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。
每 6 小时更新 · 上次更新 10/6 10:49（北京时间）
10 月 6 日4 篇
- 4点赞Rethinking Long-Video Efficiency: A Joint Allocation Perspective on Frames, Pixels, and Front-End Latency
arXiv 2610.04318Sixun Dong, Wei Li, Andong Deng 等 7 人项目主页 ↗
- 1点赞OSWorld-Pro: Process-based Evaluation for Computer Use Agents
arXiv 2609.24890Zhilin Wang, Shaokun Zhang, Yifan Zhang 等 12 人
- 1点赞PluginRSI: Recursive Improvement of Agent Harnesses with Reusable Plugins
arXiv 2609.32423Yaorui Shi, Yuchun Miao, Yuxin Chen 等 8 人
- 1点赞Prism: Dynamic Sparse Attention for Native 2K Joint Video-Audio Generation Model Training
arXiv 2610.05416Shuyuan Tu, Qi Tian, Yinming Huang 等 11 人代码 ↗项目主页 ↗
10 月 5 日65 篇
- 256点赞RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations
arXiv 2610.01780Arman Behnam, Sunglyoung Kim, Liangwei Yang
- 113点赞Does Learning Protein Folding Generalize to Broader Reasoning?
arXiv 2609.38879Yong Liu, Zhanpeng Shi, Yizhou Dang 等 7 人代码 ↗
- 91点赞FrameMorrow: Future-guided Frame Selection with Prospective Tokens for Long-Horizon Video Generation
arXiv 2609.38839Bo Yin, Xiaobin Hu, Jiaqi Zhao 等 4 人代码 ↗项目主页 ↗
- 89点赞MotorMind: Scaffolding General Vision Language Models for Zero-Shot Robot Manipulation
arXiv 2609.38078Bingxuan Li, Siqi Song, Yizhuo Wu 等 6 人项目主页 ↗
- 83点赞Scaling Trajectories for Complex Tasks through Recursive Self-Rewrite
arXiv 2610.02826Zongxia Li, Yucheng Shi, Zhongzhi Li 等 10 人
- 77点赞On-Policy Parameter Update Direction Underlies Generalization in LLM Post-Training
arXiv 2609.36659Shufan Shen, Zhongni Hou, Junshu Sun 等 8 人代码 ↗
- 76点赞Native Action-Prior Learning from Videos for World Action Models
arXiv 2610.03391Zhaochong An, Fei Zhang, Menglin Jia 等 13 人项目主页 ↗
- 76点赞World Action Modeling with Progressive Visual Planning
arXiv 2610.02508Fei Zhang, Zhaochong An, Duncan Frost 等 8 人项目主页 ↗
- 54点赞Latent-MOPD: Latent Multi-Teacher On-Policy Distillation
arXiv 2610.02381Zhengyu Fang, Seoyeon Hong, Jie Yang 等 7 人项目主页 ↗
- 51点赞PDE-JEPA: Predictive Representation Learning of Latent Dynamics Modeling for Parametric PDEs
arXiv 2609.34715Zhentao Tan, Jianrong Zhang, Ruijie Quan 等 4 人代码 ↗项目主页 ↗
- 51点赞HyperBrowseComp: A Multilingual and Multimodal Stress Test for Web-Browsing Agents
arXiv 2610.03574Alham Fikri Aji, Faiz Rizki Ramadhan, Zayd M. K. Zuhri 等 17 人
- 50点赞Science or Slop?: Benchmarking and Mitigating Scientific Slop in AI-Generated Papers
arXiv 2610.00531Yerim Oh, Young-Jun Lee, Jaewoo Ahn 等 5 人代码 ↗项目主页 ↗
- 50点赞LexReward: A Taxonomy-Driven Reward Framework for Legal Language Models
arXiv 2609.39071Yida Cai, Xin Dai, Bingxiang He 等 8 人
- 50点赞Pivot-SD: Efficient Self-Distillation for Masked Diffusion Language Models
arXiv 2610.03665Seo Hyun Kim, Sunwoo Hong, Younwoo Choi 等 6 人项目主页 ↗
- 47点赞EditHero: A Benchmark for Long-Horizon Part-Level 3D Editing and Vibe Modeling
arXiv 2610.02298Ruihan Yu, Yu-Ju Tsai, Muyao Niu 等 12 人代码 ↗项目主页 ↗
- 46点赞VeriHarness: Scaling Agentic Verification for Long-Horizon Tasks
arXiv 2610.00972Caiqi Zhang, Rujun Han, Zifeng Wang 等 7 人代码 ↗项目主页 ↗
- 46点赞SimuVerity: Benchmarking Agents for Engineering-Grade Simulink Model Generation
arXiv 2610.02304Ruiqi Zhang, Jiahao Wang, Mingxuan Li 等 12 人代码 ↗项目主页 ↗
- 44点赞Spatial Memory Intelligence: Endowing World Models with Understanding-Driven Long-Term Memory
arXiv 2610.02521Ying Yang, Guiyu Zhang, Lianghua Huang 等 8 人代码 ↗项目主页 ↗
- 43点赞World Embedding Benchmark
arXiv 2610.03632Yiqi Liu, Ruifeng Yuan, Yang Wang 等 10 人代码 ↗
- 41点赞Multilingual GSM-Symbolic: What determines capability transfer across languages?
