong, Kai Lu, Linzhuang Sun, Peidong Guo, Qian Ma, Rihui Xin, Shihui Yang, Shusen Zhang, Yichuan Mo, Zheng Liang, Zhishou Zhang, Hengfu Cui, Zuyi Zhu, Xiaochuan Wang</p><p><b>Upvotes:</b> 39</p><p><b>Summary:</b> As large language models (LLMs) advance in conversational and reasoning capabilities, their practical application in healthcare has become a critical research focus. However, there is a notable gap between the performance of medical LLMs on static benchmarks such as USMLE and their utility in real-world clinical decision-making. This discrepancy arises because traditional exams fail to capture the dynamic, interactive nature of medical consultations. To address this challenge, we introduce a novel dynamic verification framework that moves beyond static answer verifier, establishing a large-scale, high-fidelity interactive reinforcement learning system. Our framework comprises two key components: a Patient Simulator that creates realistic clinical environments using de-identified medical records, and a Clinical Rubrics Generator that dynamically produces multi-dimensional evaluation metrics. Building on this foundation, we develop Baichuan-M2, a 32B-parameter medical augmented reasoning model trained through a multi-stage reinforcement learning strategy with an improved Group Relative Policy Optimization (GRPO) algorithm. Evaluated on HealthBench, Baichuan-M2 outperforms all other open-source models and most advanced closed-source counterparts, achieving a score above 32 on the challenging HealthBench Hard benchmark-previously exceeded only by GPT-5. Our work demonstrates that robust dynamic verifier system is essential for aligning LLM capabilities with practical clinical applications, establishing a new Pareto front in the performance-parameter trade-off for medical AI deployment.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.02208</guid>
|
|
<pubDate>Tue, 02 Sep 2025 11:23:35 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning</title>
|
|
<link>https://arxiv.org/abs/2509.02479</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.02479.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhenghai Xue, Longtao Zheng, Qian Liu, Yingru Li, Xiaosen Zheng, Zejun Ma, Bo An</p><p><b>Upvotes:</b> 83</p><p><b>Summary:</b> Large Language Models (LLMs) can significantly improve their reasoning capabilities by interacting with external tools, a paradigm known as Tool-Integrated Reasoning (TIR). However, extending TIR to multi-turn scenarios using Reinforcement Learning (RL) is often hindered by training instability and performance collapse. We identify that such instability is primarily caused by a distributional drift from external tool feedback, leading to the generation of low-probability tokens. This issue compounds over successive turns, causing catastrophic gradient norm explosions that derail the training process. To address this challenge, we introduce SimpleTIR , a plug-and-play algorithm that stabilizes multi-turn TIR training. Its core strategy is to identify and filter out trajectories containing void turns, i.e., turns that yield neither a code block nor a final answer. By removing these problematic trajectories from the policy update, SimpleTIR effectively blocks the harmful, high-magnitude gradients, thus stabilizing the learning dynamics. Extensive experiments show that SimpleTIR achieves state-of-the-art performance on challenging math reasoning benchmarks, notably elevating the AIME24 score from a text-only baseline of 22.1 to 50.5 when starting from the Qwen2.5-7B base model. Furthermore, by avoiding the constraints of supervised fine-tuning, SimpleTIR encourages the model to discover diverse and sophisticated reasoning patterns, such as self-correction and cross-validation.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.02479</guid>
|
|
<pubDate>Tue, 02 Sep 2025 16:30:19 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning</title>
|
|
<link>https://arxiv.org/abs/2509.02544</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.02544.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haoming Wang, Haoyang Zou, Huatong Song, Jiazhan Feng, Junjie Fang, Junting Lu, Longxiang Liu, Qinyu Luo, Shihao Liang, Shijue Huang, Wanjun Zhong, Yining Ye, Yujia Qin, Yuwen Xiong, Yuxin Song, Zhiyong Wu, Bo Li, Chen Dun, Chong Liu, Fuxing Leng, Hanbin Wang, Hao Yu, Haobin Chen, Hongyi Guo, Jing Su, Jingjia Huang, Kai Shen, Kaiyu Shi, Lin Yan, Peiyao Zhao, Pengfei Liu, Qinghao Ye, Renjie Zheng, Wayne Xin Zhao, Wen Heng, Wenhao Huang, Wenqian Wang, Xiaobo Qin, Yi Lin, Youbin Wu, Zehui Chen, Zihao Wang, Baoquan Zhong, Xinchun Zhang, Xujing Li, Yuanfan Li, Zhongkai Zhao, Chengquan Jiang, Faming Wu, Haotian Zhou, Jinlin Pang, Li Han, Qianli Ma, Siyao Liu, Songhua Cai, Wenqi Fu, Xin Liu, Zhi Zhang, Bo Zhou, Guoliang Li, Jiajun Shi, Jiale Yang, Jie Tang, Li Li, Taoran Lu, Woyu Lin, Xiaokang Tong, Xinyao Li, Yichi Zhang, Yu Miao, Zhengxuan Jiang, Zili Li, Ziyuan Zhao, Chenxin Li, Dehua Ma, Feng Lin, Ge Zhang, Haihua Yang, Hangyu Guo, Hongda Zhu, Jiaheng Liu, Junda Du, Kai Cai, Kuanye Li, Lichen Yuan, Meilan Han, Minchao Wang, Shuyue Guo, Tianhao Cheng, Xiaobo Ma, Xiaojun Xiao, Xiaolong Huang, Xinjie Chen, Yidi Du, Yilin Chen, Yiwen Wang, Zhaojian Li, Zhenzhu Yang, Zhiyuan Zeng, Chaolin Jin, Chen Li, Hao Chen, Haoli Chen, Jian Chen, Qinghao Zhao, Guang Shi</p><p><b>Upvotes:</b> 120</p><p><b>Summary:</b> The development of autonomous agents for graphical user interfaces (GUIs) presents major challenges in artificial intelligence. While recent advances in native agent models have shown promise by unifying perception, reasoning, action, and memory through end-to-end learning, open problems remain in data scalability, multi-turn reinforcement learning (RL), the limitations of GUI-only operation, and environment stability. In this technical report, we present UI-TARS-2, a native GUI-centered agent model that addresses these challenges through a systematic training methodology: a data flywheel for scalable data generation, a stabilized multi-turn RL framework, a hybrid GUI environment that integrates file systems and terminals, and a unified sandbox platform for large-scale rollouts. Empirical evaluation demonstrates that UI-TARS-2 achieves significant improvements over its predecessor UI-TARS-1.5. On GUI benchmarks, it reaches 88.2 on Online-Mind2Web, 47.5 on OSWorld, 50.6 on WindowsAgentArena, and 73.3 on AndroidWorld, outperforming strong baselines such as Claude and OpenAI agents. In game environments, it attains a mean normalized score of 59.8 across a 15-game suite-roughly 60% of human-level performance-and remains competitive with frontier proprietary models (e.g., OpenAI o3) on LMGame-Bench. Additionally, the model can generalize to long-horizon information-seeking tasks and software engineering benchmarks, highlighting its robustness across diverse agent tasks. Detailed analyses of training dynamics further provide insights into achieving stability and efficiency in large-scale agent RL. These results underscore UI-TARS-2's potential to advance the state of GUI agents and exhibit strong generalization to real-world interactive scenarios.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.02544</guid>
|
|
<pubDate>Tue, 02 Sep 2025 17:44:45 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>The Landscape of Agentic Reinforcement Learning for LLMs: A Survey</title>
|
|
<link>https://arxiv.org/abs/2509.02547</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.02547.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Guibin Zhang, Hejia Geng, Xiaohang Yu, Zhenfei Yin, Zaibin Zhang, Zelin Tan, Heng Zhou, Zhongzhi Li, Xiangyuan Xue, Yijiang Li, Yifan Zhou, Yang Chen, Chen Zhang, Yutao Fan, Zihu Wang, Songtao Huang, Yue Liao, Hongru Wang, Mengyue Yang, Heng Ji, Michael Littman, Jun Wang, Shuicheng Yan, Philip Torr, Lei Bai</p><p><b>Upvotes:</b> 211</p><p><b>Summary:</b> The emergence of agentic reinforcement learning (Agentic RL) marks a paradigm shift from conventional reinforcement learning applied to large language models (LLM RL), reframing LLMs from passive sequence generators into autonomous, decision-making agents embedded in complex, dynamic worlds. This survey formalizes this conceptual shift by contrasting the degenerate single-step Markov Decision Processes (MDPs) of LLM-RL with the temporally extended, partially observable Markov decision processes (POMDPs) that define Agentic RL. Building on this foundation, we propose a comprehensive twofold taxonomy: one organized around core agentic capabilities, including planning, tool use, memory, reasoning, self-improvement, and perception, and the other around their applications across diverse task domains. Central to our thesis is that reinforcement learning serves as the critical mechanism for transforming these capabilities from static, heuristic modules into adaptive, robust agentic behavior. To support and accelerate future research, we consolidate the landscape of open-source environments, benchmarks, and frameworks into a practical compendium. By synthesizing over five hundred recent works, this survey charts the contours of this rapidly evolving field and highlights the opportunities and challenges that will shape the development of scalable, general-purpose AI agents.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.02547</guid>
|
|
<pubDate>Tue, 02 Sep 2025 17:46:26 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Drivel-ology: Challenging LLMs with Interpreting Nonsense with Depth</title>
|
|
<link>https://arxiv.org/abs/2509.03867</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.03867.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yang Wang, Chenghao Xiao, Chia-Yi Hsiao, Zi Yan Chang, Chi-Li Chen, Tyler Loakman, Chenghua Lin</p><p><b>Upvotes:</b> 206</p><p><b>Summary:</b> We introduce Drivelology, a unique linguistic phenomenon characterised as "nonsense with depth", utterances that are syntactically coherent yet pragmatically paradoxical, emotionally loaded, or rhetorically subversive. While such expressions may resemble surface-level nonsense, they encode implicit meaning requiring contextual inference, moral reasoning, or emotional interpretation. We find that current large language models (LLMs), despite excelling at many natural language processing (NLP) tasks, consistently fail to grasp the layered semantics of Drivelological text. To investigate this, we construct a small but diverse benchmark dataset of over 1,200 meticulously curated examples, with select instances in English, Mandarin, Spanish, French, Japanese, and Korean. Annotation was especially challenging: each of the examples required careful expert review to verify that it truly reflected Drivelological characteristics. The process involved multiple rounds of discussion and adjudication to address disagreements, highlighting the subtle and subjective nature of the Drivelology. We evaluate a range of LLMs on classification, generation, and reasoning tasks. Our results reveal clear limitations of LLMs: models often confuse Drivelology with shallow nonsense, produce incoherent justifications, or miss the implied rhetorical function altogether. These findings highlight a deeper representational gap in LLMs' pragmatic understanding and challenge the assumption that statistical fluency implies cognitive comprehension. We release our dataset and code to facilitate further research in modelling linguistic depth beyond surface-level coherence.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.03867</guid>
|
|
<pubDate>Thu, 04 Sep 2025 03:58:55 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Set Block Decoding is a Language Model Inference Accelerator</title>
|
|
<link>https://arxiv.org/abs/2509.04185</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.04185.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Itai Gat, Heli Ben-Hamu, Marton Havasi, Daniel Haziza, Jeremy Reizenstein, Gabriel Synnaeve, David Lopez-Paz, Brian Karrer, Yaron Lipman</p><p><b>Upvotes:</b> 52</p><p><b>Summary:</b> Autoregressive next token prediction language models offer powerful capabilities but face significant challenges in practical deployment due to the high computational and memory costs of inference, particularly during the decoding stage. We introduce Set Block Decoding (SBD), a simple and flexible paradigm that accelerates generation by integrating standard next token prediction (NTP) and masked token prediction (MATP) within a single architecture. SBD allows the model to sample multiple, not necessarily consecutive, future tokens in parallel, a key distinction from previous acceleration methods. This flexibility allows the use of advanced solvers from the discrete diffusion literature, offering significant speedups without sacrificing accuracy. SBD requires no architectural changes or extra training hyperparameters, maintains compatibility with exact KV-caching, and can be implemented by fine-tuning existing next token prediction models. By fine-tuning Llama-3.1 8B and Qwen-3 8B, we demonstrate that SBD enables a 3-5x reduction in the number of forward passes required for generation while achieving same performance as equivalent NTP training.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.04185</guid>
|
|
<pubDate>Thu, 04 Sep 2025 13:02:39 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Inverse IFEval: Can LLMs Unlearn Stubborn Training Conventions to Follow Real Instructions?</title>
|
|
<link>https://arxiv.org/abs/2509.04292</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.04292.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qinyan Zhang, Xinping Lei, Ruijie Miao, Yu Fu, Haojie Fan, Le Chang, Jiafan Hou, Dingling Zhang, Zhongfei Hou, Ziqiang Yang, Changxin Pu, Fei Hu, Jingkai Liu, Mengyun Liu, Yang Liu, Xiang Gao, Jiaheng Liu, Tong Yang, Zaiyuan Wang, Ge Zhang, Wenhao Huang</p><p><b>Upvotes:</b> 57</p><p><b>Summary:</b> Large Language Models (LLMs) achieve strong performance on diverse tasks but often exhibit cognitive inertia, struggling to follow instructions that conflict with the standardized patterns learned during supervised fine-tuning (SFT). To evaluate this limitation, we propose Inverse IFEval, a benchmark that measures models Counter-intuitive Abilitytheir capacity to override training-induced biases and comply with adversarial instructions. Inverse IFEval introduces eight types of such challenges, including Question Correction, Intentional Textual Flaws, Code without Comments, and Counterfactual Answering. Using a human-in-the-loop pipeline, we construct a dataset of 1012 high-quality Chinese and English questions across 23 domains, evaluated under an optimized LLM-as-a-Judge framework. Experiments on existing leading LLMs demonstrate the necessity of our proposed Inverse IFEval benchmark. Our findings emphasize that future alignment efforts should not only pursue fluency and factual correctness but also account for adaptability under unconventional contexts. We hope that Inverse IFEval serves as both a diagnostic tool and a foundation for developing methods that mitigate cognitive inertia, reduce overfitting to narrow patterns, and ultimately enhance the instruction-following reliability of LLMs in diverse and unpredictable real-world scenarios.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.04292</guid>
|
|
<pubDate>Thu, 04 Sep 2025 15:03:02 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>From Editor to Dense Geometry Estimator</title>
|
|
<link>https://arxiv.org/abs/2509.04338</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.04338.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> JiYuan Wang, Chunyu Lin, Lei Sun, Rongying Liu, Lang Nie, Mingxing Li, Kang Liao, Xiangxiang Chu, Yao Zhao</p><p><b>Upvotes:</b> 91</p><p><b>Summary:</b> Leveraging visual priors from pre-trained text-to-image (T2I) generative models has shown success in dense prediction. However, dense prediction is inherently an image-to-image task, suggesting that image editing models, rather than T2I generative models, may be a more suitable foundation for fine-tuning. Motivated by this, we conduct a systematic analysis of the fine-tuning behaviors of both editors and generators for dense geometry estimation. Our findings show that editing models possess inherent structural priors, which enable them to converge more stably by ``refining" their innate features, and ultimately achieve higher performance than their generative counterparts. Based on these findings, we introduce FE2E, a framework that pioneeringly adapts an advanced editing model based on Diffusion Transformer (DiT) architecture for dense geometry prediction. Specifically, to tailor the editor for this deterministic task, we reformulate the editor's original flow matching loss into the ``consistent velocity" training objective. And we use logarithmic quantization to resolve the precision conflict between the editor's native BFloat16 format and the high precision demand of our tasks. Additionally, we leverage the DiT's global attention for a cost-free joint estimation of depth and normals in a single forward pass, enabling their supervisory signals to mutually enhance each other. Without scaling up the training data, FE2E achieves impressive performance improvements in zero-shot monocular depth and normal estimation across multiple datasets. Notably, it achieves over 35\% performance gains on the ETH3D dataset and outperforms the DepthAnything series, which is trained on 100times data. The project page can be accessed https://amap-ml.github.io/FE2E/{here}.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.04338</guid>
|
|
<pubDate>Thu, 04 Sep 2025 15:58:50 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Towards a Unified View of Large Language Model Post-Training</title>
|
|
<link>https://arxiv.org/abs/2509.04419</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.04419.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xingtai Lv, Yuxin Zuo, Youbang Sun, Hongyi Liu, Yuntian Wei, Zhekai Chen, Lixuan He, Xuekai Zhu, Kaiyan Zhang, Bingning Wang, Ning Ding, Bowen Zhou</p><p><b>Upvotes:</b> 73</p><p><b>Summary:</b> Two major sources of training data exist for post-training modern language models: online (model-generated rollouts) data, and offline (human or other-model demonstrations) data. These two types of data are typically used by approaches like Reinforcement Learning (RL) and Supervised Fine-Tuning (SFT), respectively. In this paper, we show that these approaches are not in contradiction, but are instances of a single optimization process. We derive a Unified Policy Gradient Estimator, and present the calculations of a wide spectrum of post-training approaches as the gradient of a common objective under different data distribution assumptions and various bias-variance tradeoffs. The gradient estimator is constructed with four interchangeable parts: stabilization mask, reference policy denominator, advantage estimate, and likelihood gradient. Motivated by our theoretical findings, we propose Hybrid Post-Training (HPT), an algorithm that dynamically selects different training signals. HPT is designed to yield both effective exploitation of demonstration and stable exploration without sacrificing learned reasoning patterns. We provide extensive experiments and ablation studies to verify the effectiveness of our unified theoretical framework and HPT. Across six mathematical reasoning benchmarks and two out-of-distribution suites, HPT consistently surpasses strong baselines across models of varying scales and families.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.04419</guid>
|
|
<pubDate>Thu, 04 Sep 2025 17:40:33 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>3D and 4D World Modeling: A Survey</title>
|
|
<link>https://arxiv.org/abs/2509.07996</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.07996.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lingdong Kong, Wesley Yang, Jianbiao Mei, Youquan Liu, Ao Liang, Dekai Zhu, Dongyue Lu, Wei Yin, Xiaotao Hu, Mingkai Jia, Junyuan Deng, Kaiwen Zhang, Yang Wu, Tianyi Yan, Shenyuan Gao, Song Wang, Linfeng Li, Liang Pan, Yong Liu, Jianke Zhu, Wei Tsang Ooi, Steven C. H. Hoi, Ziwei Liu</p><p><b>Upvotes:</b> 57</p><p><b>Summary:</b> World modeling has become a cornerstone in AI research, enabling agents to understand, represent, and predict the dynamic environments they inhabit. While prior work largely emphasizes generative methods for 2D image and video data, they overlook the rapidly growing body of work that leverages native 3D and 4D representations such as RGB-D imagery, occupancy grids, and LiDAR point clouds for large-scale scene modeling. At the same time, the absence of a standardized definition and taxonomy for ``world models'' has led to fragmented and sometimes inconsistent claims in the literature. This survey addresses these gaps by presenting the first comprehensive review explicitly dedicated to 3D and 4D world modeling and generation. We establish precise definitions, introduce a structured taxonomy spanning video-based (VideoGen), occupancy-based (OccGen), and LiDAR-based (LiDARGen) approaches, and systematically summarize datasets and evaluation metrics tailored to 3D/4D settings. We further discuss practical applications, identify open challenges, and highlight promising research directions, aiming to provide a coherent and foundational reference for advancing the field. A systematic summary of existing literature is available at https://github.com/worldbench/survey</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.07996</guid>
|
|
<pubDate>Thu, 04 Sep 2025 17:59:58 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Why Language Models Hallucinate</title>
|
|
<link>https://arxiv.org/abs/2509.04664</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.04664.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Adam Tauman Kalai, Ofir Nachum, Santosh S. Vempala, Edwin Zhang</p><p><b>Upvotes:</b> 181</p><p><b>Summary:</b> Like students facing hard exam questions, large language models sometimes guess when uncertain, producing plausible yet incorrect statements instead of admitting uncertainty. Such "hallucinations" persist even in state-of-the-art systems and undermine trust. We argue that language models hallucinate because the training and evaluation procedures reward guessing over acknowledging uncertainty, and we analyze the statistical causes of hallucinations in the modern training pipeline. Hallucinations need not be mysterious -- they originate simply as errors in binary classification. If incorrect statements cannot be distinguished from facts, then hallucinations in pretrained language models will arise through natural statistical pressures. We then argue that hallucinations persist due to the way most evaluations are graded -- language models are optimized to be good test-takers, and guessing when uncertain improves test performance. This "epidemic" of penalizing uncertain responses can only be addressed through a socio-technical mitigation: modifying the scoring of existing benchmarks that are misaligned but dominate leaderboards, rather than introducing additional hallucination evaluations. This change may steer the field toward more trustworthy AI systems.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.04664</guid>
|
|
<pubDate>Thu, 04 Sep 2025 21:26:31 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Symbolic Graphics Programming with Large Language Models</title>
|
|
