Hugging Face 动态
热门模型 · 每日论文 · 热门 Spaces
Hugging Face 上正在火的模型、论文和在线 Demo,数据来自 HF 官方公开接口,严格按 HF 热度排名,每 6 小时更新一次。
2026 年 10 月 27 日的论文(UTC)· 回到最新
10 月 27 日62 篇
- 353点赞Trajectory2Gym: Decision-Grounded Compositional Interaction Synthesis for Tool-Use Agents
arXiv 2610.33568Yihao Hu, Zhihao Wen, Yitong Lin 等 8 人代码 ↗项目主页 ↗
- 280点赞Trial by Trace: Benchmarking AI Agent Harnesses for Reliability and Failure Attribution
arXiv 2610.32285Zhiyong Cao, Hengjie Zhu, Yongxin Wang 等 23 人代码 ↗项目主页 ↗
- 252点赞StreamVibe: Proactive Video Agents for Evolving User Intent
arXiv 2610.34662Chengzhi Liu, Yuxiang Lai, Yuzhe Yang 等 16 人
- 203点赞DynaFlow: Learning Free-Form Multi-Agent Orchestration
arXiv 2610.34467Ruhao Liu, Qi Li, Shizun Wang 等 4 人代码 ↗项目主页 ↗
- 122点赞InteractiveWorld: A Verifiable Human-Centric Environment for Building Better Interactive MLLM Assistants
arXiv 2610.33966Qinsi Wang, Wei Wen, Chong Zhou 等 10 人代码 ↗项目主页 ↗
- 117点赞Work Agents: Systems, Capabilities, and Optimization
arXiv 2610.35845Zishan Xu, Enjun Du, Mingqi Gao 等 16 人代码 ↗项目主页 ↗
- 61点赞
- 57点赞Spatial Audio Generation and Editing with Executable Plans and Self-Distilling Transfusion
arXiv 2610.34415Kam Man Wu, Yu Zhang, Pengjun Fang 等 7 人代码 ↗项目主页 ↗
- 52点赞Continual Learning Exam: Benchmarking Long-Horizon RSI and Experiential Learning in LLM Agents
arXiv 2610.33956Haoyu Zhao, Sitian Tu, Yuxuan Huang 等 19 人代码 ↗项目主页 ↗
- 50点赞Eat Your Precision: Precision Objective Mitigates Reward Hacking in Rubric-based RL
arXiv 2610.33512Hyun Ryu, Jong-Heon Kim, Yiqing Xie 等 6 人代码 ↗
- 48点赞WorldCast: World-Consistent Character Video Generation with Large-Angle Camera Control
arXiv 2610.33135Lei Cao, Yu Liu, Wenhua Liao 等 10 人代码 ↗项目主页 ↗
- 48点赞AV-FABLE: Audio-Visual Manipulation Forensics in Long-Form Videos
arXiv 2610.33413Yuesheng Huang, Hoi Fan Au, Jiaqi Hou 等 11 人
- 43点赞HiP3R: Hierarchical Pose Graphs for Long-Horizon 3D Reconstruction
arXiv 2610.31635Zunnan Xu, Shangchen Zhou, Yihang Luo 等 4 人代码 ↗项目主页 ↗
- 37点赞Principia: Test-Time Hypotheses to Principle Construction for Scientific Discovery
arXiv 2610.32195Dongki Kim, Sangwoo Park, Jinheon Baek 等 5 人
- 35点赞Qwen-Image-PE: Learning Visual Design for Text-to-Image Prompt Enhancement
arXiv 2610.33472Zekai Zhang, Yanran Zhang, Shengming Yin 等 29 人
- 33点赞S3AC: Stabilized, Selective, and Scalable Actor-Critic for LLM Reasoning
arXiv 2610.35518Shuo Shen, Guangran Cheng, Chengqi Lyu 等 6 人代码 ↗
- 31点赞Evolving to Match Capabilities: Improving Harness Self-Evolution via Skill Adaptation
arXiv 2610.33024Zhihao Yang, Haojin Wang, Juncheng Wu 等 10 人代码 ↗项目主页 ↗
- 30点赞RynnVLA-Latent: Scaling Robotic Manipulation Foundation Models with 3D-Grounded Latent Actions
arXiv 2610.34356Haoyu Zhao, Xingyue Zhao, Zhian Su 等 14 人代码 ↗项目主页 ↗
- 28点赞Build, Don't Play: Self-Improving LLM Research Agents Develop a Hearthstone Battlegrounds AI That Rivals Top Players
arXiv 2610.33845Changlian Ma, Limin Wang代码 ↗