arXiv 2610.03367Kenneth Enevoldsen, Riley Herchert, Sofie Mosegaard 等 25 人代码 ↗项目主页 ↗
- 39点赞Science Utopia? Closed-Loop LLM Simulation of Academic Research Ecosystems
arXiv 2610.01257Yiqiao Jin, Yiyang Wang, Lucheng Fu 等 11 人代码 ↗项目主页 ↗
- 36点赞Source Preference in the Wild: How LLM Agents Favor Items by Source, and How to Reduce It
arXiv 2610.03195Jonghyun Song, Haewon Park, Jeonghoon Shim 等 5 人
- 32点赞DEFINE: Exemplar-Guided Accent Control for Zero-Shot TTS
arXiv 2609.32777Ambuj Mehrish, Abhinaba Roy, Alex Ivanov 等 5 人代码 ↗项目主页 ↗
- 32点赞HelixWorld: A Real-time Interactive Audio-Visual World Model
arXiv 2609.38123Lei Ke, Jiahao Pan, Zeyue Tian 等 16 人代码 ↗项目主页 ↗
- 27点赞Language Models that Play Chess and Explain Their Moves
arXiv 2610.03695Adithya Bhaskar, Jeffrey Cheng, Danqi Chen代码 ↗项目主页 ↗
- 26点赞ProAR: Learning Prospective Reasoning with Autoregressive Video Models
arXiv 2610.03664Linghui Shen, Tinghui Zhu, Sheng Zhang 等 4 人代码 ↗项目主页 ↗
- 25点赞Triadic Linear Attention: Three-Dimensional Recurrent States for Long-Context Sequence Modeling
arXiv 2609.36529Oliver Sieberling, Bharat Runwal, David Jin 等 6 人代码 ↗
- 23点赞Beyond Future Prediction: Denoising as Generative Adaptation for Robot Control
arXiv 2609.28339Zanyi Wang, Yuheng Lei, Dengyang Jiang 等 7 人代码 ↗项目主页 ↗
- 23点赞Local Support Learning
arXiv 2610.02126Assaf Ben-Kish, Akarsh Kumar, James Glass 等 4 人代码 ↗项目主页 ↗
- 21点赞Tail-Influence Sampling for CVaR Policy Evaluation
arXiv 2609.38096Pauline Bourigault, Xiaotong Ji, Matthieu Zimmer 等 5 人代码 ↗
- 21点赞FrugalEvo: Towards Cost-Aware LLM-Guided Program Evolution
arXiv 2610.03675Hui Chen, Xuan Qi, James Xu Zhao 等 8 人代码 ↗
- 20点赞Diptych: Scoped, AI-Interpreted Comparison for Reference Listening in Music Production
arXiv 2609.39963Chongjun Zhong, Abhinaba Roy, Archishman Ghosh 等 5 人
- 19点赞4DCodeBench: Benchmarking Agents on Inverse Graphics of Dynamic Scenes
arXiv 2610.03715Ruihong Shen, Žiga Kovačič, Peter Kulits 等 9 人代码 ↗项目主页 ↗
- 19点赞PointWAM: 3D World Action Modeling for Dexterous Robotic Manipulation
arXiv 2610.02840Chunghyun Park, Beomjun Kim, Seungcheol Park 等 8 人项目主页 ↗
- 19点赞
- 17点赞Rollout-Marginal Distillation for Long-Horizon Autoregressive Video Generation
arXiv 2609.37925Chenjian Gao, Zhihao Hu, Jianqi Ma 等 6 人代码 ↗项目主页 ↗
- 16点赞WEFT: Scaling Tool-Use Post-Training for General-Purpose Agents
arXiv 2609.36887Bo Mao, Hang He, Linting Wang 等 20 人
- 16点赞Equal Ranking Quality, Different Decisions: Measuring and Reducing Order Dependence in LLM Scorers