<link>https://arxiv.org/abs/2509.05208</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.05208.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yamei Chen, Haoquan Zhang, Yangyi Huang, Zeju Qiu, Kaipeng Zhang, Yandong Wen, Weiyang Liu</p><p><b>Upvotes:</b> 45</p><p><b>Summary:</b> Large language models (LLMs) excel at program synthesis, yet their ability to produce symbolic graphics programs (SGPs) that render into precise visual content remains underexplored. We study symbolic graphics programming, where the goal is to generate an SGP from a natural-language description. This task also serves as a lens into how LLMs understand the visual world by prompting them to generate images rendered from SGPs. Among various SGPs, our paper sticks to scalable vector graphics (SVGs). We begin by examining the extent to which LLMs can generate SGPs. To this end, we introduce SGP-GenBench, a comprehensive benchmark covering object fidelity, scene fidelity, and compositionality (attribute binding, spatial relations, numeracy). On SGP-GenBench, we discover that frontier proprietary models substantially outperform open-source models, and performance correlates well with general coding capabilities. Motivated by this gap, we aim to improve LLMs' ability to generate SGPs. We propose a reinforcement learning (RL) with verifiable rewards approach, where a format-validity gate ensures renderable SVG, and a cross-modal reward aligns text and the rendered image via strong vision encoders (e.g., SigLIP for text-image and DINO for image-image). Applied to Qwen-2.5-7B, our method substantially improves SVG generation quality and semantics, achieving performance on par with frontier systems. We further analyze training dynamics, showing that RL induces (i) finer decomposition of objects into controllable primitives and (ii) contextual details that improve scene coherence. Our results demonstrate that symbolic graphics programming offers a precise and interpretable lens on cross-modal grounding.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.05208</guid>
|
|
<pubDate>Fri, 05 Sep 2025 16:10:53 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Reverse-Engineered Reasoning for Open-Ended Generation</title>
|
|
<link>https://arxiv.org/abs/2509.06160</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.06160.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haozhe Wang, Haoran Que, Qixin Xu, Minghao Liu, Wangchunshu Zhou, Jiazhan Feng, Wanjun Zhong, Wei Ye, Tong Yang, Wenhao Huang, Ge Zhang, Fangzhen Lin</p><p><b>Upvotes:</b> 145</p><p><b>Summary:</b> While the ``deep reasoning'' paradigm has spurred significant advances in verifiable domains like mathematics, its application to open-ended, creative generation remains a critical challenge. The two dominant methods for instilling reasoning -- reinforcement learning (RL) and instruction distillation -- falter in this area; RL struggles with the absence of clear reward signals and high-quality reward models, while distillation is prohibitively expensive and capped by the teacher model's capabilities. To overcome these limitations, we introduce REverse-Engineered Reasoning (REER), a new paradigm that fundamentally shifts the approach. Instead of building a reasoning process ``forwards'' through trial-and-error or imitation, REER works ``backwards'' from known-good solutions to computationally discover the latent, step-by-step deep reasoning process that could have produced them. Using this scalable, gradient-free approach, we curate and open-source DeepWriting-20K, a large-scale dataset of 20,000 deep reasoning trajectories for open-ended tasks. Our model, DeepWriter-8B, trained on this data, not only surpasses strong open-source baselines but also achieves performance competitive with, and at times superior to, leading proprietary models like GPT-4o and Claude 3.5.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.06160</guid>
|
|
<pubDate>Sun, 07 Sep 2025 18:07:58 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Does DINOv3 Set a New Medical Vision Standard?</title>
|
|
<link>https://arxiv.org/abs/2509.06467</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.06467.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Che Liu, Yinda Chen, Haoyuan Shi, Jinpeng Lu, Bailiang Jian, Jiazhen Pan, Linghan Cai, Jiayi Wang, Yundi Zhang, Jun Li, Cosmin I. Bercea, Cheng Ouyang, Chen Chen, Zhiwei Xiong, Benedikt Wiestler, Christian Wachinger, Daniel Rueckert, Wenjia Bai, Rossella Arcucci</p><p><b>Upvotes:</b> 36</p><p><b>Summary:</b> The advent of large-scale vision foundation models, pre-trained on diverse natural images, has marked a paradigm shift in computer vision. However, how the frontier vision foundation models' efficacies transfer to specialized domains remains such as medical imaging remains an open question. This report investigates whether DINOv3, a state-of-the-art self-supervised vision transformer (ViT) that features strong capability in dense prediction tasks, can directly serve as a powerful, unified encoder for medical vision tasks without domain-specific pre-training. To answer this, we benchmark DINOv3 across common medical vision tasks, including 2D/3D classification and segmentation on a wide range of medical imaging modalities. We systematically analyze its scalability by varying model sizes and input image resolutions. Our findings reveal that DINOv3 shows impressive performance and establishes a formidable new baseline. Remarkably, it can even outperform medical-specific foundation models like BiomedCLIP and CT-Net on several tasks, despite being trained solely on natural images. However, we identify clear limitations: The model's features degrade in scenarios requiring deep domain specialization, such as in Whole-Slide Pathological Images (WSIs), Electron Microscopy (EM), and Positron Emission Tomography (PET). Furthermore, we observe that DINOv3 does not consistently obey scaling law in the medical domain; performance does not reliably increase with larger models or finer feature resolutions, showing diverse scaling behaviors across tasks. Ultimately, our work establishes DINOv3 as a strong baseline, whose powerful visual features can serve as a robust prior for multiple complex medical tasks. This opens promising future directions, such as leveraging its features to enforce multiview consistency in 3D reconstruction.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.06467</guid>
|
|
<pubDate>Mon, 08 Sep 2025 09:28:57 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents</title>
|
|
<link>https://arxiv.org/abs/2509.06501</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.06501.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junteng Liu, Yunji Li, Chi Zhang, Jingyang Li, Aili Chen, Ke Ji, Weiyu Cheng, Zijia Wu, Chengyu Du, Qidi Xu, Jiayuan Song, Zhengmao Zhu, Wenhu Chen, Pengyu Zhao, Junxian He</p><p><b>Upvotes:</b> 77</p><p><b>Summary:</b> The paradigm of Large Language Models (LLMs) has increasingly shifted toward agentic applications, where web browsing capabilities are fundamental for retrieving information from diverse online sources. However, existing open-source web agents either demonstrate limited information-seeking abilities on complex tasks or lack transparent implementations. In this work, we identify that the key challenge lies in the scarcity of challenging data for information seeking. To address this limitation, we introduce WebExplorer: a systematic data generation approach using model-based exploration and iterative, long-to-short query evolution. This method creates challenging query-answer pairs that require multi-step reasoning and complex web navigation. By leveraging our curated high-quality dataset, we successfully develop advanced web agent WebExplorer-8B through supervised fine-tuning followed by reinforcement learning. Our model supports 128K context length and up to 100 tool calling turns, enabling long-horizon problem solving. Across diverse information-seeking benchmarks, WebExplorer-8B achieves the state-of-the-art performance at its scale. Notably, as an 8B-sized model, WebExplorer-8B is able to effectively search over an average of 16 turns after RL training, achieving higher accuracy than WebSailor-72B on BrowseComp-en/zh and attaining the best performance among models up to 100B parameters on WebWalkerQA and FRAMES. Beyond these information-seeking tasks, our model also achieves strong generalization on the HLE benchmark even though it is only trained on knowledge-intensive QA data. These results highlight our approach as a practical path toward long-horizon web agents.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.06501</guid>
|
|
<pubDate>Mon, 08 Sep 2025 10:07:03 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Reinforcement Learning Foundations for Deep Research Systems: A Survey</title>
|
|
<link>https://arxiv.org/abs/2509.06733</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.06733.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wenjun Li, Zhi Chen, Jingru Lin, Hannan Cao, Wei Han, Sheng Liang, Zhi Zhang, Kuicai Dong, Dexun Li, Chen Zhang, Yong Liu</p><p><b>Upvotes:</b> 31</p><p><b>Summary:</b> Deep research systems, agentic AI that solve complex, multi-step tasks by coordinating reasoning, search across the open web and user files, and tool use, are moving toward hierarchical deployments with a Planner, Coordinator, and Executors. In practice, training entire stacks end-to-end remains impractical, so most work trains a single planner connected to core tools such as search, browsing, and code. While SFT imparts protocol fidelity, it suffers from imitation and exposure biases and underuses environment feedback. Preference alignment methods such as DPO are schema and proxy-dependent, off-policy, and weak for long-horizon credit assignment and multi-objective trade-offs. A further limitation of SFT and DPO is their reliance on human defined decision points and subskills through schema design and labeled comparisons. Reinforcement learning aligns with closed-loop, tool-interaction research by optimizing trajectory-level policies, enabling exploration, recovery behaviors, and principled credit assignment, and it reduces dependence on such human priors and rater biases. This survey is, to our knowledge, the first dedicated to the RL foundations of deep research systems. It systematizes work after DeepSeek-R1 along three axes: (i) data synthesis and curation; (ii) RL methods for agentic research covering stability, sample efficiency, long context handling, reward and credit design, multi-objective optimization, and multimodal integration; and (iii) agentic RL training systems and frameworks. We also cover agent architecture and coordination, as well as evaluation and benchmarks, including recent QA, VQA, long-form synthesis, and domain-grounded, tool-interaction tasks. We distill recurring patterns, surface infrastructure bottlenecks, and offer practical guidance for training robust, transparent deep research agents with RL.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.06733</guid>
|
|
<pubDate>Mon, 08 Sep 2025 14:27:23 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>MachineLearningLM: Continued Pretraining Language Models on Millions of Synthetic Tabular Prediction Tasks Scales In-Context ML</title>
|
|
<link>https://arxiv.org/abs/2509.06806</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.06806.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haoyu Dong, Pengkun Zhang, Mingzhe Lu, Yanzhen Shen, Guolin Ke</p><p><b>Upvotes:</b> 63</p><p><b>Summary:</b> Large language models (LLMs) possess broad world knowledge and strong general-purpose reasoning ability, yet they struggle to learn from many in-context examples on standard machine learning (ML) tasks, that is, to leverage many-shot demonstrations purely via in-context learning (ICL) without gradient descent. We introduce MachineLearningLM, a portable continued-pretraining framework that equips a general-purpose LLM with robust in-context ML capability while preserving its general knowledge and reasoning for broader chat workflows. Our pretraining procedure synthesizes ML tasks from millions of structural causal models (SCMs), spanning shot counts up to 1,024. We begin with a random-forest teacher, distilling tree-based decision strategies into the LLM to strengthen robustness in numerical modeling. All tasks are serialized with a token-efficient prompt, enabling 3x to 6x more examples per context window and delivering up to 50x amortized throughput via batch inference. Despite a modest setup (Qwen-2.5-7B-Instruct with LoRA rank 8), MachineLearningLM outperforms strong LLM baselines (e.g., GPT-5-mini) by an average of about 15% on out-of-distribution tabular classification across finance, physics, biology, and healthcare domains. It exhibits a striking many-shot scaling law: accuracy increases monotonically as in-context demonstrations grow from 8 to 1,024. Without any task-specific training, it attains random-forest-level accuracy across hundreds of shots. General chat capabilities, including knowledge and reasoning, are preserved: it achieves 75.4% on MMLU.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.06806</guid>
|
|
<pubDate>Mon, 08 Sep 2025 15:38:31 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Paper2Agent: Reimagining Research Papers As Interactive and Reliable AI Agents</title>
|
|
<link>https://arxiv.org/abs/2509.06917</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.06917.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiacheng Miao, Joe R. Davis, Jonathan K. Pritchard, James Zou</p><p><b>Upvotes:</b> 32</p><p><b>Summary:</b> We introduce Paper2Agent, an automated framework that converts research papers into AI agents. Paper2Agent transforms research output from passive artifacts into active systems that can accelerate downstream use, adoption, and discovery. Conventional research papers require readers to invest substantial effort to understand and adapt a paper's code, data, and methods to their own work, creating barriers to dissemination and reuse. Paper2Agent addresses this challenge by automatically converting a paper into an AI agent that acts as a knowledgeable research assistant. It systematically analyzes the paper and the associated codebase using multiple agents to construct a Model Context Protocol (MCP) server, then iteratively generates and runs tests to refine and robustify the resulting MCP. These paper MCPs can then be flexibly connected to a chat agent (e.g. Claude Code) to carry out complex scientific queries through natural language while invoking tools and workflows from the original paper. We demonstrate Paper2Agent's effectiveness in creating reliable and capable paper agents through in-depth case studies. Paper2Agent created an agent that leverages AlphaGenome to interpret genomic variants and agents based on ScanPy and TISSUE to carry out single-cell and spatial transcriptomics analyses. We validate that these paper agents can reproduce the original paper's results and can correctly carry out novel user queries. By turning static papers into dynamic, interactive AI agents, Paper2Agent introduces a new paradigm for knowledge dissemination and a foundation for the collaborative ecosystem of AI co-scientists.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.06917</guid>
|
|
<pubDate>Mon, 08 Sep 2025 17:28:42 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models</title>
|
|
<link>https://arxiv.org/abs/2509.06949</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.06949.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yinjie Wang, Ling Yang, Bowen Li, Ye Tian, Ke Shen, Mengdi Wang</p><p><b>Upvotes:</b> 55</p><p><b>Summary:</b> We propose TraceRL, a trajectory-aware reinforcement learning framework for diffusion language models (DLMs) that incorporates preferred inference trajectory into post-training, and is applicable across different architectures. Equipped with a diffusion-based value model that enhances training stability, we demonstrate improved reasoning performance on complex math and coding tasks. Besides, it can also be applied to adapt block-specific models to larger blocks, which improves sampling flexibility. Employing TraceRL, we derive a series of state-of-the-art diffusion language models, namely TraDo. Although smaller than 7B-scale AR models, TraDo-4B-Instruct still consistently outperforms them across complex math reasoning tasks. TraDo-8B-Instruct achieves relative accuracy improvements of 6.1% over Qwen2.5-7B-Instruct and 51.3% over Llama3.1-8B-Instruct on mathematical reasoning benchmarks. Through curriculum learning, we also derive the first long-CoT DLM, outperforming Qwen2.5-7B-Instruct on MATH500 with an 18.1% relative accuracy gain. To facilitate reproducible research and practical applications, we release a comprehensive open-source framework for building, training, and deploying diffusion LLMs across diverse architectures. The framework integrates accelerated KV-cache techniques and inference engines for both inference and reinforcement learning, and includes implementations of various supervised fine-tuning and RL methods for mathematics, coding, and general tasks. Code and Models: https://github.com/Gen-Verse/dLLM-RL</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.06949</guid>
|
|
<pubDate>Mon, 08 Sep 2025 17:58:06 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Reconstruction Alignment Improves Unified Multimodal Models</title>
|
|
<link>https://arxiv.org/abs/2509.07295</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.07295.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ji Xie, Trevor Darrell, Luke Zettlemoyer, XuDong Wang</p><p><b>Upvotes:</b> 39</p><p><b>Summary:</b> Unified multimodal models (UMMs) unify visual understanding and generation within a single architecture. However, conventional training relies on image-text pairs (or sequences) whose captions are typically sparse and miss fine-grained visual details--even when they use hundreds of words to describe a simple image. We introduce Reconstruction Alignment (RecA), a resource-efficient post-training method that leverages visual understanding encoder embeddings as dense "text prompts," providing rich supervision without captions. Concretely, RecA conditions a UMM on its own visual understanding embeddings and optimizes it to reconstruct the input image with a self-supervised reconstruction loss, thereby realigning understanding and generation. Despite its simplicity, RecA is broadly applicable: across autoregressive, masked-autoregressive, and diffusion-based UMMs, it consistently improves generation and editing fidelity. With only 27 GPU-hours, post-training with RecA substantially improves image generation performance on GenEval (0.73rightarrow0.90) and DPGBench (80.93rightarrow88.15), while also boosting editing benchmarks (ImgEdit 3.38rightarrow3.75, GEdit 6.94rightarrow7.25). Notably, RecA surpasses much larger open-source models and applies broadly across diverse UMM architectures, establishing it as an efficient and general post-training alignment strategy for UMMs</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.07295</guid>
|
|
<pubDate>Mon, 08 Sep 2025 23:59:32 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search</title>
|
|
<link>https://arxiv.org/abs/2509.07969</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.07969.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xin Lai, Junyi Li, Wei Li, Tao Liu, Tianjian Li, Hengshuang Zhao</p><p><b>Upvotes:</b> 59</p><p><b>Summary:</b> Recent advances in large multimodal models have leveraged image-based tools with reinforcement learning to tackle visual problems. However, existing open-source approaches often exhibit monotonous reasoning patterns and allow only a limited number of interaction turns, making them inadequate for difficult tasks that require trial-and-error exploration. In this work, we address this limitation by scaling up tool-based interactions and introduce Mini-o3, a system that executes deep, multi-turn reasoning -- spanning tens of steps -- and achieves state-of-the-art performance on challenging visual search tasks. Our recipe for reproducing OpenAI o3-style behaviors comprises three key components. First, we construct the Visual Probe Dataset, a collection of thousands of challenging visual search problems designed for exploratory reasoning. Second, we develop an iterative data collection pipeline to obtain cold-start trajectories that exhibit diverse reasoning patterns, including depth-first search, trial-and-error, and goal maintenance. Third, we propose an over-turn masking strategy that prevents penalization of over-turn responses (those that hit the maximum number of turns) during reinforcement learning, thereby balancing training-time efficiency with test-time scalability. Despite training with an upper bound of only six interaction turns, our model generates trajectories that naturally scale to tens of turns at inference time, with accuracy improving as the number of turns increases. Extensive experiments demonstrate that Mini-o3 produces rich reasoning patterns and deep thinking paths, effectively solving challenging visual search problems.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.07969</guid>
|
|
<pubDate>Tue, 09 Sep 2025 17:54:21 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Visual Representation Alignment for Multimodal Large Language Models</title>
|
|
<link>https://arxiv.org/abs/2509.07979</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.07979.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Heeji Yoon, Jaewoo Jung, Junwan Kim, Hyungyu Choi, Heeseong Shin, Sangbeom Lim, Honggyu An, Chaehyun Kim, Jisang Han, Donghyun Kim, Chanho Eom, Sunghwan Hong, Seungryong Kim</p><p><b>Upvotes:</b> 81</p><p><b>Summary:</b> Multimodal large language models (MLLMs) trained with visual instruction tuning have achieved strong performance across diverse tasks, yet they remain limited in vision-centric tasks such as object counting or spatial reasoning. We attribute this gap to the prevailing text-only supervision paradigm, which provides only indirect guidance for the visual pathway and often leads MLLMs to discard fine-grained visual details during training. In this paper, we present VIsual Representation ALignment (VIRAL), a simple yet effective regularization strategy that aligns the internal visual representations of MLLMs with those of pre-trained vision foundation models (VFMs). By explicitly enforcing this alignment, VIRAL enables the model not only to retain critical visual details from the input vision encoder but also to complement additional visual knowledge from VFMs, thereby enhancing its ability to reason over complex visual inputs. Our experiments demonstrate consistent improvements across all tasks on widely adopted multimodal benchmarks. Furthermore, we conduct comprehensive ablation studies to validate the key design choices underlying our framework. We believe this simple finding opens up an important direction for the effective integration of visual information in training MLLMs.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.07979</guid>
|
|
<pubDate>Tue, 09 Sep 2025 17:59:14 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Parallel-R1: Towards Parallel Thinking via Reinforcement Learning</title>
|
|