- 27点赞Δτ-Bench: Pushing Agents Toward a Moving Capability
arXiv 2610.34238Shuofei Qiao, Xuanguang Pan, Yijun Chen 等 9 人代码 ↗
- 27点赞World-in-Context: Interactive Video World Modeling with In-Context Conditioning
arXiv 2610.33169Harold Haodong Chen, Rui Peng, Rongjin Guo 等 7 人代码 ↗项目主页 ↗
- 26点赞ProAS: A Progress-Aware Advantage Shaping Framework for Multi-Turn Agentic Reinforcement Learning
arXiv 2610.18683Bowen Ding, Mingda Wan, Yuhan Chen 等 10 人代码 ↗
- 26点赞Mycelium: A Meta-Study of Hallucination Detection Across Provenance, Typology, and Granularities
arXiv 2610.33608Julia Belikova, Elisei Rykov代码 ↗
- 24点赞Trustworthy Recursive Self-Improvement in the Era of Large Models: Foundation, Risks, Evaluation and Open Challenges
arXiv 2610.35193Jiayue Pu, Ang Gao, Jinyi Bai 等 12 人
- 24点赞miniTE: Diagnosing and Bridging the Execution Gap in Native NVFP4 Reinforcement Learning
arXiv 2610.23928Zhen Li, Mingfa Feng, Yiming Zhang 等 9 人项目主页 ↗
- 23点赞More Memory, Better Videos? A Controlled Study of Visual Memory in Long-Video Generation
arXiv 2610.35001Yuzhuo Chen, Huafeng Shi, Xinyu Wang 等 9 人代码 ↗项目主页 ↗
- 22点赞
- 22点赞How Far Can Coding Agents Go in Visual Generation?
arXiv 2610.19025Hengguang Zhou, Yuanhao Ban, Jiaqi Feng 等 6 人项目主页 ↗
- 22点赞CausalAlign: Causal Alignment of Video Generation Models for Consistent Ego-Motion
arXiv 2610.29915Kai Zhu, Yintianrun Zhang, Shuwei Jiang 等 10 人代码 ↗项目主页 ↗
- 20点赞iPrefBench: A User-Centric Benchmark for Personalized Mobile Use Agents
arXiv 2610.34735Yuting Ning, Ruijia Cheng, Sushobhan Ghosh 等 10 人
- 19点赞EmbodiedLab: Benchmarking Embodied Agents That Act to Know
arXiv 2610.35385Hongcheng Gao, Zelin Zheng, Alex Zhou 等 21 人代码 ↗项目主页 ↗
- 19点赞Thinking-in-Bets at Test Time Reduces Sycophantic Revisions in LLM Agents
arXiv 2610.34654Nghi D. Q. Bui项目主页 ↗
- 17点赞ReGE: Stronger Agents through Experience Synthesis
arXiv 2610.33861Jiarong Liang, Yubo Wang, Zijie Liu 等 6 人代码 ↗项目主页 ↗
- 16点赞ParetoRSI-Gym: Can AI Agents Improve Language Models Across Multiple Domains?
arXiv 2610.34386Haojin Wang, Yangzhen Wu, Zeyi Chen 等 9 人代码 ↗
- 16点赞Extreme Compression of Per-Layer Embeddings via Cross-Layer Latent Vector Quantization
arXiv 2610.31309Jiacheng Liu, Yaxin Luo, Xiaohan Zhao 等 8 人代码 ↗
- 15点赞Rethinking Video Storage for AI Training: Breaking Cross-Frame Dependencies for Efficient Random Access
arXiv 2610.33079Zetian Song, Qize Yu, Yue Chen 等 13 人代码 ↗项目主页 ↗
- 15点赞Novel or Not? PatEx-Gym: Agentic Prior-Art Search for Novelty Assessment in Patent Examination
arXiv 2610.33503Qiyao Wang, Xinyi Chen, Hongbo Wang 等 8 人代码 ↗项目主页 ↗
- 14点赞RoboJev: An Open Vision-Language Judge for Robot Success Detection
arXiv 2610.33718Josef Liyanjun Chen项目主页 ↗
- 14点赞AgentProofBench: Benchmarking Reusable Verifiers for Web Agents
arXiv 2610.34634Jingjie Ning, Xueqi Li, Yi Lu 等 4 人代码 ↗项目主页 ↗
- 14点赞
- 13点赞Beyond Benchmarks: Can Small Open-Weight Models Get Real Coding Work Done?