arXiv 2608.26762Markus Frohmann, Mahdiyar Ali Akbar Alavi, Elizabeth Lingg 等 4 人代码 ↗
- 16点赞LVMT: Video Mask Transformer for Long-term Video Segmentation
arXiv 2609.34895Narges Norouzi, Niccolò Cavagnero, Idil Esen Zulfikar 等 6 人代码 ↗项目主页 ↗
- 15点赞Skill2Real: Agentic Skill Learning for Zero-Shot Sim-to-Real Robot Manipulation
arXiv 2610.02788Xincheng He, Siyu Ma, Chang Yu 等 8 人项目主页 ↗
- 15点赞Looping Beyond Twice: A Scalable Recipe for Looped Mixture-of-Experts
arXiv 2610.01153Di He, Pengxiang Li, Da Chang 等 6 人代码 ↗
- 14点赞Collective Bias Mitigation via Model Routing and Collaboration
arXiv 2610.03240Mingzhe Du, Luu Anh Tuan, Xiaobao Wu 等 10 人
- 14点赞Learning from Runtime Feedback through Failure-Bank Self-Evolution for Vision-Language-Action Models
arXiv 2609.39820Mingyue Cui, Zheyuan Liu, Yihan Zhu 等 5 人代码 ↗项目主页 ↗
- 13点赞MinkowskiPE: Minkowski Positional Encoding for Spatiotemporal Perception
arXiv 2609.33804Yuhao Li, Louie Hong Yao, Tianyi Shi 等 7 人项目主页 ↗
- 13点赞Covert Assistance: Helpful LLM Agents Evade Oversight in Multi-Agent Systems
arXiv 2609.39050Deema Alnuhait, Gengyu Wang, Muhammad Khalifa 等 4 人
- 13点赞Efficient Reasoning Training Does Not Always Harm CoT Faithfulness and Monitorability
arXiv 2610.03509Samuel Lewis-Lim, Xingwei Tan, Mario Sanger 等 5 人
- 12点赞GTR: Gated Token Recurrence for Efficient Dense Prediction
arXiv 2609.26590Zhe Feng, Longfei Liu, Wei Liu 等 10 人代码 ↗项目主页 ↗
- 11点赞Rethinking Token Reweighting for SFT: Suppress, Reverse, and Extrapolate Learned Features
arXiv 2609.33463Cunchun Li, Haonan He, Yifan Gao 等 7 人
- 11点赞QuantWM: Temporally Consistent 2-Bit KV Cache Quantization for Video World Models
arXiv 2609.26425Jiaqi Zhao, Xiaobin Hu, Bo Yin 等 6 人项目主页 ↗
- 11点赞Where Does Retrieval-Based Open-Ended Evaluation Fail? Automatic Taxonomy Induction from Long-Form Medical Answer Factuality Verification
arXiv 2609.30467Heyuan Huang, Jirui Dai, Alexandra DeLucia 等 8 人
- 11点赞From Gradients to Capabilities: Understanding Multi-Teacher On-Policy Distillation
arXiv 2610.02179Siqi Zhu, Suozhi Huang, Kaixuan Zhang 等 7 人
- 11点赞From Retrieval to Typed Decisions: Calibrated System One Models from Biomedical Sentence Encoders
arXiv 2610.02486Pritam Deka代码 ↗
- 10点赞Receiver-Conditioned Latent Communication gives 94% CacheBack
arXiv 2609.32046Maximillian Rossi, Prajwal Raghunath, Haoqing Xuan 等 5 人代码 ↗项目主页 ↗
- 10点赞Octrees as an Explicit 3D Language
arXiv 2610.02388Ran Dan, Si-Tong Wei, Pengfei Xiong 等 6 人代码 ↗项目主页 ↗
- 9点赞KeyRec: Bounded Visual Memory for Streaming and Long-Video Understanding