<link>https://arxiv.org/abs/2509.07980</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.07980.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tong Zheng, Hongming Zhang, Wenhao Yu, Xiaoyang Wang, Xinyu Yang, Runpeng Dai, Rui Liu, Huiwen Bao, Chengsong Huang, Heng Huang, Dong Yu</p><p><b>Upvotes:</b> 96</p><p><b>Summary:</b> Parallel thinking has emerged as a novel approach for enhancing the reasoning capabilities of large language models (LLMs) by exploring multiple reasoning paths concurrently. However, activating such capabilities through training remains challenging, as existing methods predominantly rely on supervised fine-tuning (SFT) over synthetic data, which encourages teacher-forced imitation rather than exploration and generalization. Different from them, we propose Parallel-R1, the first reinforcement learning (RL) framework that enables parallel thinking behaviors for complex real-world reasoning tasks. Our framework employs a progressive curriculum that explicitly addresses the cold-start problem in training parallel thinking with RL. We first use SFT on prompt-generated trajectories from easier tasks to instill the parallel thinking ability, then transition to RL to explore and generalize this skill on harder problems. Experiments on various math benchmarks, including MATH, AMC23, and AIME, show that Parallel-R1 successfully instills parallel thinking, leading to 8.4% accuracy improvements over the sequential thinking model trained directly on challenging tasks with RL. Further analysis reveals a clear shift in the model's thinking behavior: at an early stage, it uses parallel thinking as an exploration strategy, while in a later stage, it uses the same capability for multi-perspective verification. Most significantly, we validate parallel thinking as a mid-training exploration scaffold, where this temporary exploratory phase unlocks a higher performance ceiling after RL, yielding a 42.9% improvement over the baseline on AIME25. Our model, data, and code will be open-source at https://github.com/zhengkid/Parallel-R1.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.07980</guid>
|
|
<pubDate>Tue, 09 Sep 2025 17:59:35 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning</title>
|
|
<link>https://arxiv.org/abs/2509.08519</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.08519.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Liyang Chen, Tianxiang Ma, Jiawei Liu, Bingchuan Li, Zhuowei Chen, Lijie Liu, Xu He, Gen Li, Qian He, Zhiyong Wu</p><p><b>Upvotes:</b> 123</p><p><b>Summary:</b> Human-Centric Video Generation (HCVG) methods seek to synthesize human videos from multimodal inputs, including text, image, and audio. Existing methods struggle to effectively coordinate these heterogeneous modalities due to two challenges: the scarcity of training data with paired triplet conditions and the difficulty of collaborating the sub-tasks of subject preservation and audio-visual sync with multimodal inputs. In this work, we present HuMo, a unified HCVG framework for collaborative multimodal control. For the first challenge, we construct a high-quality dataset with diverse and paired text, reference images, and audio. For the second challenge, we propose a two-stage progressive multimodal training paradigm with task-specific strategies. For the subject preservation task, to maintain the prompt following and visual generation abilities of the foundation model, we adopt the minimal-invasive image injection strategy. For the audio-visual sync task, besides the commonly adopted audio cross-attention layer, we propose a focus-by-predicting strategy that implicitly guides the model to associate audio with facial regions. For joint learning of controllabilities across multimodal inputs, building on previously acquired capabilities, we progressively incorporate the audio-visual sync task. During inference, for flexible and fine-grained multimodal control, we design a time-adaptive Classifier-Free Guidance strategy that dynamically adjusts guidance weights across denoising steps. Extensive experimental results demonstrate that HuMo surpasses specialized state-of-the-art methods in sub-tasks, establishing a unified framework for collaborative multimodal-conditioned HCVG. Project Page: https://phantom-video.github.io/HuMo.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.08519</guid>
|
|
<pubDate>Wed, 10 Sep 2025 11:54:29 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Sharing is Caring: Efficient LM Post-Training with Collective RL Experience Sharing</title>
|
|
<link>https://arxiv.org/abs/2509.08721</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.08721.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jeffrey Amico, Gabriel Passamani Andrade, John Donaghy, Ben Fielding, Tristin Forbus, Harry Grieve, Semih Kara, Jari Kolehmainen, Yihua Lou, Christopher Nies, Edward Phillip Flores Nuño, Diogo Ortega, Shikhar Rastogi, Austin Virts, Matthew J. Wright</p><p><b>Upvotes:</b> 637</p><p><b>Summary:</b> Post-training language models (LMs) with reinforcement learning (RL) can enhance their complex reasoning capabilities without supervised fine-tuning, as demonstrated by DeepSeek-R1-Zero. However, effectively utilizing RL for LMs requires significant parallelization to scale-up inference, which introduces non-trivial technical challenges (e.g. latency, memory, and reliability) alongside ever-growing financial costs. We present Swarm sAmpling Policy Optimization (SAPO), a fully decentralized and asynchronous RL post-training algorithm. SAPO is designed for decentralized networks of heterogenous compute nodes, where each node manages its own policy model(s) while "sharing" rollouts with others in the network; no explicit assumptions about latency, model homogeneity, or hardware are required and nodes can operate in silo if desired. As a result, the algorithm avoids common bottlenecks in scaling RL post-training while also allowing (and even encouraging) new possibilities. By sampling rollouts "shared" across the network, it enables "Aha moments" to propagate, thereby bootstrapping the learning process. In this paper we show SAPO achieved cumulative reward gains of up to 94% in controlled experiments. We also share insights from tests on a network with thousands of nodes contributed by Gensyn community members running the algorithm on diverse hardware and models during an open-source demo.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.08721</guid>
|
|
<pubDate>Wed, 10 Sep 2025 16:14:20 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning</title>
|
|
<link>https://arxiv.org/abs/2509.08755</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.08755.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhiheng Xi, Jixuan Huang, Chenyang Liao, Baodai Huang, Honglin Guo, Jiaqi Liu, Rui Zheng, Junjie Ye, Jiazheng Zhang, Wenxiang Chen, Wei He, Yiwen Ding, Guanyu Li, Zehui Chen, Zhengyin Du, Xuesong Yao, Yufei Xu, Jiecao Chen, Tao Gui, Zuxuan Wu, Qi Zhang, Xuanjing Huang, Yu-Gang Jiang</p><p><b>Upvotes:</b> 54</p><p><b>Summary:</b> Developing autonomous LLM agents capable of making a series of intelligent decisions to solve complex, real-world tasks is a fast-evolving frontier. Like human cognitive development, agents are expected to acquire knowledge and skills through exploration and interaction with the environment. Despite advances, the community still lacks a unified, interactive reinforcement learning (RL) framework that can effectively train such agents from scratch -- without relying on supervised fine-tuning (SFT) -- across diverse and realistic environments. To bridge this gap, we introduce AgentGym-RL, a new framework to train LLM agents for multi-turn interactive decision-making through RL. The framework features a modular and decoupled architecture, ensuring high flexibility and extensibility. It encompasses a wide variety of real-world scenarios, and supports mainstream RL algorithms. Furthermore, we propose ScalingInter-RL, a training approach designed for exploration-exploitation balance and stable RL optimization. In early stages, it emphasizes exploitation by restricting the number of interactions, and gradually shifts towards exploration with larger horizons to encourage diverse problem-solving strategies. In this way, the agent develops more diverse behaviors and is less prone to collapse under long horizons. We perform extensive experiments to validate the stability and effectiveness of both the AgentGym-RL framework and the ScalingInter-RL approach. Our agents match or surpass commercial models on 27 tasks across diverse environments. We offer key insights and will open-source the complete AgentGym-RL framework -- including code and datasets -- to empower the research community in developing the next generation of intelligent agents.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.08755</guid>
|
|
<pubDate>Wed, 10 Sep 2025 16:46:11 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>RewardDance: Reward Scaling in Visual Generation</title>
|
|
<link>https://arxiv.org/abs/2509.08826</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.08826.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jie Wu, Yu Gao, Zilyu Ye, Ming Li, Liang Li, Hanzhong Guo, Jie Liu, Zeyue Xue, Xiaoxia Hou, Wei Liu, Yan Zeng, Weilin Huang</p><p><b>Upvotes:</b> 69</p><p><b>Summary:</b> Reward Models (RMs) are critical for improving generation models via Reinforcement Learning (RL), yet the RM scaling paradigm in visual generation remains largely unexplored. It primarily due to fundamental limitations in existing approaches: CLIP-based RMs suffer from architectural and input modality constraints, while prevalent Bradley-Terry losses are fundamentally misaligned with the next-token prediction mechanism of Vision-Language Models (VLMs), hindering effective scaling. More critically, the RLHF optimization process is plagued by Reward Hacking issue, where models exploit flaws in the reward signal without improving true quality. To address these challenges, we introduce RewardDance, a scalable reward modeling framework that overcomes these barriers through a novel generative reward paradigm. By reformulating the reward score as the model's probability of predicting a "yes" token, indicating that the generated image outperforms a reference image according to specific criteria, RewardDance intrinsically aligns reward objectives with VLM architectures. This alignment unlocks scaling across two dimensions: (1) Model Scaling: Systematic scaling of RMs up to 26 billion parameters; (2) Context Scaling: Integration of task-specific instructions, reference examples, and chain-of-thought (CoT) reasoning. Extensive experiments demonstrate that RewardDance significantly surpasses state-of-the-art methods in text-to-image, text-to-video, and image-to-video generation. Crucially, we resolve the persistent challenge of "reward hacking": Our large-scale RMs exhibit and maintain high reward variance during RL fine-tuning, proving their resistance to hacking and ability to produce diverse, high-quality outputs. It greatly relieves the mode collapse problem that plagues smaller models.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.08826</guid>
|
|
<pubDate>Wed, 10 Sep 2025 17:59:31 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>A Survey of Reinforcement Learning for Large Reasoning Models</title>
|
|
<link>https://arxiv.org/abs/2509.08827</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.08827.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kaiyan Zhang, Yuxin Zuo, Bingxiang He, Youbang Sun, Runze Liu, Che Jiang, Yuchen Fan, Kai Tian, Guoli Jia, Pengfei Li, Yu Fu, Xingtai Lv, Yuchen Zhang, Sihang Zeng, Shang Qu, Haozhan Li, Shijie Wang, Yuru Wang, Xinwei Long, Fangfu Liu, Xiang Xu, Jiaze Ma, Xuekai Zhu, Ermo Hua, Yihao Liu, Zonglin Li, Huayu Chen, Xiaoye Qu, Yafu Li, Weize Chen, Zhenzhao Yuan, Junqi Gao, Dong Li, Zhiyuan Ma, Ganqu Cui, Zhiyuan Liu, Biqing Qi, Ning Ding, Bowen Zhou</p><p><b>Upvotes:</b> 174</p><p><b>Summary:</b> In this paper, we survey recent advances in Reinforcement Learning (RL) for reasoning with Large Language Models (LLMs). RL has achieved remarkable success in advancing the frontier of LLM capabilities, particularly in addressing complex logical tasks such as mathematics and coding. As a result, RL has emerged as a foundational methodology for transforming LLMs into LRMs. With the rapid progress of the field, further scaling of RL for LRMs now faces foundational challenges not only in computational resources but also in algorithm design, training data, and infrastructure. To this end, it is timely to revisit the development of this domain, reassess its trajectory, and explore strategies to enhance the scalability of RL toward Artificial SuperIntelligence (ASI). In particular, we examine research applying RL to LLMs and LRMs for reasoning abilities, especially since the release of DeepSeek-R1, including foundational components, core problems, training resources, and downstream applications, to identify future opportunities and directions for this rapidly evolving area. We hope this review will promote future research on RL for broader reasoning models. Github: https://github.com/TsinghuaC3I/Awesome-RL-for-LRMs</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.08827</guid>
|
|
<pubDate>Wed, 10 Sep 2025 17:59:43 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>EchoX: Towards Mitigating Acoustic-Semantic Gap via Echo Training for Speech-to-Speech LLMs</title>
|
|
<link>https://arxiv.org/abs/2509.09174</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.09174.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuhao Zhang, Yuhao Du, Zhanchen Dai, Xiangnan Ma, Kaiqi Kou, Benyou Wang, Haizhou Li</p><p><b>Upvotes:</b> 57</p><p><b>Summary:</b> Speech-to-speech large language models (SLLMs) are attracting increasing attention. Derived from text-based large language models (LLMs), SLLMs often exhibit degradation in knowledge and reasoning capabilities. We hypothesize that this limitation arises because current training paradigms for SLLMs fail to bridge the acoustic-semantic gap in the feature representation space. To address this issue, we propose EchoX, which leverages semantic representations and dynamically generates speech training targets. This approach integrates both acoustic and semantic learning, enabling EchoX to preserve strong reasoning abilities as a speech LLM. Experimental results demonstrate that EchoX, with about six thousand hours of training data, achieves advanced performance on multiple knowledge-based question-answering benchmarks. The project is available at https://github.com/FreedomIntelligence/EchoX.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.09174</guid>
|
|
<pubDate>Thu, 11 Sep 2025 06:17:59 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents</title>
|
|
<link>https://arxiv.org/abs/2509.09265</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.09265.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiawei Wang, Jiacai Liu, Yuqian Fu, Yingru Li, Xintao Wang, Yuan Lin, Yu Yue, Lin Zhang, Yang Wang, Ke Wang</p><p><b>Upvotes:</b> 45</p><p><b>Summary:</b> In long-horizon tasks, recent agents based on Large Language Models (LLMs) face a significant challenge that sparse, outcome-based rewards make it difficult to assign credit to intermediate steps. Previous methods mainly focus on creating dense reward signals to guide learning, either through traditional reinforcement learning techniques like inverse reinforcement learning or by using Process Reward Models for step-by-step feedback. In this paper, we identify a fundamental problem in the learning dynamics of LLMs: the magnitude of policy gradients is inherently coupled with the entropy, which leads to inefficient small updates for confident correct actions and potentially destabilizes large updates for uncertain ones. To resolve this, we propose Entropy-Modulated Policy Gradients (EMPG), a framework that re-calibrates the learning signal based on step-wise uncertainty and the final task outcome. EMPG amplifies updates for confident correct actions, penalizes confident errors, and attenuates updates from uncertain steps to stabilize exploration. We further introduce a bonus term for future clarity that encourages agents to find more predictable solution paths. Through comprehensive experiments on three challenging agent tasks, WebShop, ALFWorld, and Deep Search, we demonstrate that EMPG achieves substantial performance gains and significantly outperforms strong policy gradient baselines. Project page is at https://empgseed-seed.github.io/</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.09265</guid>
|
|
<pubDate>Thu, 11 Sep 2025 08:50:01 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model</title>
|
|
<link>https://arxiv.org/abs/2509.09372</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.09372.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yihao Wang, Pengxiang Ding, Lingxiao Li, Can Cui, Zirui Ge, Xinyang Tong, Wenxuan Song, Han Zhao, Wei Zhao, Pengxu Hou, Siteng Huang, Yifan Tang, Wenhui Wang, Ru Zhang, Jianyi Liu, Donglin Wang</p><p><b>Upvotes:</b> 216</p><p><b>Summary:</b> Vision-Language-Action (VLA) models typically bridge the gap between perceptual and action spaces by pre-training a large-scale Vision-Language Model (VLM) on robotic data. While this approach greatly enhances performance, it also incurs significant training costs. In this paper, we investigate how to effectively bridge vision-language (VL) representations to action (A). We introduce VLA-Adapter, a novel paradigm designed to reduce the reliance of VLA models on large-scale VLMs and extensive pre-training. To this end, we first systematically analyze the effectiveness of various VL conditions and present key findings on which conditions are essential for bridging perception and action spaces. Based on these insights, we propose a lightweight Policy module with Bridge Attention, which autonomously injects the optimal condition into the action space. In this way, our method achieves high performance using only a 0.5B-parameter backbone, without any robotic data pre-training. Extensive experiments on both simulated and real-world robotic benchmarks demonstrate that VLA-Adapter not only achieves state-of-the-art level performance, but also offers the fast inference speed reported to date. Furthermore, thanks to the proposed advanced bridging paradigm, VLA-Adapter enables the training of a powerful VLA model in just 8 hours on a single consumer-grade GPU, greatly lowering the barrier to deploying the VLA model. Project page: https://vla-adapter.github.io/.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.09372</guid>
|
|
<pubDate>Thu, 11 Sep 2025 11:42:21 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Kling-Avatar: Grounding Multimodal Instructions for Cascaded Long-Duration Avatar Animation Synthesis</title>
|
|
<link>https://arxiv.org/abs/2509.09595</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.09595.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yikang Ding, Jiwen Liu, Wenyuan Zhang, Zekun Wang, Wentao Hu, Liyuan Cui, Mingming Lao, Yingchao Shao, Hui Liu, Xiaohan Li, Ming Chen, Xiaoqiang Liu, Yu-Shen Liu, Pengfei Wan</p><p><b>Upvotes:</b> 47</p><p><b>Summary:</b> Recent advances in audio-driven avatar video generation have significantly enhanced audio-visual realism. However, existing methods treat instruction conditioning merely as low-level tracking driven by acoustic or visual cues, without modeling the communicative purpose conveyed by the instructions. This limitation compromises their narrative coherence and character expressiveness. To bridge this gap, we introduce Kling-Avatar, a novel cascaded framework that unifies multimodal instruction understanding with photorealistic portrait generation. Our approach adopts a two-stage pipeline. In the first stage, we design a multimodal large language model (MLLM) director that produces a blueprint video conditioned on diverse instruction signals, thereby governing high-level semantics such as character motion and emotions. In the second stage, guided by blueprint keyframes, we generate multiple sub-clips in parallel using a first-last frame strategy. This global-to-local framework preserves fine-grained details while faithfully encoding the high-level intent behind multimodal instructions. Our parallel architecture also enables fast and stable generation of long-duration videos, making it suitable for real-world applications such as digital human livestreaming and vlogging. To comprehensively evaluate our method, we construct a benchmark of 375 curated samples covering diverse instructions and challenging scenarios. Extensive experiments demonstrate that Kling-Avatar is capable of generating vivid, fluent, long-duration videos at up to 1080p and 48 fps, achieving superior performance in lip synchronization accuracy, emotion and dynamic expressiveness, instruction controllability, identity preservation, and cross-domain generalization. These results establish Kling-Avatar as a new benchmark for semantically grounded, high-fidelity audio-driven avatar synthesis.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.09595</guid>
|
|
<pubDate>Thu, 11 Sep 2025 16:34:57 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning</title>
|
|
<link>https://arxiv.org/abs/2509.09674</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.09674.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haozhan Li, Yuxin Zuo, Jiale Yu, Yuhao Zhang, Zhaohui Yang, Kaiyan Zhang, Xuekai Zhu, Yuchen Zhang, Tianxing Chen, Ganqu Cui, Dehui Wang, Dingxiang Luo, Yuchen Fan, Youbang Sun, Jia Zeng, Jiangmiao Pang, Shanghang Zhang, Yu Wang, Yao Mu, Bowen Zhou, Ning Ding</p><p><b>Upvotes:</b> 76</p><p><b>Summary:</b> Vision-Language-Action (VLA) models have recently emerged as a powerful paradigm for robotic manipulation. Despite substantial progress enabled by large-scale pretraining and supervised fine-tuning (SFT), these models face two fundamental challenges: (i) the scarcity and high cost of large-scale human-operated robotic trajectories required for SFT scaling, and (ii) limited generalization to tasks involving distribution shift. Recent breakthroughs in Large Reasoning Models (LRMs) demonstrate that reinforcement learning (RL) can dramatically enhance step-by-step reasoning capabilities, raising a natural question: Can RL similarly improve the long-horizon step-by-step action planning of VLA? In this work, we introduce SimpleVLA-RL, an efficient RL framework tailored for VLA models. Building upon veRL, we introduce VLA-specific trajectory sampling, scalable parallelization, multi-environment rendering, and optimized loss computation. When applied to OpenVLA-OFT, SimpleVLA-RL achieves SoTA performance on LIBERO and even outperforms pi_0 on RoboTwin 1.0\&2.0 with the exploration-enhancing strategies we introduce. SimpleVLA-RL not only reduces dependence on large-scale data and enables robust generalization, but also remarkably surpasses SFT in real-world tasks. Moreover, we identify a novel phenomenon ``pushcut'' during RL training, wherein the policy discovers previously unseen patterns beyond those seen in the previous training process. Github: https://github.com/PRIME-RL/SimpleVLA-RL</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.09674</guid>
|
|
<pubDate>Thu, 11 Sep 2025 17:59:17 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>SpatialVID: A Large-Scale Video Dataset with Spatial Annotations</title>
|
|