arXiv 2610.34241Vaibhav Jain
- 12点赞DialFork: Going Beyond Factuality to Evaluate Procedural Hallucination in Conversational Agents
arXiv 2610.21561Sergio Burdisso, Esaú Villatoro-Tello, Dairazalia Sánchez-Cortés 等 7 人代码 ↗
- 12点赞
- 11点赞Skill^{infty}: Recursive Self-Improvement for Agent Skill Optimization
arXiv 2610.35434Wangcheng Tao, Zhanglu Yan, Han Wu 等 4 人代码 ↗项目主页 ↗
- 11点赞CRM-Agent-Bench: Benchmarking Tool-Using Agents in Stateful Enterprise Environments
arXiv 2610.32004Monojit Banerjee, Zhujun Lan, Defu Cao代码 ↗项目主页 ↗
- 9点赞Trust Mechanisms for Offline Generative AI at the Edge: A Connectivity-Regime Framework and an Empirical Study on a Raspberry Pi 5
arXiv 2610.33732Georgios Feretzakis, Alexandros Papaspyridis代码 ↗项目主页 ↗
- 9点赞Rethinking Verification in Agent Harnesses
arXiv 2610.34577Zhengxin Zhang, Erkang Zhu, Yin Lin 等 6 人
- 9点赞
- 9点赞Constrained Decoding: Harmful or Beneficial? Revisiting Its Impact on LLM Performance
arXiv 2610.35328Ngoc Trinh Hung Nguyen, Alonso Silva, Armen Aghasaryan 等 4 人
- 8点赞Steering Black-Box Large Language Model Agents with Pitfall Anticipation World Model
arXiv 2610.29139Jiongxiao Wang, Han Ding, Youzhi Luo 等 7 人
- 8点赞Semantic Concept Steering Breaks the Explanation Drift Loop in Continual Learning
arXiv 2610.33877Yehonatan Elisha, Oren Barkan, Noam Koenigstein
- 7点赞Intrinsic Goals for Autonomous Agents: Hierarchical Exploration Captures Future Volitional Action in Drosophila
arXiv 2610.34638Declan Kutscher, Reece Keller, Alyn Kirsch 等 5 人代码 ↗项目主页 ↗
- 6点赞OpenESM: Energy-Steered Models Are Scalable Foundation Learners
arXiv 2610.33005Yuan Pu, Yudong Lu, Ting Wang 等 9 人代码 ↗项目主页 ↗
- 6点赞Assessing the CAD Capabilities of General-Purpose AI Models: A Case Study of GPT-6 Astra
arXiv 2610.24451Qiang Zou, Jiajun Shen, Zhijie Yang 等 6 人项目主页 ↗
- 6点赞Did the Model Use That? Counterfactual Training Boosts Self-Attribution in Language Models
arXiv 2610.35295Zikai Zhou, Jiacheng Sang, Yilin Xu 等 5 人代码 ↗
- 6点赞EnvLunch: The Environment as a Free Lunch for Learning to Interact
arXiv 2610.33817Wei Liu, Min Gao, Yali Du 等 4 人代码 ↗
- 5点赞
- 5点赞
- 5点赞ThinkBit: Search Codewords, Recalibrate Scales, Select by Reasoning
arXiv 2610.34886Rhea Sanjay Sukthanker, Pashmina Cameron
- 4点赞Humans in Space: Can MLLMs Construct Human-Centric Spatial Understanding via Active Exocentric Exploration?
arXiv 2610.34149Tianchen Guo, Tengyue Zhang, Chen Liu 等 5 人代码 ↗项目主页 ↗
- 3点赞Ψ-0.6: Adaptive Streams of Thought in a Unified Vision-Language World Model
arXiv 2610.32177Khai Loong Aw, Klemen Kotar, Baihan Zhang 等 8 人代码 ↗项目主页 ↗
- 3点赞CellTrack-Bench: Microscopic Cell Tracking Benchmark for Vision-Language Models
arXiv 2610.31566Ilan Theodoro, Jordão Bragantini, Loïc A. Royer代码 ↗
数据说明
数据来源
热门模型、热门 Spaces、每日论文分别来自 Hugging Face 官方公开接口,每 6 小时抓取一次,按 UTC 日期每天存一份快照,可以按日期回看。论文标题保留英文原文。
排名口径
排名完全按 HF 返回的热度(trendingScore),本站不做任何筛选或调整,看到的就是 HF 热榜本身。同一天多次抓取时,以当天最后一次为准。按任务类型或 SDK 筛选只是缩小列表,名次仍是 HF 热榜上的原名次。
点赞增量与新上榜
「7 天增量」是所看那一天快照的点赞数减去它之前 7 天内最早一份快照的点赞数;历史不满 7 天时括号里标出实际天数,没有更早的快照则显示「—」。「新上榜」指那一天在榜、之前的快照里从没出现过。
免责声明
本页不是 Hugging Face 的官方页面。模型和 Space 的许可、用途与内容以 Hugging Face 原页面为准。