arXiv 2609.32182Zihan Chen, Xuejian Rong, Xiaojuan Wang 等 7 人
- 9点赞EyeRobot 2.0: Active Gaze for Precise Manipulation without Wrist Cameras
arXiv 2610.03710Kush Hari, Justin Kerr, Nidhya Shivakumar 等 10 人项目主页 ↗
- 9点赞WM-VLM: Probing Internal World Models for Interleaved Visual-Textual Reasoning
arXiv 2609.34826Yuheng Zha, Yilei Wang, Qiyue Gao 等 8 人代码 ↗
- 8点赞Can Computation from Earlier Problems Help LLMs Solve New Ones?
arXiv 2609.39394Jipei He, Wenhui Tan, Xiaoyi Yu 等 7 人
- 8点赞Dream4ACT: A Shared Visual Action Interface for Multi-Embodiment Video-Action Modeling
arXiv 2609.40153Xiangyu Zhu, Jin Xu, Yue Guo 等 9 人项目主页 ↗
- 7点赞Improving Atomic-Fact Recall via Focused Views in Unstructured Knowledge Editing
arXiv 2610.02772Ding Wu, Ye Zhang, Haoyu Wang 等 4 人
- 7点赞Self-Supervised Scaling of Terminal Environments for Scientific Domains
arXiv 2610.02710Zhongzhi Li, Yucheng Shi, Zongxia Li 等 11 人
- 6点赞Strike a Chord! Modal Kinetic Typography
arXiv 2609.38325Maham Tanveer, Jiyeon Han, Nanxuan Zhao 等 4 人项目主页 ↗
- 6点赞The Extender: A Log-Structured Transformer
arXiv 2609.32759Jakob Eriksson
- 2点赞JEPA-TTT: Persistent Test-Time Training of Latent World Models for Planning under Dynamics Shifts
arXiv 2610.00722Zheyuan Zhang, Suyu Ye, Nakul Agarwal 等 8 人项目主页 ↗
- 1点赞CUAWright: A Minimal Unified Interface for Digital Agents
arXiv 2610.04116Yadong Lu, Theodore Lee, Yifei Li 等 8 人代码 ↗
10 月 2 日31 篇
- 222点赞OneStreamer: Unifying Perception, Memory, and Proactive Response in Streaming Video Interaction
arXiv 2610.01762Xiangyu Zeng, Yuandong Yang, Zhiqiu Zhang 等 24 人代码 ↗项目主页 ↗
- 183点赞On-Policy or Off-Policy Learning? A Systematic Study of Distillation Dynamics
arXiv 2609.35259Julianna Piskorz, Antonin Berthon, Mihaela van der Schaar
- 73点赞Transformers Stop Thinking Too Early, and a Tiny LoRA Fixes It
arXiv 2609.36585Zehao Jin, Ruixuan Deng, Junran Wang代码 ↗项目主页 ↗
- 69点赞X-Tree: Tokenizing Reusable Experience for Efficient Agent Generalization
arXiv 2609.32993Sitao Cheng, Xunjian Yin, Zhiyuan Sun 等 7 人代码 ↗项目主页 ↗
- 61点赞E-MoE: Enhanced Mixture-of-Experts for Non-Factorized Diffusion Language Models
arXiv 2609.37533Arseny Ivanov, Alexander Kolesov, Alexander Korotin 等 5 人
- 56点赞Video Generation Models: A Survey of Post-Training and Alignment
arXiv 2610.00812Chaoyu Li, Xiaoyi Gu, Yogesh Kulkarni 等 13 人代码 ↗
- 51点赞Persona Dosing: Calibrated Activation Steering for Graded Trait Control
arXiv 2609.36388Zehao Jin, Junran Wang, Ruixuan Deng 等 7 人