<link>https://arxiv.org/abs/2509.09676</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.09676.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiahao Wang, Yufeng Yuan, Rujie Zheng, Youtian Lin, Jian Gao, Lin-Zhuo Chen, Yajie Bao, Yi Zhang, Chang Zeng, Yanxi Zhou, Xiaoxiao Long, Hao Zhu, Zhaoxiang Zhang, Xun Cao, Yao Yao</p><p><b>Upvotes:</b> 31</p><p><b>Summary:</b> Significant progress has been made in spatial intelligence, spanning both spatial reconstruction and world exploration. However, the scalability and real-world fidelity of current models remain severely constrained by the scarcity of large-scale, high-quality training data. While several datasets provide camera pose information, they are typically limited in scale, diversity, and annotation richness, particularly for real-world dynamic scenes with ground-truth camera motion. To this end, we collect SpatialVID, a dataset consists of a large corpus of in-the-wild videos with diverse scenes, camera movements and dense 3D annotations such as per-frame camera poses, depth, and motion instructions. Specifically, we collect more than 21,000 hours of raw video, and process them into 2.7 million clips through a hierarchical filtering pipeline, totaling 7,089 hours of dynamic content. A subsequent annotation pipeline enriches these clips with detailed spatial and semantic information, including camera poses, depth maps, dynamic masks, structured captions, and serialized motion instructions. Analysis of SpatialVID's data statistics reveals a richness and diversity that directly foster improved model generalization and performance, establishing it as a key asset for the video and 3D vision research community.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.09676</guid>
|
|
<pubDate>Thu, 11 Sep 2025 17:59:31 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmark</title>
|
|
<link>https://arxiv.org/abs/2509.09680</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.09680.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Rongyao Fang, Aldrich Yu, Chengqi Duan, Linjiang Huang, Shuai Bai, Yuxuan Cai, Kun Wang, Si Liu, Xihui Liu, Hongsheng Li</p><p><b>Upvotes:</b> 42</p><p><b>Summary:</b> The advancement of open-source text-to-image (T2I) models has been hindered by the absence of large-scale, reasoning-focused datasets and comprehensive evaluation benchmarks, resulting in a performance gap compared to leading closed-source systems. To address this challenge, We introduce FLUX-Reason-6M and PRISM-Bench (Precise and Robust Image Synthesis Measurement Benchmark). FLUX-Reason-6M is a massive dataset consisting of 6 million high-quality FLUX-generated images and 20 million bilingual (English and Chinese) descriptions specifically designed to teach complex reasoning. The image are organized according to six key characteristics: Imagination, Entity, Text rendering, Style, Affection, and Composition, and design explicit Generation Chain-of-Thought (GCoT) to provide detailed breakdowns of image generation steps. The whole data curation takes 15,000 A100 GPU days, providing the community with a resource previously unattainable outside of large industrial labs. PRISM-Bench offers a novel evaluation standard with seven distinct tracks, including a formidable Long Text challenge using GCoT. Through carefully designed prompts, it utilizes advanced vision-language models for nuanced human-aligned assessment of prompt-image alignment and image aesthetics. Our extensive evaluation of 19 leading models on PRISM-Bench reveals critical performance gaps and highlights specific areas requiring improvement. Our dataset, benchmark, and evaluation code are released to catalyze the next wave of reasoning-oriented T2I generation. Project page: https://flux-reason-6m.github.io/ .</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.09680</guid>
|
|
<pubDate>Thu, 11 Sep 2025 17:59:59 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>UI-S1: Advancing GUI Automation via Semi-online Reinforcement Learning</title>
|
|
<link>https://arxiv.org/abs/2509.11543</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.11543.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhengxi Lu, Jiabo Ye, Fei Tang, Yongliang Shen, Haiyang Xu, Ziwei Zheng, Weiming Lu, Ming Yan, Fei Huang, Jun Xiao, Yueting Zhuang</p><p><b>Upvotes:</b> 46</p><p><b>Summary:</b> Graphical User Interface (GUI) agents have demonstrated remarkable progress in automating complex user interface interactions through reinforcement learning. However, current approaches face a fundamental dilemma: offline RL enables stable training on pre-collected trajectories, but struggles with multi-step task execution for lack of trajectory-level reward signals; online RL captures these signals through environment interaction, but suffers from sparse rewards and prohibitive deployment costs. To address it, we present Semi-online Reinforcement Learning, a novel paradigm that simulates online RL on offline trajectories. During each rollout process, we preserve the original model output within the multi-turn dialogue, where a Patch Module adaptively recovers the divergence between rollout and expert trajectories. To capture long-term training signals, Semi-online RL introduces discounted future returns into the reward computation and optimizes the policy with weighted step-level and episode-level advantages. We further introduce Semi-Online Performance (SOP), a metric that aligns better with true online performance, serving as a practical and effective proxy for real-world evaluation. Experiments show that ours Semi-online RL achieves SOTA performance among 7B models across four dynamic benchmarks, with significant gains over the base model (e.g., +12.0% on AndroidWorld, +23.8% on AITW), demonstrating significant progress in bridging the gap between offline training efficiency and online multi-turn reasoning. The code is available at https://github.com/X-PLUG/MobileAgent/tree/main/UI-S1.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.11543</guid>
|
|
<pubDate>Mon, 15 Sep 2025 03:24:08 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling</title>
|
|
<link>https://arxiv.org/abs/2509.12201</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.12201.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yang Zhou, Yifan Wang, Jianjun Zhou, Wenzheng Chang, Haoyu Guo, Zizun Li, Kaijing Ma, Xinyue Li, Yating Wang, Haoyi Zhu, Mingyu Liu, Dingning Liu, Jiange Yang, Zhoujie Fu, Junyi Chen, Chunhua Shen, Jiangmiao Pang, Kaipeng Zhang, Tong He</p><p><b>Upvotes:</b> 103</p><p><b>Summary:</b> The field of 4D world modeling - aiming to jointly capture spatial geometry and temporal dynamics - has witnessed remarkable progress in recent years, driven by advances in large-scale generative models and multimodal learning. However, the development of truly general 4D world models remains fundamentally constrained by the availability of high-quality data. Existing datasets and benchmarks often lack the dynamic complexity, multi-domain diversity, and spatial-temporal annotations required to support key tasks such as 4D geometric reconstruction, future prediction, and camera-control video generation. To address this gap, we introduce OmniWorld, a large-scale, multi-domain, multi-modal dataset specifically designed for 4D world modeling. OmniWorld consists of a newly collected OmniWorld-Game dataset and several curated public datasets spanning diverse domains. Compared with existing synthetic datasets, OmniWorld-Game provides richer modality coverage, larger scale, and more realistic dynamic interactions. Based on this dataset, we establish a challenging benchmark that exposes the limitations of current state-of-the-art (SOTA) approaches in modeling complex 4D environments. Moreover, fine-tuning existing SOTA methods on OmniWorld leads to significant performance gains across 4D reconstruction and video generation tasks, strongly validating OmniWorld as a powerful resource for training and evaluation. We envision OmniWorld as a catalyst for accelerating the development of general-purpose 4D world models, ultimately advancing machines' holistic understanding of the physical world.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.12201</guid>
|
|
<pubDate>Mon, 15 Sep 2025 17:59:19 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Hunyuan3D Studio: End-to-End AI Pipeline for Game-Ready 3D Asset Generation</title>
|
|
<link>https://arxiv.org/abs/2509.12815</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.12815.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Biwen Lei, Yang Li, Xinhai Liu, Shuhui Yang, Lixin Xu, Jingwei Huang, Ruining Tang, Haohan Weng, Jian Liu, Jing Xu, Zhen Zhou, Yiling Zhu, Jiankai Xing, Jiachen Xu, Changfeng Ma, Xinhao Yan, Yunhan Yang, Chunshi Wang, Duoteng Xu, Xueqi Ma, Yuguang Chen, Jing Li, Mingxin Yang, Sheng Zhang, Yifei Feng, Xin Huang, Di Luo, Zebin He, Puhua Jiang, Changrong Hu, Zihan Qin, Shiwei Miao, Haolin Liu, Yunfei Zhao, Zeqiang Lai, Qingxiang Lin, Zibo Zhao, Kunhong Li, Xianghui Yang, Huiwen Shi, Xin Yang, Yuxuan Wang, Zebin Yao, Yihang Lian, Sicong Liu, Xintong Han, Wangchen Qin, Caisheng Ouyang, Jianyin Liu, Tianwen Yuan, Shuai Jiang, Hong Duan, Yanqi Niu, Wencong Lin, Yifu Sun, Shirui Huang, Lin Niu, Gu Gong, Guojian Xiao, Bojian Zheng, Xiang Yuan, Qi Chen, Jie Xiao, Dongyang Zheng, Xiaofeng Yang, Kai Liu, Jianchen Zhu, Lifu Wang, Qinglin Lu, Jie Liu, Liang Dong, Fan Jiang, Ruibin Chen, Lei Wang, Chao Zhang, Jiaxin Lin, Hao Zhang, Zheng Ye, Peng He, Runzhou Wu, Yinhe Wu, Jiayao Du, Jupeng Chen, Xinyue Mao, Dongyuan Guo, Yixuan Tang, Yulin Tsai, Yonghao Tan, Jiaao Yu, Junlin Yu, Keren Zhang, Yifan Li, Peng Chen, Tian Liu, Di Wang, Yuhong Liu, Linus, Jie Jiang, Zhuo Chen, Chunchao Guo</p><p><b>Upvotes:</b> 38</p><p><b>Summary:</b> The creation of high-quality 3D assets, a cornerstone of modern game development, has long been characterized by labor-intensive and specialized workflows. This paper presents Hunyuan3D Studio, an end-to-end AI-powered content creation platform designed to revolutionize the game production pipeline by automating and streamlining the generation of game-ready 3D assets. At its core, Hunyuan3D Studio integrates a suite of advanced neural modules (such as Part-level 3D Generation, Polygon Generation, Semantic UV, etc.) into a cohesive and user-friendly system. This unified framework allows for the rapid transformation of a single concept image or textual description into a fully-realized, production-quality 3D model complete with optimized geometry and high-fidelity PBR textures. We demonstrate that assets generated by Hunyuan3D Studio are not only visually compelling but also adhere to the stringent technical requirements of contemporary game engines, significantly reducing iteration time and lowering the barrier to entry for 3D content creation. By providing a seamless bridge from creative intent to technical asset, Hunyuan3D Studio represents a significant leap forward for AI-assisted workflows in game development and interactive media.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.12815</guid>
|
|
<pubDate>Tue, 16 Sep 2025 08:33:03 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Single-stream Policy Optimization</title>
|
|
<link>https://arxiv.org/abs/2509.13232</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.13232.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhongwen Xu, Zihan Ding</p><p><b>Upvotes:</b> 34</p><p><b>Summary:</b> We revisit policy-gradient optimization for Large Language Models (LLMs) from a single-stream perspective. Prevailing group-based methods like GRPO reduce variance with on-the-fly baselines but suffer from critical flaws: frequent degenerate groups erase learning signals, and synchronization barriers hinder scalability. We introduce Single-stream Policy Optimization (SPO), which eliminates these issues by design. SPO replaces per-group baselines with a persistent, KL-adaptive value tracker and normalizes advantages globally across the batch, providing a stable, low-variance learning signal for every sample. Being group-free, SPO enables higher throughput and scales effectively in long-horizon or tool-integrated settings where generation times vary. Furthermore, the persistent value tracker naturally enables an adaptive curriculum via prioritized sampling. Experiments using Qwen3-8B show that SPO converges more smoothly and attains higher accuracy than GRPO, while eliminating computation wasted on degenerate groups. Ablation studies confirm that SPO's gains stem from its principled approach to baseline estimation and advantage normalization, offering a more robust and efficient path for LLM reasoning. Across five hard math benchmarks with Qwen3 8B, SPO improves the average maj@32 by +3.4 percentage points (pp) over GRPO, driven by substantial absolute point gains on challenging datasets, including +7.3 pp on BRUMO 25, +4.4 pp on AIME 25, +3.3 pp on HMMT 25, and achieves consistent relative gain in pass@k across the evaluated k values. SPO's success challenges the prevailing trend of adding incidental complexity to RL algorithms, highlighting a path where fundamental principles, not architectural workarounds, drive the next wave of progress in LLM reasoning.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.13232</guid>
|
|
<pubDate>Tue, 16 Sep 2025 16:39:11 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning</title>
|
|
<link>https://arxiv.org/abs/2509.13305</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.13305.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kuan Li, Zhongwang Zhang, Huifeng Yin, Rui Ye, Yida Zhao, Liwen Zhang, Litu Ou, Dingchu Zhang, Xixi Wu, Jialong Wu, Xinyu Wang, Zile Qiao, Zhen Zhang, Yong Jiang, Pengjun Xie, Fei Huang, Jingren Zhou</p><p><b>Upvotes:</b> 83</p><p><b>Summary:</b> Transcending human cognitive limitations represents a critical frontier in LLM training. Proprietary agentic systems like DeepResearch have demonstrated superhuman capabilities on extremely complex information-seeking benchmarks such as BrowseComp, a feat previously unattainable. We posit that their success hinges on a sophisticated reasoning pattern absent in open-source models: the ability to systematically reduce extreme uncertainty when navigating vast information landscapes. Based on this insight, we introduce WebSailor, a complete post-training methodology designed to instill this crucial capability. Our approach involves generating novel, high-uncertainty tasks through structured sampling and information obfuscation, RFT cold start, and an efficient agentic RL training algorithm, Duplicating Sampling Policy Optimization (DUPO). With this integrated pipeline, WebSailor significantly outperforms all open-source agents in complex information-seeking tasks, matching proprietary agents' performance and closing the capability gap.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.13305</guid>
|
|
<pubDate>Tue, 16 Sep 2025 17:57:03 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agents</title>
|
|
<link>https://arxiv.org/abs/2509.13309</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.13309.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zile Qiao, Guoxin Chen, Xuanzhong Chen, Donglei Yu, Wenbiao Yin, Xinyu Wang, Zhen Zhang, Baixuan Li, Huifeng Yin, Kuan Li, Rui Min, Minpeng Liao, Yong Jiang, Pengjun Xie, Fei Huang, Jingren Zhou</p><p><b>Upvotes:</b> 66</p><p><b>Summary:</b> Recent advances in deep-research systems have demonstrated the potential for AI agents to autonomously discover and synthesize knowledge from external sources. In this paper, we introduce WebResearcher, a novel framework for building such agents through two key components: (1) WebResearcher, an iterative deep-research paradigm that reformulates deep research as a Markov Decision Process, where agents periodically consolidate findings into evolving reports while maintaining focused workspaces, overcoming the context suffocation and noise contamination that plague existing mono-contextual approaches; and (2) WebFrontier, a scalable data synthesis engine that generates high-quality training data through tool-augmented complexity escalation, enabling systematic creation of research tasks that bridge the gap between passive knowledge recall and active knowledge construction. Notably, we find that the training data from our paradigm significantly enhances tool-use capabilities even for traditional mono-contextual methods. Furthermore, our paradigm naturally scales through parallel thinking, enabling concurrent multi-agent exploration for more comprehensive conclusions. Extensive experiments across 6 challenging benchmarks demonstrate that WebResearcher achieves state-of-the-art performance, even surpassing frontier proprietary systems.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.13309</guid>
|
|
<pubDate>Tue, 16 Sep 2025 17:57:17 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Scaling Agents via Continual Pre-training</title>
|
|
<link>https://arxiv.org/abs/2509.13310</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.13310.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Liangcai Su, Zhen Zhang, Guangyu Li, Zhuo Chen, Chenxi Wang, Maojia Song, Xinyu Wang, Kuan Li, Jialong Wu, Xuanzhong Chen, Zile Qiao, Zhongwang Zhang, Huifeng Yin, Shihao Cai, Runnan Fang, Zhengwei Tao, Wenbiao Yin, Chenxiong Qian, Yong Jiang, Pengjun Xie, Fei Huang, Jingren Zhou</p><p><b>Upvotes:</b> 107</p><p><b>Summary:</b> Large language models (LLMs) have evolved into agentic systems capable of autonomous tool use and multi-step reasoning for complex problem-solving. However, post-training approaches building upon general-purpose foundation models consistently underperform in agentic tasks, particularly in open-source implementations. We identify the root cause: the absence of robust agentic foundation models forces models during post-training to simultaneously learn diverse agentic behaviors while aligning them to expert demonstrations, thereby creating fundamental optimization tensions. To this end, we are the first to propose incorporating Agentic Continual Pre-training (Agentic CPT) into the deep research agents training pipeline to build powerful agentic foundational models. Based on this approach, we develop a deep research agent model named AgentFounder. We evaluate our AgentFounder-30B on 10 benchmarks and achieve state-of-the-art performance while retains strong tool-use ability, notably 39.9% on BrowseComp-en, 43.3% on BrowseComp-zh, and 31.5% Pass@1 on HLE.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.13310</guid>
|
|
<pubDate>Tue, 16 Sep 2025 17:57:19 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Towards General Agentic Intelligence via Environment Scaling</title>
|
|
<link>https://arxiv.org/abs/2509.13311</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.13311.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Runnan Fang, Shihao Cai, Baixuan Li, Jialong Wu, Guangyu Li, Wenbiao Yin, Xinyu Wang, Xiaobin Wang, Liangcai Su, Zhen Zhang, Shibin Wu, Zhengwei Tao, Yong Jiang, Pengjun Xie, Fei Huang, Jingren Zhou</p><p><b>Upvotes:</b> 68</p><p><b>Summary:</b> Advanced agentic intelligence is a prerequisite for deploying Large Language Models in practical, real-world applications. Diverse real-world APIs demand precise, robust function-calling intelligence, which needs agents to develop these capabilities through interaction in varied environments. The breadth of function-calling competence is closely tied to the diversity of environments in which agents are trained. In this work, we scale up environments as a step towards advancing general agentic intelligence. This gives rise to two central challenges: (i) how to scale environments in a principled manner, and (ii) how to effectively train agentic capabilities from experiences derived through interactions with these environments. To address these, we design a scalable framework that automatically constructs heterogeneous environments that are fully simulated, systematically broadening the space of function-calling scenarios. We further adapt a two-phase agent fine-tuning strategy: first endowing agents with fundamental agentic capabilities, then specializing them for domain-specific contexts. Extensive experiments on agentic benchmarks, tau-bench, tau2-Bench, and ACEBench, demonstrate that our trained model, AgentScaler, significantly enhances the function-calling capability of models.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.13311</guid>
|
|
<pubDate>Tue, 16 Sep 2025 17:57:20 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research</title>
|
|
<link>https://arxiv.org/abs/2509.13312</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.13312.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zijian Li, Xin Guan, Bo Zhang, Shen Huang, Houquan Zhou, Shaopeng Lai, Ming Yan, Yong Jiang, Pengjun Xie, Fei Huang, Jun Zhang, Jingren Zhou</p><p><b>Upvotes:</b> 100</p><p><b>Summary:</b> This paper tackles open-ended deep research (OEDR), a complex challenge where AI agents must synthesize vast web-scale information into insightful reports. Current approaches are plagued by dual-fold limitations: static research pipelines that decouple planning from evidence acquisition and one-shot generation paradigms that easily suffer from long-context failure issues like "loss in the middle" and hallucinations. To address these challenges, we introduce WebWeaver, a novel dual-agent framework that emulates the human research process. The planner operates in a dynamic cycle, iteratively interleaving evidence acquisition with outline optimization to produce a comprehensive, source-grounded outline linking to a memory bank of evidence. The writer then executes a hierarchical retrieval and writing process, composing the report section by section. By performing targeted retrieval of only the necessary evidence from the memory bank for each part, it effectively mitigates long-context issues. Our framework establishes a new state-of-the-art across major OEDR benchmarks, including DeepResearch Bench, DeepConsult, and DeepResearchGym. These results validate our human-centric, iterative methodology, demonstrating that adaptive planning and focused synthesis are crucial for producing high-quality, reliable, and well-structured reports.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.13312</guid>
|
|
<pubDate>Tue, 16 Sep 2025 17:57:21 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization</title>
|
|
<link>https://arxiv.org/abs/2509.13313</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.13313.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xixi Wu, Kuan Li, Yida Zhao, Liwen Zhang, Litu Ou, Huifeng Yin, Zhongwang Zhang, Yong Jiang, Pengjun Xie, Fei Huang, Minhao Cheng, Shuai Wang, Hong Cheng, Jingren Zhou</p><p><b>Upvotes:</b> 72</p><p><b>Summary:</b> Large Language Model (LLM)-based web agents demonstrate strong performance on knowledge-intensive tasks but are hindered by context window limitations in paradigms like ReAct. Complex queries involving multiple entities, intertwined relationships, and high uncertainty demand extensive search cycles that rapidly exhaust context budgets before reaching complete solutions. To overcome this challenge, we introduce ReSum, a novel paradigm that enables indefinite exploration through periodic context summarization. ReSum converts growing interaction histories into compact reasoning states, maintaining awareness of prior discoveries while bypassing context constraints. For paradigm adaptation, we propose ReSum-GRPO, integrating GRPO with segmented trajectory training and advantage broadcasting to familiarize agents with summary-conditioned reasoning. Extensive experiments on web agents of varying scales across three benchmarks demonstrate that ReSum delivers an average absolute improvement of 4.5\% over ReAct, with further gains of up to 8.2\% following ReSum-GRPO training. Notably, with only 1K training samples, our WebResummer-30B (a ReSum-GRPO-trained version of WebSailor-30B) achieves 33.3\% Pass@1 on BrowseComp-zh and 18.3\% on BrowseComp-en, surpassing existing open-source web agents.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.13313</guid>
|
|
<pubDate>Tue, 16 Sep 2025 17:57:22 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe</title>
|
|
<link>https://arxiv.org/abs/2509.18154</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.18154.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tianyu Yu, Zefan Wang, Chongyi Wang, Fuwei Huang, Wenshuo Ma, Zhihui He, Tianchi Cai, Weize Chen, Yuxiang Huang, Yuanqian Zhao, Bokai Xu, Junbo Cui, Yingjing Xu, Liqing Ruan, Luoyuan Zhang, Hanyu Liu, Jingkun Tang, Hongyuan Liu, Qining Guo, Wenhao Hu, Bingxiang He, Jie Zhou, Jie Cai, Ji Qi, Zonghao Guo, Chi Chen, Guoyang Zeng, Yuxuan Li, Ganqu Cui, Ning Ding, Xu Han, Yuan Yao, Zhiyuan Liu, Maosong Sun</p><p><b>Upvotes:</b> 46</p><p><b>Summary:</b> Multimodal Large Language Models (MLLMs) are undergoing rapid progress and represent the frontier of AI development. However, their training and inference efficiency have emerged as a core bottleneck in making MLLMs more accessible and scalable. To address the challenges, we present MiniCPM-V 4.5, an 8B parameter model designed for high efficiency and strong performance. We introduce three core improvements in model architecture, data strategy and training method: a unified 3D-Resampler model architecture for highly compact encoding over images and videos, a unified learning paradigm for document knowledge and text recognition without heavy data engineering, and a hybrid reinforcement learning strategy for proficiency in both short and long reasoning modes. Comprehensive experimental results in OpenCompass evaluation show that MiniCPM-V 4.5 surpasses widely used proprietary models such as GPT-4o-latest, and significantly larger open-source models such as Qwen2.5-VL 72B. Notably, the strong performance is achieved with remarkable efficiency. For example, on the widely adopted VideoMME benchmark, MiniCPM-V 4.5 achieves state-of-the-art performance among models under 30B size, using just 46.7\% GPU memory cost and 8.7\% inference time of Qwen2.5-VL 7B.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.18154</guid>
|
|
<pubDate>Tue, 16 Sep 2025 19:41:48 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Hala Technical Report: Building Arabic-Centric Instruction & Translation Models at Scale</title>
|
|
<link>https://arxiv.org/abs/2509.14008</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.14008.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hasan Abed Al Kader Hammoud, Mohammad Zbeeb, Bernard Ghanem</p><p><b>Upvotes:</b> 86</p><p><b>Summary:</b> We present Hala, a family of Arabic-centric instruction and translation models built with our translate-and-tune pipeline. We first compress a strong ARleftrightarrowEN teacher to FP8 (yielding sim2times higher throughput with no quality loss) and use it to create high-fidelity bilingual supervision. A lightweight language model LFM2-1.2B is then fine-tuned on this data and used to translate high-quality English instruction sets into Arabic, producing a million-scale corpus tailored to instruction following. We train Hala models at 350M, 700M, 1.2B, and 9B parameters, and apply slerp merging to balance Arabic specialization with base-model strengths. On Arabic-centric benchmarks, Hala achieves state-of-the-art results within both the "nano" (leq2B) and "small" (7-9B) categories, outperforming their bases. We release models, data, evaluation, and recipes to accelerate research in Arabic NLP.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.14008</guid>
|
|
<pubDate>Wed, 17 Sep 2025 14:19:28 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>SAIL-VL2 Technical Report</title>
|
|
<link>https://arxiv.org/abs/2509.14033</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.14033.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weijie Yin, Yongjie Ye, Fangxun Shu, Yue Liao, Zijian Kang, Hongyuan Dong, Haiyang Yu, Dingkang Yang, Jiacong Wang, Han Wang, Wenzhuo Liu, Xiao Liang, Shuicheng Yan, Chao Feng</p><p><b>Upvotes:</b> 43</p><p><b>Summary:</b> We introduce SAIL-VL2, an open-suite vision-language foundation model (LVM) for comprehensive multimodal understanding and reasoning. As the successor to SAIL-VL, SAIL-VL2 achieves state-of-the-art performance at the 2B and 8B parameter scales across diverse image and video benchmarks, demonstrating strong capabilities from fine-grained perception to complex reasoning. Three core innovations drive its effectiveness. First, a large-scale data curation pipeline with scoring and filtering strategies enhances both quality and distribution across captioning, OCR, QA, and video data, improving training efficiency. Second, a progressive training framework begins with a powerful pre-trained vision encoder (SAIL-ViT), advances through multimodal pre-training, and culminates in a thinking-fusion SFT-RL hybrid paradigm that systematically strengthens model capabilities. Third, architectural advances extend beyond dense LLMs to efficient sparse Mixture-of-Experts (MoE) designs. With these contributions, SAIL-VL2 demonstrates competitive performance across 106 datasets and achieves state-of-the-art results on challenging reasoning benchmarks such as MMMU and MathVista. Furthermore, on the OpenCompass leaderboard, SAIL-VL2-2B ranks first among officially released open-source models under the 4B parameter scale, while serving as an efficient and extensible foundation for the open-source multimodal community.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.14033</guid>
|
|
<pubDate>Wed, 17 Sep 2025 14:34:02 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Baseer: A Vision-Language Model for Arabic Document-to-Markdown OCR</title>
|
|
<link>https://arxiv.org/abs/2509.18174</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.18174.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Khalil Hennara, Muhammad Hreden, Mohamed Motasim Hamed, Ahmad Bastati, Zeina Aldallal, Sara Chrouf, Safwan AlModhayan</p><p><b>Upvotes:</b> 121</p><p><b>Summary:</b> Arabic document OCR remains a challenging task due to the language's cursive script, diverse fonts, diacritics, and right-to-left orientation. While modern Multimodal Large Language Models (MLLMs) have advanced document understanding for high-resource languages, their performance on Arabic remains limited. In this work, we introduce Baseer, a vision-language model fine- tuned specifically for Arabic document OCR. Leveraging a large-scale dataset combining synthetic and real-world documents, Baseer is trained using a decoder-only fine-tuning strategy to adapt a pre-trained MLLM while preserving general visual features. We also present Misraj-DocOCR, a high-quality, expert-verified benchmark designed for rigorous evaluation of Arabic OCR systems. Our experiments show that Baseer significantly outperforms existing open-source and commercial solutions, achieving a WER of 0.25 and establishing a new state-of-the-art in the domain of Arabic document OCR. Our results highlight the benefits of domain-specific adaptation of general-purpose MLLMs and establish a strong baseline for high-accuracy OCR on morphologically rich languages like Arabic.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.18174</guid>
|
|
<pubDate>Wed, 17 Sep 2025 15:07:29 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>AToken: A Unified Tokenizer for Vision</title>
|
|
<link>https://arxiv.org/abs/2509.14476</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.14476.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiasen Lu, Liangchen Song, Mingze Xu, Byeongjoo Ahn, Yanjun Wang, Chen Chen, Afshin Dehghan, Yinfei Yang</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> We present AToken, the first unified visual tokenizer that achieves both high-fidelity reconstruction and semantic understanding across images, videos, and 3D assets. Unlike existing tokenizers that specialize in either reconstruction or understanding for single modalities, AToken encodes these diverse visual inputs into a shared 4D latent space, unifying both tasks and modalities in a single framework. Specifically, we introduce a pure transformer architecture with 4D rotary position embeddings to process visual inputs of arbitrary resolutions and temporal durations. To ensure stable training, we introduce an adversarial-free training objective that combines perceptual and Gram matrix losses, achieving state-of-the-art reconstruction quality. By employing a progressive training curriculum, AToken gradually expands from single images, videos, and 3D, and supports both continuous and discrete latent tokens. AToken achieves 0.21 rFID with 82.2% ImageNet accuracy for images, 3.01 rFVD with 32.6% MSRVTT retrieval for videos, and 28.19 PSNR with 90.9% classification accuracy for 3D. In downstream applications, AToken enables both visual generation tasks (e.g., image generation with continuous and discrete tokens, text-to-video generation, image-to-3D synthesis) and understanding tasks (e.g., multimodal LLMs), achieving competitive performance across all benchmarks. These results shed light on the next-generation multimodal AI systems built upon unified visual tokenization.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.14476</guid>
|
|
<pubDate>Wed, 17 Sep 2025 23:11:18 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>SWE-QA: Can Language Models Answer Repository-level Code Questions?</title>
|
|
<link>https://arxiv.org/abs/2509.14635</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.14635.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weihan Peng, Yuling Shi, Yuhang Wang, Xinyun Zhang, Beijun Shen, Xiaodong Gu</p><p><b>Upvotes:</b> 34</p><p><b>Summary:</b> Understanding and reasoning about entire software repositories is an essential capability for intelligent software engineering tools. While existing benchmarks such as CoSQA and CodeQA have advanced the field, they predominantly focus on small, self-contained code snippets. These setups fail to capture the complexity of real-world repositories, where effective understanding and reasoning often require navigating multiple files, understanding software architecture, and grounding answers in long-range code dependencies. In this paper, we present SWE-QA, a repository-level code question answering (QA) benchmark designed to facilitate research on automated QA systems in realistic code environments. SWE-QA involves 576 high-quality question-answer pairs spanning diverse categories, including intention understanding, cross-file reasoning, and multi-hop dependency analysis. To construct SWE-QA, we first crawled 77,100 GitHub issues from 11 popular repositories. Based on an analysis of naturally occurring developer questions extracted from these issues, we developed a two-level taxonomy of repository-level questions and constructed a set of seed questions for each category. For each category, we manually curated and validated questions and collected their corresponding answers. As a prototype application, we further develop SWE-QA-Agent, an agentic framework in which LLM agents reason and act to find answers automatically. We evaluate six advanced LLMs on SWE-QA under various context augmentation strategies. Experimental results highlight the promise of LLMs, particularly our SWE-QA-Agent framework, in addressing repository-level QA, while also revealing open challenges and pointing to future research directions.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.14635</guid>
|
|
<pubDate>Thu, 18 Sep 2025 05:25:32 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Reasoning over Boundaries: Enhancing Specification Alignment via Test-time Delibration</title>
|
|
<link>https://arxiv.org/abs/2509.14760</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.14760.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haoran Zhang, Yafu Li, Xuyang Hu, Dongrui Liu, Zhilin Wang, Bo Li, Yu Cheng</p><p><b>Upvotes:</b> 50</p><p><b>Summary:</b> Large language models (LLMs) are increasingly applied in diverse real-world scenarios, each governed by bespoke behavioral and safety specifications (spec) custom-tailored by users or organizations. These spec, categorized into safety-spec and behavioral-spec, vary across scenarios and evolve with changing preferences and requirements. We formalize this challenge as specification alignment, focusing on LLMs' ability to follow dynamic, scenario-specific spec from both behavioral and safety perspectives. To address this challenge, we propose Align3, a lightweight method that employs Test-Time Deliberation (TTD) with hierarchical reflection and revision to reason over the specification boundaries. We further present SpecBench, a unified benchmark for measuring specification alignment, covering 5 scenarios, 103 spec, and 1,500 prompts. Experiments on 15 reasoning and 18 instruct models with several TTD methods, including Self-Refine, TPO, and MoreThink, yield three key findings: (i) test-time deliberation enhances specification alignment; (ii) Align3 advances the safety-helpfulness trade-off frontier with minimal overhead; (iii) SpecBench effectively reveals alignment gaps. These results highlight the potential of test-time deliberation as an effective strategy for reasoning over the real-world specification boundaries.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.14760</guid>
|
|
<pubDate>Thu, 18 Sep 2025 09:08:53 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation</title>
|
|
<link>https://arxiv.org/abs/2509.15194</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.15194.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yujun Zhou, Zhenwen Liang, Haolin Liu, Wenhao Yu, Kishan Panaganti, Linfeng Song, Dian Yu, Xiangliang Zhang, Haitao Mi, Dong Yu</p><p><b>Upvotes:</b> 32</p><p><b>Summary:</b> Large language models (LLMs) are increasingly trained with reinforcement learning from verifiable rewards (RLVR), yet real-world deployment demands models that can self-improve without labels or external judges. Existing label-free methods, confidence minimization, self-consistency, or majority-vote objectives, stabilize learning but steadily shrink exploration, causing an entropy collapse: generations become shorter, less diverse, and brittle. Unlike prior approaches such as Test-Time Reinforcement Learning (TTRL), which primarily adapt models to the immediate unlabeled dataset at hand, our goal is broader: to enable general improvements without sacrificing the model's inherent exploration capacity and generalization ability, i.e., evolving. We formalize this issue and propose EVolution-Oriented and Label-free Reinforcement Learning (EVOL-RL), a simple rule that couples stability with variation under a label-free setting. EVOL-RL keeps the majority-voted answer as a stable anchor (selection) while adding a novelty-aware reward that favors responses whose reasoning differs from what has already been produced (variation), measured in semantic space. Implemented with GRPO, EVOL-RL also uses asymmetric clipping to preserve strong signals and an entropy regularizer to sustain search. This majority-for-selection + novelty-for-variation design prevents collapse, maintains longer and more informative chains of thought, and improves both pass@1 and pass@n. EVOL-RL consistently outperforms the majority-only TTRL baseline; e.g., training on label-free AIME24 lifts Qwen3-4B-Base AIME25 pass@1 from TTRL's 4.6% to 16.4%, and pass@16 from 18.5% to 37.9%. EVOL-RL not only prevents diversity collapse but also unlocks stronger generalization across domains (e.g., GPQA). Furthermore, we demonstrate that EVOL-RL also boosts performance in the RLVR setting, highlighting its broad applicability.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.15194</guid>
|
|
<pubDate>Thu, 18 Sep 2025 17:50:04 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>FlowRL: Matching Reward Distributions for LLM Reasoning</title>
|
|
<link>https://arxiv.org/abs/2509.15207</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.15207.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xuekai Zhu, Daixuan Cheng, Dinghuai Zhang, Hengli Li, Kaiyan Zhang, Che Jiang, Youbang Sun, Ermo Hua, Yuxin Zuo, Xingtai Lv, Qizheng Zhang, Lin Chen, Fanghao Shao, Bo Xue, Yunchong Song, Zhenjie Yang, Ganqu Cui, Ning Ding, Jianfeng Gao, Xiaodong Liu, Bowen Zhou, Hongyuan Mei, Zhouhan Lin</p><p><b>Upvotes:</b> 103</p><p><b>Summary:</b> We propose FlowRL: matching the full reward distribution via flow balancing instead of maximizing rewards in large language model (LLM) reinforcement learning (RL). Recent advanced reasoning models adopt reward-maximizing methods (\eg, PPO and GRPO), which tend to over-optimize dominant reward signals while neglecting less frequent but valid reasoning paths, thus reducing diversity. In contrast, we transform scalar rewards into a normalized target distribution using a learnable partition function, and then minimize the reverse KL divergence between the policy and the target distribution. We implement this idea as a flow-balanced optimization method that promotes diverse exploration and generalizable reasoning trajectories. We conduct experiments on math and code reasoning tasks: FlowRL achieves a significant average improvement of 10.0% over GRPO and 5.1% over PPO on math benchmarks, and performs consistently better on code reasoning tasks. These results highlight reward distribution-matching as a key step toward efficient exploration and diverse reasoning in LLM reinforcement learning.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.15207</guid>
|
|
<pubDate>Thu, 18 Sep 2025 17:56:36 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data</title>
|
|
<link>https://arxiv.org/abs/2509.15221</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.15221.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhaoyang Liu, JingJing Xie, Zichen Ding, Zehao Li, Bowen Yang, Zhenyu Wu, Xuehui Wang, Qiushi Sun, Shi Liu, Weiyun Wang, Shenglong Ye, Qingyun Li, Zeyue Tian, Gen Luo, Xiangyu Yue, Biqing Qi, Kai Chen, Bowen Zhou, Yu Qiao, Qifeng Chen, Wenhai Wang</p><p><b>Upvotes:</b> 102</p><p><b>Summary:</b> Vision-Language Models (VLMs) have enabled computer use agents (CUAs) that operate GUIs autonomously, showing great potential, yet progress is limited by the lack of large-scale, open-source computer use data and foundation models. In this work, we introduce ScaleCUA, a step toward scaling open-source CUAs. It offers a large-scale dataset spanning 6 operating systems and 3 task domains, built via a closed-loop pipeline uniting automated agents with human experts. Trained on this scaled-up data, ScaleCUA can operate seamlessly across platforms. Specifically, it delivers strong gains over baselines (+26.6 on WebArena-Lite-v2, +10.7 on ScreenSpot-Pro) and sets new state-of-the-art results (94.4% on MMBench-GUI L1-Hard, 60.6% on OSWorld-G, 47.4% on WebArena-Lite-v2). These findings underscore the power of data-driven scaling for general-purpose computer use agents. We will release data, models, and code to advance future research: https://github.com/OpenGVLab/ScaleCUA.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.15221</guid>
|
|
<pubDate>Thu, 18 Sep 2025 17:59:22 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification</title>
|
|
<link>https://arxiv.org/abs/2509.15591</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.15591.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zinan Lin, Enshu Liu, Xuefei Ning, Junyi Zhu, Wenyu Wang, Sergey Yekhanin</p><p><b>Upvotes:</b> 44</p><p><b>Summary:</b> Generative modeling, representation learning, and classification are three core problems in machine learning (ML), yet their state-of-the-art (SoTA) solutions remain largely disjoint. In this paper, we ask: Can a unified principle address all three? Such unification could simplify ML pipelines and foster greater synergy across tasks. We introduce Latent Zoning Network (LZN) as a step toward this goal. At its core, LZN creates a shared Gaussian latent space that encodes information across all tasks. Each data type (e.g., images, text, labels) is equipped with an encoder that maps samples to disjoint latent zones, and a decoder that maps latents back to data. ML tasks are expressed as compositions of these encoders and decoders: for example, label-conditional image generation uses a label encoder and image decoder; image embedding uses an image encoder; classification uses an image encoder and label decoder. We demonstrate the promise of LZN in three increasingly complex scenarios: (1) LZN can enhance existing models (image generation): When combined with the SoTA Rectified Flow model, LZN improves FID on CIFAR10 from 2.76 to 2.59-without modifying the training objective. (2) LZN can solve tasks independently (representation learning): LZN can implement unsupervised representation learning without auxiliary loss functions, outperforming the seminal MoCo and SimCLR methods by 9.3% and 0.2%, respectively, on downstream linear classification on ImageNet. (3) LZN can solve multiple tasks simultaneously (joint generation and classification): With image and label encoders/decoders, LZN performs both tasks jointly by design, improving FID and achieving SoTA classification accuracy on CIFAR10. The code and trained models are available at https://github.com/microsoft/latent-zoning-networks. The project website is at https://zinanlin.me/blogs/latent_zoning_networks.html.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.15591</guid>
|
|
<pubDate>Fri, 19 Sep 2025 04:47:16 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer</title>
|
|
<link>https://arxiv.org/abs/2509.16197</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.16197.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yanghao Li, Rui Qian, Bowen Pan, Haotian Zhang, Haoshuo Huang, Bowen Zhang, Jialing Tong, Haoxuan You, Xianzhi Du, Zhe Gan, Hyunjik Kim, Chao Jia, Zhenbang Wang, Yinfei Yang, Mingfei Gao, Zi-Yi Dou, Wenze Hu, Chang Gao, Dongxu Li, Philipp Dufter, Zirui Wang, Guoli Yin, Zhengdong Zhang, Chen Chen, Yang Zhao, Ruoming Pang, Zhifeng Chen</p><p><b>Upvotes:</b> 49</p><p><b>Summary:</b> Unified multimodal Large Language Models (LLMs) that can both understand and generate visual content hold immense potential. However, existing open-source models often suffer from a performance trade-off between these capabilities. We present Manzano, a simple and scalable unified framework that substantially reduces this tension by coupling a hybrid image tokenizer with a well-curated training recipe. A single shared vision encoder feeds two lightweight adapters that produce continuous embeddings for image-to-text understanding and discrete tokens for text-to-image generation within a common semantic space. A unified autoregressive LLM predicts high-level semantics in the form of text and image tokens, with an auxiliary diffusion decoder subsequently translating the image tokens into pixels. The architecture, together with a unified training recipe over understanding and generation data, enables scalable joint learning of both capabilities. Manzano achieves state-of-the-art results among unified models, and is competitive with specialist models, particularly on text-rich evaluation. Our studies show minimal task conflicts and consistent gains from scaling model size, validating our design choice of a hybrid tokenizer.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.16197</guid>
|
|
<pubDate>Fri, 19 Sep 2025 17:58:00 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation</title>
|
|
<link>https://arxiv.org/abs/2509.16198</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.16198.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jane Luo, Xin Zhang, Steven Liu, Jie Wu, Yiming Huang, Yangyu Huang, Chengyu Yin, Ying Xin, Jianfeng Liu, Yuefeng Zhan, Hao Sun, Qi Chen, Scarlett Li, Mao Yang</p><p><b>Upvotes:</b> 119</p><p><b>Summary:</b> Large language models excel at function- and file-level code generation, yet generating complete repositories from scratch remains a fundamental challenge. This process demands coherent and reliable planning across proposal- and implementation-level stages, while natural language, due to its ambiguity and verbosity, is ill-suited for faithfully representing complex software structures. To address this, we introduce the Repository Planning Graph (RPG), a persistent representation that unifies proposal- and implementation-level planning by encoding capabilities, file structures, data flows, and functions in one graph. RPG replaces ambiguous natural language with an explicit blueprint, enabling long-horizon planning and scalable repository generation. Building on RPG, we develop ZeroRepo, a graph-driven framework for repository generation from scratch. It operates in three stages: proposal-level planning and implementation-level refinement to construct the graph, followed by graph-guided code generation with test validation. To evaluate this setting, we construct RepoCraft, a benchmark of six real-world projects with 1,052 tasks. On RepoCraft, ZeroRepo produces repositories averaging nearly 36K LOC, roughly 3.9times the strongest baseline (Claude Code) and about 64times other baselines. It attains 81.5% functional coverage and a 69.7% pass rate, exceeding Claude Code by 27.3 and 35.8 percentage points, respectively. Further analysis shows that RPG models complex dependencies, enables progressively more sophisticated planning through near-linear scaling, and enhances LLM understanding of repositories, thereby accelerating agent localization.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.16198</guid>
|
|
<pubDate>Fri, 19 Sep 2025 17:58:14 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>ARE: Scaling Up Agent Environments and Evaluations</title>
|
|
<link>https://arxiv.org/abs/2509.17158</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.17158.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Pierre Andrews, Amine Benhalloum, Gerard Moreno-Torres Bertran, Matteo Bettini, Amar Budhiraja, Ricardo Silveira Cabral, Virginie Do, Romain Froger, Emilien Garreau, Jean-Baptiste Gaya, Hugo Laurençon, Maxime Lecanu, Kunal Malkan, Dheeraj Mekala, Pierre Ménard, Grégoire Mialon, Ulyana Piterbarg, Mikhail Plekhanov, Mathieu Rita, Andrey Rusakov, Thomas Scialom, Vladislav Vorotilov, Mengjue Wang, Ian Yu</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> We introduce Meta Agents Research Environments (ARE), a research platform for scalable creation of environments, integration of synthetic or real applications, and execution of agentic orchestrations. ARE provides simple abstractions to build complex and diverse environments, each with their own rules, tools, content, and verifiers, helping to bridge the gap between model development and real-world deployment. We also propose Gaia2, a benchmark built in ARE and designed to measure general agent capabilities. Beyond search and execution, Gaia2 requires agents to handle ambiguities and noise, adapt to dynamic environments, collaborate with other agents, and operate under temporal constraints. Unlike prior benchmarks, Gaia2 runs asynchronously, surfacing new failure modes that are invisible in static settings. Our experiments show that no system dominates across the intelligence spectrum: stronger reasoning often comes at the cost of efficiency, and budget scaling curves plateau, highlighting the need for new architectures and adaptive compute strategies. Perhaps more importantly, ARE abstractions enable continuous extension of Gaia2 to other environments, empowering the community to rapidly create new benchmarks tailored to their domains. In AI's second half, progress increasingly depends on defining meaningful tasks and robust evaluations to drive frontier capabilities forward.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.17158</guid>
|
|
<pubDate>Sun, 21 Sep 2025 16:59:45 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>LIMI: Less is More for Agency</title>
|
|
<link>https://arxiv.org/abs/2509.17567</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.17567.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yang Xiao, Mohan Jiang, Jie Sun, Keyu Li, Jifan Lin, Yumin Zhuang, Ji Zeng, Shijie Xia, Qishuo Hua, Xuefeng Li, Xiaojie Cai, Tongyu Wang, Yue Zhang, Liming Liu, Xia Wu, Jinlong Hou, Yuan Cheng, Wenjie Li, Xiang Wang, Dequan Wang, Pengfei Liu</p><p><b>Upvotes:</b> 94</p><p><b>Summary:</b> We define Agency as the emergent capacity of AI systems to function as autonomous agents actively discovering problems, formulating hypotheses, and executing solutions through self-directed engagement with environments and tools. This fundamental capability marks the dawn of the Age of AI Agency, driven by a critical industry shift: the urgent need for AI systems that don't just think, but work. While current AI excels at reasoning and generating responses, industries demand autonomous agents that can execute tasks, operate tools, and drive real-world outcomes. As agentic intelligence becomes the defining characteristic separating cognitive systems from productive workers, efficiently cultivating machine autonomy becomes paramount. Current approaches assume that more data yields better agency, following traditional scaling laws from language modeling. We fundamentally challenge this paradigm. LIMI (Less Is More for Intelligent Agency) demonstrates that agency follows radically different development principles. Through strategic focus on collaborative software development and scientific research workflows, we show that sophisticated agentic intelligence can emerge from minimal but strategically curated demonstrations of autonomous behavior. Using only 78 carefully designed training samples, LIMI achieves 73.5% on comprehensive agency benchmarks, dramatically outperforming state-of-the-art models: Kimi-K2-Instruct (24.1%), DeepSeek-V3.1 (11.9%), Qwen3-235B-A22B-Instruct (27.5%), and GLM-4.5 (45.1%). Most strikingly, LIMI demonstrates 53.7% improvement over models trained on 10,000 samples-achieving superior agentic intelligence with 128 times fewer samples. Our findings establish the Agency Efficiency Principle: machine autonomy emerges not from data abundance but from strategic curation of high-quality agentic demonstrations.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.17567</guid>
|
|
<pubDate>Mon, 22 Sep 2025 10:59:32 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>OmniInsert: Mask-Free Video Insertion of Any Reference via Diffusion Transformer Models</title>
|
|
<link>https://arxiv.org/abs/2509.17627</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.17627.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jinshu Chen, Xinghui Li, Xu Bai, Tianxiang Ma, Pengze Zhang, Zhuowei Chen, Gen Li, Lijie Liu, Songtao Zhao, Bingchuan Li, Qian He</p><p><b>Upvotes:</b> 63</p><p><b>Summary:</b> Recent advances in video insertion based on diffusion models are impressive. However, existing methods rely on complex control signals but struggle with subject consistency, limiting their practical applicability. In this paper, we focus on the task of Mask-free Video Insertion and aim to resolve three key challenges: data scarcity, subject-scene equilibrium, and insertion harmonization. To address the data scarcity, we propose a new data pipeline InsertPipe, constructing diverse cross-pair data automatically. Building upon our data pipeline, we develop OmniInsert, a novel unified framework for mask-free video insertion from both single and multiple subject references. Specifically, to maintain subject-scene equilibrium, we introduce a simple yet effective Condition-Specific Feature Injection mechanism to distinctly inject multi-source conditions and propose a novel Progressive Training strategy that enables the model to balance feature injection from subjects and source video. Meanwhile, we design the Subject-Focused Loss to improve the detailed appearance of the subjects. To further enhance insertion harmonization, we propose an Insertive Preference Optimization methodology to optimize the model by simulating human preferences, and incorporate a Context-Aware Rephraser module during reference to seamlessly integrate the subject into the original scenes. To address the lack of a benchmark for the field, we introduce InsertBench, a comprehensive benchmark comprising diverse scenes with meticulously selected subjects. Evaluation on InsertBench indicates OmniInsert outperforms state-of-the-art closed-source commercial solutions. The code will be released.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.17627</guid>
|
|
<pubDate>Mon, 22 Sep 2025 11:35:55 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Qwen3-Omni Technical Report</title>
|
|
<link>https://arxiv.org/abs/2509.17765</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.17765.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jin Xu, Zhifang Guo, Hangrui Hu, Yunfei Chu, Xiong Wang, Jinzheng He, Yuxuan Wang, Xian Shi, Ting He, Xinfa Zhu, Yuanjun Lv, Yongqi Wang, Dake Guo, He Wang, Linhan Ma, Pei Zhang, Xinyu Zhang, Hongkun Hao, Zishan Guo, Baosong Yang, Bin Zhang, Ziyang Ma, Xipin Wei, Shuai Bai, Keqin Chen, Xuejing Liu, Peng Wang, Mingkun Yang, Dayiheng Liu, Xingzhang Ren, Bo Zheng, Rui Men, Fan Zhou, Bowen Yu, Jianxin Yang, Le Yu, Jingren Zhou, Junyang Lin</p><p><b>Upvotes:</b> 121</p><p><b>Summary:</b> We present Qwen3-Omni, a single multimodal model that, for the first time, maintains state-of-the-art performance across text, image, audio, and video without any degradation relative to single-modal counterparts. Qwen3-Omni matches the performance of same-sized single-modal models within the Qwen series and excels particularly on audio tasks. Across 36 audio and audio-visual benchmarks, Qwen3-Omni achieves open-source SOTA on 32 benchmarks and overall SOTA on 22, outperforming strong closed-source models such as Gemini-2.5-Pro, Seed-ASR, and GPT-4o-Transcribe. Qwen3-Omni adopts a Thinker-Talker MoE architecture that unifies perception and generation across text, images, audio, and video, yielding fluent text and natural real-time speech. It supports text interaction in 119 languages, speech understanding in 19 languages, and speech generation in 10 languages. To reduce first-packet latency in streaming synthesis, Talker autoregressively predicts discrete speech codecs using a multi-codebook scheme. Leveraging the representational capacity of these codebooks, we replace computationally intensive block-wise diffusion with a lightweight causal ConvNet, enabling streaming from the first codec frame. In cold-start settings, Qwen3-Omni achieves a theoretical end-to-end first-packet latency of 234 ms. To further strengthen multimodal reasoning, we introduce a Thinking model that explicitly reasons over inputs from any modality. Since the research community currently lacks a general-purpose audio captioning model, we fine-tuned Qwen3-Omni-30B-A3B to obtain Qwen3-Omni-30B-A3B-Captioner, which produces detailed, low-hallucination captions for arbitrary audio inputs. Qwen3-Omni-30B-A3B, Qwen3-Omni-30B-A3B-Thinking, and Qwen3-Omni-30B-A3B-Captioner are publicly released under the Apache 2.0 license.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.17765</guid>
|
|
<pubDate>Mon, 22 Sep 2025 13:26:24 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>OnePiece: Bringing Context Engineering and Reasoning to Industrial Cascade Ranking System</title>
|
|
<link>https://arxiv.org/abs/2509.18091</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.18091.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sunhao Dai, Jiakai Tang, Jiahua Wu, Kun Wang, Yuxuan Zhu, Bingjun Chen, Bangyang Hong, Yu Zhao, Cong Fu, Kangle Wu, Yabo Ni, Anxiang Zeng, Wenjie Wang, Xu Chen, Jun Xu, See-Kiong Ng</p><p><b>Upvotes:</b> 32</p><p><b>Summary:</b> Despite the growing interest in replicating the scaled success of large language models (LLMs) in industrial search and recommender systems, most existing industrial efforts remain limited to transplanting Transformer architectures, which bring only incremental improvements over strong Deep Learning Recommendation Models (DLRMs). From a first principle perspective, the breakthroughs of LLMs stem not only from their architectures but also from two complementary mechanisms: context engineering, which enriches raw input queries with contextual cues to better elicit model capabilities, and multi-step reasoning, which iteratively refines model outputs through intermediate reasoning paths. However, these two mechanisms and their potential to unlock substantial improvements remain largely underexplored in industrial ranking systems. In this paper, we propose OnePiece, a unified framework that seamlessly integrates LLM-style context engineering and reasoning into both retrieval and ranking models of industrial cascaded pipelines. OnePiece is built on a pure Transformer backbone and further introduces three key innovations: (1) structured context engineering, which augments interaction history with preference and scenario signals and unifies them into a structured tokenized input sequence for both retrieval and ranking; (2) block-wise latent reasoning, which equips the model with multi-step refinement of representations and scales reasoning bandwidth via block size; (3) progressive multi-task training, which leverages user feedback chains to effectively supervise reasoning steps during training. OnePiece has been deployed in the main personalized search scenario of Shopee and achieves consistent online gains across different key business metrics, including over +2% GMV/UU and a +2.90% increase in advertising revenue.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.18091</guid>
|
|
<pubDate>Mon, 22 Sep 2025 17:59:07 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Do You Need Proprioceptive States in Visuomotor Policies?</title>
|
|
<link>https://arxiv.org/abs/2509.18644</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.18644.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Juntu Zhao, Wenbo Lu, Di Zhang, Yufeng Liu, Yushen Liang, Tianluo Zhang, Yifeng Cao, Junyuan Xie, Yingdong Hu, Shengjie Wang, Junliang Guo, Dequan Wang, Yang Gao</p><p><b>Upvotes:</b> 49</p><p><b>Summary:</b> Imitation-learning-based visuomotor policies have been widely used in robot manipulation, where both visual observations and proprioceptive states are typically adopted together for precise control. However, in this study, we find that this common practice makes the policy overly reliant on the proprioceptive state input, which causes overfitting to the training trajectories and results in poor spatial generalization. On the contrary, we propose the State-free Policy, removing the proprioceptive state input and predicting actions only conditioned on visual observations. The State-free Policy is built in the relative end-effector action space, and should ensure the full task-relevant visual observations, here provided by dual wide-angle wrist cameras. Empirical results demonstrate that the State-free policy achieves significantly stronger spatial generalization than the state-based policy: in real-world tasks such as pick-and-place, challenging shirt-folding, and complex whole-body manipulation, spanning multiple robot embodiments, the average success rate improves from 0\% to 85\% in height generalization and from 6\% to 64\% in horizontal generalization. Furthermore, they also show advantages in data efficiency and cross-embodiment adaptation, enhancing their practicality for real-world deployment.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.18644</guid>
|
|
<pubDate>Tue, 23 Sep 2025 04:56:59 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Reinforcement Learning on Pre-Training Data</title>
|
|
<link>https://arxiv.org/abs/2509.19249</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.19249.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Siheng Li, Kejiao Li, Zenan Xu, Guanhua Huang, Evander Yang, Kun Li, Haoyuan Wu, Jiajia Wu, Zihao Zheng, Chenchen Zhang, Kun Shi, Kyrierl Deng, Qi Yi, Ruibin Xiong, Tingqiang Xu, Yuhao Jiang, Jianfeng Yan, Yuyuan Zeng, Guanghui Xu, Jinbao Xue, Zhijiang Xu, Zheng Fang, Shuai Li, Qibin Liu, Xiaoxue Li, Zhuoyu Li, Yangyu Tao, Fei Gao, Cheng Jiang, Bo Chao Wang, Kai Liu, Jianchen Zhu, Wai Lam, Wayyt Wang, Bo Zhou, Di Wang</p><p><b>Upvotes:</b> 61</p><p><b>Summary:</b> The growing disparity between the exponential scaling of computational resources and the finite growth of high-quality text data now constrains conventional scaling approaches for large language models (LLMs). To address this challenge, we introduce Reinforcement Learning on Pre-Training data (RLPT), a new training-time scaling paradigm for optimizing LLMs. In contrast to prior approaches that scale training primarily through supervised learning, RLPT enables the policy to autonomously explore meaningful trajectories to learn from pre-training data and improve its capability through reinforcement learning (RL). While existing RL strategies such as reinforcement learning from human feedback (RLHF) and reinforcement learning with verifiable rewards (RLVR) rely on human annotation for reward construction, RLPT eliminates this dependency by deriving reward signals directly from pre-training data. Specifically, it adopts a next-segment reasoning objective, rewarding the policy for accurately predicting subsequent text segments conditioned on the preceding context. This formulation allows RL to be scaled on pre-training data, encouraging the exploration of richer trajectories across broader contexts and thereby fostering more generalizable reasoning skills. Extensive experiments on both general-domain and mathematical reasoning benchmarks across multiple models validate the effectiveness of RLPT. For example, when applied to Qwen3-4B-Base, RLPT yields absolute improvements of 3.0, 5.1, 8.1, 6.0, 6.6, and 5.3 on MMLU, MMLU-Pro, GPQA-Diamond, KOR-Bench, AIME24, and AIME25, respectively. The results further demonstrate favorable scaling behavior, suggesting strong potential for continued gains with more compute. In addition, RLPT provides a solid foundation, extending the reasoning boundaries of LLMs and enhancing RLVR performance.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.19249</guid>
|
|
<pubDate>Tue, 23 Sep 2025 17:10:40 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>VCRL: Variance-based Curriculum Reinforcement Learning for Large Language Models</title>
|
|
<link>https://arxiv.org/abs/2509.19803</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.19803.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Guochao Jiang, Wenfeng Feng, Guofeng Quan, Chuzhan Hao, Yuewei Zhang, Guohua Liu, Hao Wang</p><p><b>Upvotes:</b> 113</p><p><b>Summary:</b> Policy-based reinforcement learning currently plays an important role in improving LLMs on mathematical reasoning tasks. However, existing rollout-based reinforcement learning methods (GRPO, DAPO, GSPO, etc.) fail to explicitly consider LLMs' learning ability for samples of different difficulty levels, which is contrary to the human cognitive process of mathematical reasoning tasks from easy to difficult. Intuitively, we find that the variance of the rollout group's reward in RLVR partly reflects the difficulty of the current sample for LLMs. Samples that are too easy or too difficult have a lower variance, while samples with moderate difficulty have a higher variance. Based on this, we propose VCRL, a curriculum reinforcement learning framework that dynamically controls the difficulty of training samples based on the variance of group rewards. Experiments on five mathematical benchmarks and two models reveal the advantages of VCRL over the current LLM RL baselines.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.19803</guid>
|
|
<pubDate>Wed, 24 Sep 2025 06:38:58 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>SIM-CoT: Supervised Implicit Chain-of-Thought</title>
|
|
<link>https://arxiv.org/abs/2509.20317</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.20317.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xilin Wei, Xiaoran Liu, Yuhang Zang, Xiaoyi Dong, Yuhang Cao, Jiaqi Wang, Xipeng Qiu, Dahua Lin</p><p><b>Upvotes:</b> 35</p><p><b>Summary:</b> Implicit Chain-of-Thought (CoT) methods present a promising, token-efficient alternative to explicit CoT reasoning in Large Language Models (LLMs), but a persistent performance gap has limited the application of implicit CoT. We identify a core latent instability issue by scaling the computational budget of implicit CoT approaches: as we increase the number of implicit reasoning tokens to enhance performance, the training process often becomes unstable and collapses. Our analysis reveals that this instability arises from the latent representations becoming homogeneous and losing their semantic diversity, a failure caused by insufficient step-level supervision in existing implicit CoT approaches. To address this issue, we propose SIM-CoT, a plug-and-play training module that introduces step-level supervision to stabilize and enrich the latent reasoning space. Specifically, SIM-CoT employs an auxiliary decoder during training to align each implicit token with its corresponding explicit reasoning step, ensuring that latent states capture distinct and meaningful information. The proposed auxiliary decoder is removed during inference, preserving the computational efficiency of implicit CoT methods with no added overhead. In addition, the auxiliary decoder affords interpretability of implicit reasoning by projecting each latent token onto an explicit reasoning vocabulary, enabling per-step visualization of semantic roles and diagnosis. SIM-CoT significantly enhances both the in-domain accuracy and out-of-domain stability of various implicit CoT methods, boosting baselines like Coconut by +8.2% on GPT-2 and CODI by +3.0% on LLaMA-3.1 8B. Demonstrating strong scalability, SIM-CoT also surpasses the explicit CoT baseline on GPT-2 by 2.1% with 2.3\times greater token efficiency, while substantially closing the performance gap on larger models like LLaMA-3.1 8B.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.20317</guid>
|
|
<pubDate>Wed, 24 Sep 2025 17:01:32 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Video models are zero-shot learners and reasoners</title>
|
|
<link>https://arxiv.org/abs/2509.20328</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.20328.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Thaddäus Wiedemer, Yuxuan Li, Paul Vicol, Shixiang Shane Gu, Nick Matarese, Kevin Swersky, Been Kim, Priyank Jaini, Robert Geirhos</p><p><b>Upvotes:</b> 86</p><p><b>Summary:</b> The remarkable zero-shot capabilities of Large Language Models (LLMs) have propelled natural language processing from task-specific models to unified, generalist foundation models. This transformation emerged from simple primitives: large, generative models trained on web-scale data. Curiously, the same primitives apply to today's generative video models. Could video models be on a trajectory towards general-purpose vision understanding, much like LLMs developed general-purpose language understanding? We demonstrate that Veo 3 can solve a broad variety of tasks it wasn't explicitly trained for: segmenting objects, detecting edges, editing images, understanding physical properties, recognizing object affordances, simulating tool use, and more. These abilities to perceive, model, and manipulate the visual world enable early forms of visual reasoning like maze and symmetry solving. Veo's emergent zero-shot capabilities indicate that video models are on a path to becoming unified, generalist vision foundation models.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.20328</guid>
|
|
<pubDate>Wed, 24 Sep 2025 17:17:27 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>EmbeddingGemma: Powerful and Lightweight Text Representations</title>
|
|
<link>https://arxiv.org/abs/2509.20354</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.20354.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Henrique Schechter Vera, Sahil Dua, Biao Zhang, Daniel Salz, Ryan Mullins, Sindhu Raghuram Panyam, Sara Smoot, Iftekhar Naim, Joe Zou, Feiyang Chen, Daniel Cer, Alice Lisak, Min Choi, Lucas Gonzalez, Omar Sanseviero, Glenn Cameron, Ian Ballantyne, Kat Black, Kaifeng Chen, Weiyi Wang, Zhe Li, Gus Martins, Jinhyuk Lee, Mark Sherwood, Juyeong Ji, Renjie Wu, Jingxiao Zheng, Jyotinder Singh, Abheesht Sharma, Divya Sreepat, Aashi Jain, Adham Elarabawy, AJ Co, Andreas Doumanoglou, Babak Samari, Ben Hora, Brian Potetz, Dahun Kim, Enrique Alfonseca, Fedor Moiseev, Feng Han, Frank Palma Gomez, Gustavo Hernández Ábrego, Hesen Zhang, Hui Hui, Jay Han, Karan Gill, Ke Chen, Koert Chen, Madhuri Shanbhogue, Michael Boratko, Paul Suganthan, Sai Meher Karthik Duddu, Sandeep Mariserla, Setareh Ariafar, Shanfeng Zhang, Shijie Zhang, Simon Baumgartner, Sonam Goenka, Steve Qiu, Tanmaya Dabral, Trevor Walker, Vikram Rao, Waleed Khawaja, Wenlei Zhou, Xiaoqi Ren, Ye Xia, Yichang Chen, Yi-Ting Chen, Zhe Dong, Zhongli Ding, Francesco Visin, Gaël Liu, Jiageng Zhang, Kathleen Kenealy, Michelle Casbon, Ravin Kumar, Thomas Mesnard, Zach Gleicher, Cormac Brick, Olivier Lacombe, Adam Roberts, Yunhsuan Sung, Raphael Hoffmann, Tris Warkentin, Armand Joulin, Tom Duerig, Mojtaba Seyedhosseini</p><p><b>Upvotes:</b> 32</p><p><b>Summary:</b> We introduce EmbeddingGemma, a new lightweight, open text embedding model based on the Gemma 3 language model family. Our innovative training recipe strategically captures knowledge from larger models via encoder-decoder initialization and geometric embedding distillation. We improve model robustness and expressiveness with a spread-out regularizer, and ensure generalizability by merging checkpoints from varied, optimized mixtures. Evaluated on the Massive Text Embedding Benchmark (MTEB) across multilingual, English, and code domains, EmbeddingGemma (300M) achieves state-of-the-art results. Notably, it outperforms prior top models, both proprietary and open, with fewer than 500M parameters, and provides performance comparable to models double its size, offering an exceptional performance-to-cost ratio. Remarkably, this lead persists when quantizing model weights or truncating embedding outputs. This makes EmbeddingGemma particularly well-suited for low-latency and high-throughput use cases such as on-device applications. We provide ablation studies exploring our key design choices. We release EmbeddingGemma to the community to promote further research.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.20354</guid>
|
|
<pubDate>Wed, 24 Sep 2025 17:56:51 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Seedream 4.0: Toward Next-generation Multimodal Image Generation</title>
|
|
<link>https://arxiv.org/abs/2509.20427</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.20427.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Team Seedream, Yunpeng Chen, Yu Gao, Lixue Gong, Meng Guo, Qiushan Guo, Zhiyao Guo, Xiaoxia Hou, Weilin Huang, Yixuan Huang, Xiaowen Jian, Huafeng Kuang, Zhichao Lai, Fanshi Li, Liang Li, Xiaochen Lian, Chao Liao, Liyang Liu, Wei Liu, Yanzuo Lu, Zhengxiong Luo, Tongtong Ou, Guang Shi, Yichun Shi, Shiqi Sun, Yu Tian, Zhi Tian, Peng Wang, Rui Wang, Xun Wang, Ye Wang, Guofeng Wu, Jie Wu, Wenxu Wu, Yonghui Wu, Xin Xia, Xuefeng Xiao, Shuang Xu, Xin Yan, Ceyuan Yang, Jianchao Yang, Zhonghua Zhai, Chenlin Zhang, Heng Zhang, Qi Zhang, Xinyu Zhang, Yuwei Zhang, Shijia Zhao, Wenliang Zhao, Wenjia Zhu</p><p><b>Upvotes:</b> 68</p><p><b>Summary:</b> We introduce Seedream 4.0, an efficient and high-performance multimodal image generation system that unifies text-to-image (T2I) synthesis, image editing, and multi-image composition within a single framework. We develop a highly efficient diffusion transformer with a powerful VAE which also can reduce the number of image tokens considerably. This allows for efficient training of our model, and enables it to fast generate native high-resolution images (e.g., 1K-4K). Seedream 4.0 is pretrained on billions of text-image pairs spanning diverse taxonomies and knowledge-centric concepts. Comprehensive data collection across hundreds of vertical scenarios, coupled with optimized strategies, ensures stable and large-scale training, with strong generalization. By incorporating a carefully fine-tuned VLM model, we perform multi-modal post-training for training both T2I and image editing tasks jointly. For inference acceleration, we integrate adversarial distillation, distribution matching, and quantization, as well as speculative decoding. It achieves an inference time of up to 1.8 seconds for generating a 2K image (without a LLM/VLM as PE model). Comprehensive evaluations reveal that Seedream 4.0 can achieve state-of-the-art results on both T2I and multimodal image editing. In particular, it demonstrates exceptional multimodal capabilities in complex tasks, including precise image editing and in-context reasoning, and also allows for multi-image reference, and can generate multiple output images. This extends traditional T2I systems into an more interactive and multidimensional creative tool, pushing the boundary of generative AI for both creativity and professional applications. Seedream 4.0 is now accessible on https://www.volcengine.com/experience/ark?launch=seedream.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.20427</guid>
|
|
<pubDate>Wed, 24 Sep 2025 17:59:04 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Tree Search for LLM Agent Reinforcement Learning</title>
|
|
<link>https://arxiv.org/abs/2509.21240</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.21240.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuxiang Ji, Ziyu Ma, Yong Wang, Guanhua Chen, Xiangxiang Chu, Liaoni Wu</p><p><b>Upvotes:</b> 81</p><p><b>Summary:</b> Recent advances in reinforcement learning (RL) have significantly enhanced the agentic capabilities of large language models (LLMs). In long-term and multi-turn agent tasks, existing approaches driven solely by outcome rewards often suffer from the problem of sparse supervision. To address the challenge, we propose Tree-based Group Relative Policy Optimization (Tree-GRPO), a grouped agent RL method based on tree search, where each tree node represents the complete agent interaction step. By sharing common prefixes, the tree search sampling increases the number of rollouts achievable within a fixed budget of tokens or tool calls. Moreover, we find that the tree-structured trajectory naturally allows the construction of step-wise process supervised signals even using only the outcome reward. Based on this, Tree-GRPO estimates the grouped relative advantages both on intra-tree and inter-tree levels. Through theoretical analysis, we demonstrate that the objective of intra-tree level group relative policy optimization is equivalent to that of step-level direct preference learning. Experiments across 11 datasets and 3 types of QA tasks demonstrate the superiority of the proposed tree-based RL over the chain-based RL method.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.21240</guid>
|
|
<pubDate>Thu, 25 Sep 2025 14:37:09 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Hunyuan3D-Omni: A Unified Framework for Controllable Generation of 3D Assets</title>
|
|
<link>https://arxiv.org/abs/2509.21245</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.21245.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Team Hunyuan3D, Bowen Zhang, Chunchao Guo, Haolin Liu, Hongyu Yan, Huiwen Shi, Jingwei Huang, Junlin Yu, Kunhong Li, Linus, Penghao Wang, Qingxiang Lin, Sicong Liu, Xianghui Yang, Yixuan Tang, Yunfei Zhao, Zeqiang Lai, Zhihao Liang, Zibo Zhao</p><p><b>Upvotes:</b> 36</p><p><b>Summary:</b> Recent advances in 3D-native generative models have accelerated asset creation for games, film, and design. However, most methods still rely primarily on image or text conditioning and lack fine-grained, cross-modal controls, which limits controllability and practical adoption. To address this gap, we present Hunyuan3D-Omni, a unified framework for fine-grained, controllable 3D asset generation built on Hunyuan3D 2.1. In addition to images, Hunyuan3D-Omni accepts point clouds, voxels, bounding boxes, and skeletal pose priors as conditioning signals, enabling precise control over geometry, topology, and pose. Instead of separate heads for each modality, our model unifies all signals in a single cross-modal architecture. We train with a progressive, difficulty-aware sampling strategy that selects one control modality per example and biases sampling toward harder signals (e.g., skeletal pose) while downweighting easier ones (e.g., point clouds), encouraging robust multi-modal fusion and graceful handling of missing inputs. Experiments show that these additional controls improve generation accuracy, enable geometry-aware transformations, and increase robustness for production workflows.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.21245</guid>
|
|
<pubDate>Thu, 25 Sep 2025 14:39:17 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>MMR1: Enhancing Multimodal Reasoning with Variance-Aware Sampling and Open Resources</title>
|
|
<link>https://arxiv.org/abs/2509.21268</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.21268.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sicong Leng, Jing Wang, Jiaxi Li, Hao Zhang, Zhiqiang Hu, Boqiang Zhang, Yuming Jiang, Hang Zhang, Xin Li, Lidong Bing, Deli Zhao, Wei Lu, Yu Rong, Aixin Sun, Shijian Lu</p><p><b>Upvotes:</b> 93</p><p><b>Summary:</b> Large multimodal reasoning models have achieved rapid progress, but their advancement is constrained by two major limitations: the absence of open, large-scale, high-quality long chain-of-thought (CoT) data, and the instability of reinforcement learning (RL) algorithms in post-training. Group Relative Policy Optimization (GRPO), the standard framework for RL fine-tuning, is prone to gradient vanishing when reward variance is low, which weakens optimization signals and impairs convergence. This work makes three contributions: (1) We propose Variance-Aware Sampling (VAS), a data selection strategy guided by Variance Promotion Score (VPS) that combines outcome variance and trajectory diversity to promote reward variance and stabilize policy optimization. (2) We release large-scale, carefully curated resources containing ~1.6M long CoT cold-start data and ~15k RL QA pairs, designed to ensure quality, difficulty, and diversity, along with a fully reproducible end-to-end training codebase. (3) We open-source a family of multimodal reasoning models in multiple scales, establishing standardized baselines for the community. Experiments across mathematical reasoning benchmarks demonstrate the effectiveness of both the curated data and the proposed VAS. Comprehensive ablation studies and analyses provide further insight into the contributions of each component. In addition, we theoretically establish that reward variance lower-bounds the expected policy gradient magnitude, with VAS serving as a practical mechanism to realize this guarantee. Our code, data, and checkpoints are available at https://github.com/LengSicong/MMR1.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.21268</guid>
|
|
<pubDate>Thu, 25 Sep 2025 14:58:29 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>SciReasoner: Laying the Scientific Reasoning Ground Across Disciplines</title>
|
|
<link>https://arxiv.org/abs/2509.21320</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.21320.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yizhou Wang, Chen Tang, Han Deng, Jiabei Xiao, Jiaqi Liu, Jianyu Wu, Jun Yao, Pengze Li, Encheng Su, Lintao Wang, Guohang Zhuang, Yuchen Ren, Ben Fei, Ming Hu, Xin Chen, Dongzhan Zhou, Junjun He, Xiangyu Yue, Zhenfei Yin, Jiamin Wu, Qihao Zheng, Yuhao Zhou, Huihui Xu, Chenglong Ma, Yan Lu, Wenlong Zhang, Chunfeng Song, Philip Torr, Shixiang Tang, Xinzhu Ma, Wanli Ouyang, Lei Bai</p><p><b>Upvotes:</b> 91</p><p><b>Summary:</b> We present a scientific reasoning foundation model that aligns natural language with heterogeneous scientific representations. The model is pretrained on a 206B-token corpus spanning scientific text, pure sequences, and sequence-text pairs, then aligned via SFT on 40M instructions, annealed cold-start bootstrapping to elicit long-form chain-of-thought, and reinforcement learning with task-specific reward shaping, which instills deliberate scientific reasoning. It supports four capability families, covering up to 103 tasks across workflows: (i) faithful translation between text and scientific formats, (ii) text/knowledge extraction, (iii) property prediction, (iv) property classification, (v) unconditional and conditional sequence generation and design. Compared with specialist systems, our approach broadens instruction coverage, improves cross-domain generalization, and enhances fidelity. We detail data curation and training and show that cross-discipline learning strengthens transfer and downstream reliability. The model, instruct tuning datasets and the evaluation code are open-sourced at https://huggingface.co/SciReason and https://github.com/open-sciencelab/SciReason.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.21320</guid>
|
|
<pubDate>Thu, 25 Sep 2025 17:52:06 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>ReviewScore: Misinformed Peer Review Detection with Large Language Models</title>
|
|
<link>https://arxiv.org/abs/2509.21679</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.21679.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hyun Ryu, Doohyuk Jang, Hyemin S. Lee, Joonhyun Jeong, Gyeongman Kim, Donghyeon Cho, Gyouk Chu, Minyeong Hwang, Hyeongwon Jang, Changhun Kim, Haechan Kim, Jina Kim, Joowon Kim, Yoonjeon Kim, Kwanhyung Lee, Chanjae Park, Heecheol Yun, Gregor Betz, Eunho Yang</p><p><b>Upvotes:</b> 58</p><p><b>Summary:</b> Peer review serves as a backbone of academic research, but in most AI conferences, the review quality is degrading as the number of submissions explodes. To reliably detect low-quality reviews, we define misinformed review points as either "weaknesses" in a review that contain incorrect premises, or "questions" in a review that can be already answered by the paper. We verify that 15.2% of weaknesses and 26.4% of questions are misinformed and introduce ReviewScore indicating if a review point is misinformed. To evaluate the factuality of each premise of weaknesses, we propose an automated engine that reconstructs every explicit and implicit premise from a weakness. We build a human expert-annotated ReviewScore dataset to check the ability of LLMs to automate ReviewScore evaluation. Then, we measure human-model agreements on ReviewScore using eight current state-of-the-art LLMs and verify moderate agreements. We also prove that evaluating premise-level factuality shows significantly higher agreements than evaluating weakness-level factuality. A thorough disagreement analysis further supports a potential of fully automated ReviewScore evaluation.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.21679</guid>
|
|
<pubDate>Thu, 25 Sep 2025 22:55:05 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing</title>
|
|
<link>https://arxiv.org/abs/2509.22186</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.22186.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junbo Niu, Zheng Liu, Zhuangcheng Gu, Bin Wang, Linke Ouyang, Zhiyuan Zhao, Tao Chu, Tianyao He, Fan Wu, Qintong Zhang, Zhenjiang Jin, Guang Liang, Rui Zhang, Wenzheng Zhang, Yuan Qu, Zhifei Ren, Yuefeng Sun, Yuanhong Zheng, Dongsheng Ma, Zirui Tang, Boyu Niu, Ziyang Miao, Hejun Dong, Siyi Qian, Junyuan Zhang, Jingzhou Chen, Fangdong Wang, Xiaomeng Zhao, Liqun Wei, Wei Li, Shasha Wang, Ruiliang Xu, Yuanyuan Cao, Lu Chen, Qianqian Wu, Huaiyu Gu, Lindong Lu, Keming Wang, Dechen Lin, Guanlin Shen, Xuanhe Zhou, Linfeng Zhang, Yuhang Zang, Xiaoyi Dong, Jiaqi Wang, Bo Zhang, Lei Bai, Pei Chu, Weijia Li, Jiang Wu, Lijun Wu, Zhenxiang Li, Guangyu Wang, Zhongying Tu, Chao Xu, Kai Chen, Yu Qiao, Bowen Zhou, Dahua Lin, Wentao Zhang, Conghui He</p><p><b>Upvotes:</b> 92</p><p><b>Summary:</b> We introduce MinerU2.5, a 1.2B-parameter document parsing vision-language model that achieves state-of-the-art recognition accuracy while maintaining exceptional computational efficiency. Our approach employs a coarse-to-fine, two-stage parsing strategy that decouples global layout analysis from local content recognition. In the first stage, the model performs efficient layout analysis on downsampled images to identify structural elements, circumventing the computational overhead of processing high-resolution inputs. In the second stage, guided by the global layout, it performs targeted content recognition on native-resolution crops extracted from the original image, preserving fine-grained details in dense text, complex formulas, and tables. To support this strategy, we developed a comprehensive data engine that generates diverse, large-scale training corpora for both pretraining and fine-tuning. Ultimately, MinerU2.5 demonstrates strong document parsing ability, achieving state-of-the-art performance on multiple benchmarks, surpassing both general-purpose and domain-specific models across various recognition tasks, while maintaining significantly lower computational overhead.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.22186</guid>
|
|
<pubDate>Fri, 26 Sep 2025 10:45:48 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>StableToken: A Noise-Robust Semantic Speech Tokenizer for Resilient SpeechLLMs</title>
|
|
<link>https://arxiv.org/abs/2509.22220</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.22220.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuhan Song, Linhao Zhang, Chuhan Wu, Aiwei Liu, Wei Jia, Houfeng Wang, Xiao Zhou</p><p><b>Upvotes:</b> 57</p><p><b>Summary:</b> Prevalent semantic speech tokenizers, designed to capture linguistic content, are surprisingly fragile. We find they are not robust to meaning-irrelevant acoustic perturbations; even at high Signal-to-Noise Ratios (SNRs) where speech is perfectly intelligible, their output token sequences can change drastically, increasing the learning burden for downstream LLMs. This instability stems from two flaws: a brittle single-path quantization architecture and a distant training signal indifferent to intermediate token stability. To address this, we introduce StableToken, a tokenizer that achieves stability through a consensus-driven mechanism. Its multi-branch architecture processes audio in parallel, and these representations are merged via a powerful bit-wise voting mechanism to form a single, stable token sequence. StableToken sets a new state-of-the-art in token stability, drastically reducing Unit Edit Distance (UED) under diverse noise conditions. This foundational stability translates directly to downstream benefits, significantly improving the robustness of SpeechLLMs on a variety of tasks.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.22220</guid>
|
|
<pubDate>Fri, 26 Sep 2025 11:32:51 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>EPO: Entropy-regularized Policy Optimization for LLM Agents Reinforcement Learning</title>
|
|
<link>https://arxiv.org/abs/2509.22576</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.22576.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xu Wujiang, Wentian Zhao, Zhenting Wang, Li Yu-Jhe, Jin Can, Jin Mingyu, Mei Kai, Wan Kun, Metaxas Dimitris</p><p><b>Upvotes:</b> 115</p><p><b>Summary:</b> Training LLM agents in multi-turn environments with sparse rewards, where completing a single task requires 30+ turns of interaction within an episode, presents a fundamental challenge for reinforcement learning. We identify a critical failure mode unique to this setting: the exploration-exploitation cascade failure. This cascade begins with early-stage policy premature convergence, where sparse feedback causes agents to commit to flawed, low-entropy strategies. Subsequently, agents enter late-stage policy collapse, where conventional entropy regularization becomes counterproductive, promoting chaotic exploration that destabilizes training. We propose Entropy-regularized Policy Optimization (EPO), a general framework that breaks this failure cycle through three synergistic mechanisms: (1) adopting entropy regularization in multi-turn settings to enhance exploration, (2) an entropy smoothing regularizer that bounds policy entropy within historical averages to prevent abrupt fluctuations, and (3) adaptive phase-based weighting that balances exploration and exploitation across training. Our analysis justifies that EPO guarantees monotonically decreasing entropy variance while maintaining convergence. EPO achieves up to 152% performance improvement on ScienceWorld and up to 19.8% on ALFWorld. Our work demonstrates that multi-turn sparse-reward settings require fundamentally different entropy control than traditional RL, with broad implications for LLM agent training.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.22576</guid>
|
|
<pubDate>Fri, 26 Sep 2025 16:51:44 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Quantile Advantage Estimation for Entropy-Safe Reasoning</title>
|
|
<link>https://arxiv.org/abs/2509.22611</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.22611.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junkang Wu, Kexin Huang, Jiancan Wu, An Zhang, Xiang Wang, Xiangnan He</p><p><b>Upvotes:</b> 108</p><p><b>Summary:</b> Reinforcement Learning with Verifiable Rewards (RLVR) strengthens LLM reasoning, but training often oscillates between {entropy collapse} and {entropy explosion}. We trace both hazards to the mean baseline used in value-free RL (e.g., GRPO and DAPO), which improperly penalizes negative-advantage samples under reward outliers. We propose {Quantile Advantage Estimation} (QAE), replacing the mean with a group-wise K-quantile baseline. QAE induces a response-level, two-regime gate: on hard queries (p <= 1 - K) it reinforces rare successes, while on easy queries (p > 1 - K) it targets remaining failures. Under first-order softmax updates, we prove {two-sided entropy safety}, giving lower and upper bounds on one-step entropy change that curb explosion and prevent collapse. Empirically, this minimal modification stabilizes entropy, sparsifies credit assignment (with tuned K, roughly 80% of responses receive zero advantage), and yields sustained pass@1 gains on Qwen3-8B/14B-Base across AIME 2024/2025 and AMC 2023. These results identify {baseline design} -- rather than token-level heuristics -- as the primary mechanism for scaling RLVR.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.22611</guid>
|
|
<pubDate>Fri, 26 Sep 2025 17:37:52 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>LongLive: Real-time Interactive Long Video Generation</title>
|
|
<link>https://arxiv.org/abs/2509.22622</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.22622.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shuai Yang, Wei Huang, Ruihang Chu, Yicheng Xiao, Yuyang Zhao, Xianbang Wang, Muyang Li, Enze Xie, Yingcong Chen, Yao Lu, Song Han, Yukang Chen</p><p><b>Upvotes:</b> 157</p><p><b>Summary:</b> We present LongLive, a frame-level autoregressive (AR) framework for real-time and interactive long video generation. Long video generation presents challenges in both efficiency and quality. Diffusion and Diffusion-Forcing models can produce high-quality videos but suffer from low efficiency due to bidirectional attention. Causal attention AR models support KV caching for faster inference, but often degrade in quality on long videos due to memory challenges during long-video training. In addition, beyond static prompt-based generation, interactive capabilities, such as streaming prompt inputs, are critical for dynamic content creation, enabling users to guide narratives in real time. This interactive requirement significantly increases complexity, especially in ensuring visual consistency and semantic coherence during prompt transitions. To address these challenges, LongLive adopts a causal, frame-level AR design that integrates a KV-recache mechanism that refreshes cached states with new prompts for smooth, adherent switches; streaming long tuning to enable long video training and to align training and inference (train-long-test-long); and short window attention paired with a frame-level attention sink, shorten as frame sink, preserving long-range consistency while enabling faster generation. With these key designs, LongLive fine-tunes a 1.3B-parameter short-clip model to minute-long generation in just 32 GPU-days. At inference, LongLive sustains 20.7 FPS on a single NVIDIA H100, achieves strong performance on VBench in both short and long videos. LongLive supports up to 240-second videos on a single H100 GPU. LongLive further supports INT8-quantized inference with only marginal quality loss.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.22622</guid>
|
|
<pubDate>Fri, 26 Sep 2025 17:48:24 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Variational Reasoning for Language Models</title>
|
|
<link>https://arxiv.org/abs/2509.22637</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.22637.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiangxin Zhou, Zichen Liu, Haonan Wang, Chao Du, Min Lin, Chongxuan Li, Liang Wang, Tianyu Pang</p><p><b>Upvotes:</b> 58</p><p><b>Summary:</b> We introduce a variational reasoning framework for language models that treats thinking traces as latent variables and optimizes them through variational inference. Starting from the evidence lower bound (ELBO), we extend it to a multi-trace objective for tighter bounds and propose a forward-KL formulation that stabilizes the training of the variational posterior. We further show that rejection sampling finetuning and binary-reward RL, including GRPO, can be interpreted as local forward-KL objectives, where an implicit weighting by model accuracy naturally arises from the derivation and reveals a previously unnoticed bias toward easier questions. We empirically validate our method on the Qwen 2.5 and Qwen 3 model families across a wide range of reasoning tasks. Overall, our work provides a principled probabilistic perspective that unifies variational inference with RL-style methods and yields stable objectives for improving the reasoning ability of language models. Our code is available at https://github.com/sail-sg/variational-reasoning.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.22637</guid>
|
|
<pubDate>Fri, 26 Sep 2025 17:58:10 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Language Models Can Learn from Verbal Feedback Without Scalar Rewards</title>
|
|
<link>https://arxiv.org/abs/2509.22638</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.22638.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Renjie Luo, Zichen Liu, Xiangyan Liu, Chao Du, Min Lin, Wenhu Chen, Wei Lu, Tianyu Pang</p><p><b>Upvotes:</b> 57</p><p><b>Summary:</b> LLMs are often trained with RL from human or AI feedback, yet such methods typically compress nuanced feedback into scalar rewards, discarding much of their richness and inducing scale imbalance. We propose treating verbal feedback as a conditioning signal. Inspired by language priors in text-to-image generation, which enable novel outputs from unseen prompts, we introduce the feedback-conditional policy (FCP). FCP learns directly from response-feedback pairs, approximating the feedback-conditional posterior through maximum likelihood training on offline data. We further develop an online bootstrapping stage where the policy generates under positive conditions and receives fresh feedback to refine itself. This reframes feedback-driven learning as conditional generation rather than reward optimization, offering a more expressive way for LLMs to directly learn from verbal feedback. Our code is available at https://github.com/sail-sg/feedback-conditional-policy.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.22638</guid>
|
|
<pubDate>Fri, 26 Sep 2025 17:58:27 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Multiplayer Nash Preference Optimization</title>
|
|
<link>https://arxiv.org/abs/2509.23102</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.23102.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fang Wu, Xu Huang, Weihao Xuan, Zhiwei Zhang, Yijia Xiao, Guancheng Wan, Xiaomin Li, Bing Hu, Peng Xia, Jure Leskovec, Yejin Choi</p><p><b>Upvotes:</b> 52</p><p><b>Summary:</b> Reinforcement learning from human feedback (RLHF) has emerged as the standard paradigm for aligning large language models (LLMs) with human preferences. However, reward-based methods built on the Bradley-Terry assumption struggle to capture the non-transitive and heterogeneous nature of real-world preferences. To address this, recent studies have reframed alignment as a two-player Nash game, giving rise to Nash learning from human feedback (NLHF). While this perspective has inspired algorithms such as INPO, ONPO, and EGPO with strong theoretical and empirical guarantees, they remain fundamentally restricted to two-player interactions, creating a single-opponent bias that fails to capture the full complexity of realistic preference structures. In this work, we introduce Multiplayer Nash Preference Optimization (MNPO), a novel framework that generalizes NLHF to the multiplayer regime. It formulates alignment as an n-player game, where each policy competes against a population of opponents while being regularized toward a reference model. Our framework establishes well-defined Nash equilibria in multiplayer settings and extends the concept of duality gap to quantify approximation quality. We demonstrate that MNPO inherits the equilibrium guarantees of two-player methods while enabling richer competitive dynamics and improved coverage of diverse preference structures. Through comprehensive empirical evaluation, we show that MNPO consistently outperforms existing NLHF baselines on instruction-following benchmarks, achieving superior alignment quality under heterogeneous annotator conditions and mixed-policy evaluation scenarios. Together, these results establish MNPO as a principled and scalable framework for aligning LLMs with complex, non-transitive human preferences. Code is available at https://github.com/smiles724/MNPO.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.23102</guid>
|
|
<pubDate>Sat, 27 Sep 2025 04:18:33 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Democratizing AI scientists using ToolUniverse</title>
|
|
<link>https://arxiv.org/abs/2509.23426</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.23426.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shanghua Gao, Richard Zhu, Pengwei Sui, Zhenglun Kong, Sufian Aldogom, Yepeng Huang, Ayush Noori, Reza Shamji, Krishna Parvataneni, Theodoros Tsiligkaridis, Marinka Zitnik</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> AI scientists are emerging computational systems that serve as collaborative partners in discovery. These systems remain difficult to build because they are bespoke, tied to rigid workflows, and lack shared environments that unify tools, data, and analyses into a common ecosystem. In omics, unified ecosystems have transformed research by enabling interoperability, reuse, and community-driven development; AI scientists require comparable infrastructure. We present ToolUniverse, an ecosystem for building AI scientists from any language or reasoning model, whether open or closed. TOOLUNIVERSE standardizes how AI scientists identify and call tools, integrating more than 600 machine learning models, datasets, APIs, and scientific packages for data analysis, knowledge retrieval, and experimental design. It automatically refines tool interfaces for correct use by AI scientists, creates new tools from natural language descriptions, iteratively optimizes tool specifications, and composes tools into agentic workflows. In a case study of hypercholesterolemia, ToolUniverse was used to create an AI scientist to identify a potent analog of a drug with favorable predicted properties. The open-source ToolUniverse is available at https://aiscientist.tools.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.23426</guid>
|
|
<pubDate>Sat, 27 Sep 2025 17:38:53 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Beyond the Exploration-Exploitation Trade-off: A Hidden State Approach for LLM Reasoning in RLVR</title>
|
|
<link>https://arxiv.org/abs/2509.23808</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.23808.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fanding Huang, Guanbo Huang, Xiao Fan, Yi He, Xiao Liang, Xiao Chen, Qinting Jiang, Faisal Nadeem Khan, Jingyan Jiang, Zhi Wang</p><p><b>Upvotes:</b> 38</p><p><b>Summary:</b> A prevailing view in Reinforcement Learning for Verifiable Rewards (RLVR) interprets recent progress through the lens of an exploration-exploitation trade-off, a perspective largely shaped by token-level metrics. We re-examine this perspective, proposing that this perceived trade-off may not be a fundamental constraint but rather an artifact of the measurement level. To investigate this, we shift the analysis to the semantically rich hidden-state space, adopting Effective Rank (ER) to quantify exploration and proposing its novel first- and second-order derivatives, named Effective Rank Velocity (ERV) and Effective Rank Acceleration (ERA), to capture exploitation dynamics. Our analysis reveals that at the hidden-state level, exploration and exploitation could be decoupled (Sec. 4). This finding reveals an opportunity to enhance both capacities simultaneously. This insight motivates our method, Velocity-Exploiting Rank-Learning (VERL), the first to operationalize the principle of synergistic exploration-exploitation enhancement by directly shaping the RL advantage function. The key innovation is leveraging the theoretically stable ERA as a predictive meta-controller to create a synergistic, dual-channel incentive structure. Instead of forcing a trade-off, VERL prospectively amplifies rewards for exploration to preempt overconfidence and reinforces exploitative gains to consolidate reasoning. Experiments across diverse LLMs and reasoning benchmarks show consistent gains, including up to 21.4% absolute accuracy improvement on the challenging Gaokao 2024 dataset.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.23808</guid>
|
|
<pubDate>Sun, 28 Sep 2025 11:14:58 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse-Linear Attention</title>
|
|
<link>https://arxiv.org/abs/2509.24006</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.24006.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jintao Zhang, Haoxu Wang, Kai Jiang, Shuo Yang, Kaiwen Zheng, Haocheng Xi, Ziteng Wang, Hongzhou Zhu, Min Zhao, Ion Stoica, Joseph E. Gonzalez, Jun Zhu, Jianfei Chen</p><p><b>Upvotes:</b> 98</p><p><b>Summary:</b> In Diffusion Transformer (DiT) models, particularly for video generation, attention latency is a major bottleneck due to the long sequence length and the quadratic complexity. We find that attention weights can be separated into two parts: a small fraction of large weights with high rank and the remaining weights with very low rank. This naturally suggests applying sparse acceleration to the first part and low-rank acceleration to the second. Based on this finding, we propose SLA (Sparse-Linear Attention), a trainable attention method that fuses sparse and linear attention to accelerate diffusion models. SLA classifies attention weights into critical, marginal, and negligible categories, applying O(N^2) attention to critical weights, O(N) attention to marginal weights, and skipping negligible ones. SLA combines these computations into a single GPU kernel and supports both forward and backward passes. With only a few fine-tuning steps using SLA, DiT models achieve a 20x reduction in attention computation, resulting in significant acceleration without loss of generation quality. Experiments show that SLA reduces attention computation by 95% without degrading end-to-end generation quality, outperforming baseline methods. In addition, we implement an efficient GPU kernel for SLA, which yields a 13.7x speedup in attention computation and a 2.2x end-to-end speedup in video generation on Wan2.1-1.3B.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.24006</guid>
|
|
<pubDate>Sun, 28 Sep 2025 17:58:59 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer</title>
|
|
<link>https://arxiv.org/abs/2509.24695</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.24695.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junsong Chen, Yuyang Zhao, Jincheng Yu, Ruihang Chu, Junyu Chen, Shuai Yang, Xianbang Wang, Yicheng Pan, Daquan Zhou, Huan Ling, Haozhe Liu, Hongwei Yi, Hao Zhang, Muyang Li, Yukang Chen, Han Cai, Sanja Fidler, Ping Luo, Song Han, Enze Xie</p><p><b>Upvotes:</b> 35</p><p><b>Summary:</b> We introduce SANA-Video, a small diffusion model that can efficiently generate videos up to 720x1280 resolution and minute-length duration. SANA-Video synthesizes high-resolution, high-quality and long videos with strong text-video alignment at a remarkably fast speed, deployable on RTX 5090 GPU. Two core designs ensure our efficient, effective and long video generation: (1) Linear DiT: We leverage linear attention as the core operation, which is more efficient than vanilla attention given the large number of tokens processed in video generation. (2) Constant-Memory KV cache for Block Linear Attention: we design block-wise autoregressive approach for long video generation by employing a constant-memory state, derived from the cumulative properties of linear attention. This KV cache provides the Linear DiT with global context at a fixed memory cost, eliminating the need for a traditional KV cache and enabling efficient, minute-long video generation. In addition, we explore effective data filters and model training strategies, narrowing the training cost to 12 days on 64 H100 GPUs, which is only 1% of the cost of MovieGen. Given its low cost, SANA-Video achieves competitive performance compared to modern state-of-the-art small diffusion models (e.g., Wan 2.1-1.3B and SkyReel-V2-1.3B) while being 16x faster in measured latency. Moreover, SANA-Video can be deployed on RTX 5090 GPUs with NVFP4 precision, accelerating the inference speed of generating a 5-second 720p video from 71s to 29s (2.4x speedup). In summary, SANA-Video enables low-cost, high-quality video generation.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.24695</guid>
|
|
<pubDate>Mon, 29 Sep 2025 12:28:09 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>RealUnify: Do Unified Models Truly Benefit from Unification? A Comprehensive Benchmark</title>
|
|
<link>https://arxiv.org/abs/2509.24897</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.24897.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yang Shi, Yuhao Dong, Yue Ding, Yuran Wang, Xuanyu Zhu, Sheng Zhou, Wenting Liu, Haochen Tian, Rundong Wang, Huanqian Wang, Zuyan Liu, Bohan Zeng, Ruizhe Chen, Qixun Wang, Zhuoran Zhang, Xinlong Chen, Chengzhuo Tong, Bozhou Li, Chaoyou Fu, Qiang Liu, Haotian Wang, Wenjing Yang, Yuanxing Zhang, Pengfei Wan, Yi-Fan Zhang, Ziwei Liu</p><p><b>Upvotes:</b> 41</p><p><b>Summary:</b> The integration of visual understanding and generation into unified multimodal models represents a significant stride toward general-purpose AI. However, a fundamental question remains unanswered by existing benchmarks: does this architectural unification actually enable synergetic interaction between the constituent capabilities? Existing evaluation paradigms, which primarily assess understanding and generation in isolation, are insufficient for determining whether a unified model can leverage its understanding to enhance its generation, or use generative simulation to facilitate deeper comprehension. To address this critical gap, we introduce RealUnify, a benchmark specifically designed to evaluate bidirectional capability synergy. RealUnify comprises 1,000 meticulously human-annotated instances spanning 10 categories and 32 subtasks. It is structured around two core axes: 1) Understanding Enhances Generation, which requires reasoning (e.g., commonsense, logic) to guide image generation, and 2) Generation Enhances Understanding, which necessitates mental simulation or reconstruction (e.g., of transformed or disordered visual inputs) to solve reasoning tasks. A key contribution is our dual-evaluation protocol, which combines direct end-to-end assessment with a diagnostic stepwise evaluation that decomposes tasks into distinct understanding and generation phases. This protocol allows us to precisely discern whether performance bottlenecks stem from deficiencies in core abilities or from a failure to integrate them. Through large-scale evaluations of 12 leading unified models and 6 specialized baselines, we find that current unified models still struggle to achieve effective synergy, indicating that architectural unification alone is insufficient. These results highlight the need for new training strategies and inductive biases to fully unlock the potential of unified modeling.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.24897</guid>
|
|
<pubDate>Mon, 29 Sep 2025 15:07:28 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>OpenGPT-4o-Image: A Comprehensive Dataset for Advanced Image Generation and Editing</title>
|
|
<link>https://arxiv.org/abs/2509.24900</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.24900.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhihong Chen, Xuehai Bai, Yang Shi, Chaoyou Fu, Huanyu Zhang, Haotian Wang, Xiaoyan Sun, Zhang Zhang, Liang Wang, Yuanxing Zhang, Pengfei Wan, Yi-Fan Zhang</p><p><b>Upvotes:</b> 38</p><p><b>Summary:</b> The performance of unified multimodal models for image generation and editing is fundamentally constrained by the quality and comprehensiveness of their training data. While existing datasets have covered basic tasks like style transfer and simple object manipulation, they often lack the systematic structure and challenging scenarios required for real-world applications. To address this bottleneck, we introduce OpenGPT-4o-Image, a large-scale dataset constructed using a novel methodology that combines hierarchical task taxonomy with automated data generation. Our taxonomy not only includes fundamental capabilities such as text rendering and style control but also introduces highly practical yet challenging categories like scientific imagery for chemistry illustrations and complex instruction editing requiring simultaneous execution of multiple operations. Through an automated pipeline leveraging structured resource pools and GPT-4o, we generate 80k high-quality instruction-image pairs with controlled diversity, covering 11 major domains and 51 subtasks. Extensive experiments show that fine-tuning leading models on our dataset achieves significant performance gains across multiple benchmarks, with improvements of up to 18\% on editing tasks (UniWorld-V1 on ImgEdit-Bench) and 13% on generation tasks (Harmon on GenEval). Our work demonstrates that systematic data construction is key to advancing multimodal AI capabilities.</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.24900</guid>
|
|
<pubDate>Mon, 29 Sep 2025 15:11:09 +0000</pubDate>
|
|
</item>
|
|
<item>
|
|
<title>Visual Jigsaw Post-Training Improves MLLMs</title>
|
|
<link>https://arxiv.org/abs/2509.25190</link>
|
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.25190.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Penghao Wu, Yushan Zhang, Haiwen Diao, Bo Li, Lewei Lu, Ziwei Liu</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> Reinforcement learning based post-training has recently emerged as a powerful paradigm for enhancing the alignment and reasoning capabilities of multimodal large language models (MLLMs). While vision-centric post-training is crucial for enhancing MLLMs' intrinsic understanding of visual signals, current post-training paradigms are predominantly text-centric, where dense visual inputs are only leveraged to extract sparse cues for text-based reasoning. There exist a few approaches in this direction, however, they often still rely on text as an intermediate mediator or introduce additional visual generative designs. In this work, we introduce Visual Jigsaw, a generic self-supervised post-training framework designed to strengthen visual understanding in MLLMs. Visual Jigsaw is formulated as a general ordering task: visual inputs are partitioned, shuffled, and the model must reconstruct the visual information by producing the correct permutation in natural language. This naturally aligns with reinforcement learning from verifiable rewards (RLVR), requires no additional visual generative components, and derives its supervisory signal automatically without any annotations. We instantiate Visual Jigsaw across three visual modalities, including images, videos, and 3D data. Extensive experiments demonstrate substantial improvements in fine-grained perception, temporal reasoning, and 3D spatial understanding. Our findings highlight the potential of self-supervised vision-centric tasks in post-training MLLMs and aim to inspire further research on vision-centric pretext designs. Project Page: https://penghao-wu.github.io/visual_jigsaw/</p></description>
|
|
<guid isPermaLink="false">https://arxiv.org/abs/2509.25190</guid>
|
|
<pubDate>Mon, 29 Sep 2025 17:59:57 +0000</pubDate>
|
|
</item>
|
|
</channel>
|
|
</rss>
|