- 46点赞Fewer Tokens, Better Action: GPT-6 Astra Robot Agents with 14% Higher Success Rate but 65% Fewer Tokens
arXiv 2610.01939Ruiyang Si, Jianxin Bi, Shunyu Yang 等 12 人代码 ↗项目主页 ↗
- 45点赞Architect-Ant: Editable Automatic Furnishing of Architectural Floor Plans
arXiv 2606.10953Fedor Rodionov, Aleksandar Cvejic, Michael Birsak 等 5 人项目主页 ↗
- 43点赞Decoding Looped Transformers Better for (Almost) Free
arXiv 2610.02185Weihao Liu, Huangjie Zheng, Tianrong Chen 等 8 人
- 33点赞CorrGRPO: Correlation-Normalized GRPO for Multi-Reward Learning
arXiv 2609.36820Wenbin Hu, Huihao Jing, Haochen Shi 等 6 人代码 ↗项目主页 ↗
- 27点赞Ego2Act: Evaluating Goal-Directed Manipulation in Egocentric Video Generation
arXiv 2610.01092Patrick Amadeus Irawan, Iskandar Muda Rizky Parlambang, Rava Maulana 等 13 人代码 ↗项目主页 ↗
- 23点赞PhysVista: Benchmarking Physical Intelligence in VLMs via a Perception-Reasoning-Assessment Loop
arXiv 2610.00559Xinge Peng, Yiting Lu, Tianwu Zhi 等 7 人代码 ↗
- 17点赞Where-OPD: Spatially Guided On-Policy Self-Distillation of MLLMs with Synthetic Scenes
arXiv 2610.02117Sophia Sirko-Galouchenko, Monika Wysoczanska, Andrei Bursuc 等 5 人
- 14点赞OpenTumorBoard: A Real-World Benchmark of Multidisciplinary Tumor Board Discussion Trajectories
arXiv 2609.32810Anqi Li, Zhixuan Ge, Yixuan Duan 等 12 人代码 ↗项目主页 ↗
- 13点赞Removing the NEEDLE in the Haystack: Backdoor Removal in LLMs via Weight Orthogonalisation
arXiv 2610.00348Minoo Kim, Vasileios Lampos, George Drayson代码 ↗
- 12点赞ScholarCatalyst: A Benchmark for Retrieving Papers That Inspire New Research
arXiv 2610.02202Sohyeon Kim, Yoonho Lee, Bo Liu 等 14 人
- 12点赞RLE-Bench: A Qualifying Exam for Coding Agents as Robot Learning Engineers
arXiv 2609.34210Haitong Ma, Chenxiao Gao, Rushi Qiang 等 5 人代码 ↗项目主页 ↗
- 11点赞LOCI: Spatial Linear Memory for Streaming World Models
arXiv 2609.40222Ji Xia, Tingting Liao, Xuezhi Liang 等 5 人代码 ↗项目主页 ↗
- 11点赞SemanTok: Predictable Semantic Tokens for Efficient Autoregressive Video Generation
arXiv 2610.00686Mikhail Dereviannykh, Vikram Voleti, Simon Donne 等 6 人代码 ↗项目主页 ↗
- 11点赞Generalization Is Stability, Not Accuracy: Multi-Axis Evaluation of LLMs
arXiv 2610.01428Nagham Omar, Mahmoud Jabarin, Maya Rozenshtein 等 6 人
- 11点赞VTR-Bench: A Systematic Benchmark for Evaluating Visual Text Rendering in Video Generation
arXiv 2610.01499Yu Huang, Jungang Li, Zhiyuan Wang 等 11 人代码 ↗
- 8点赞Latent-Foresight: End-to-End Learning Predictable Representations for Latent World Models
arXiv 2610.01942Efstathios Karypidis, Spyros Gidaris, Nikos Komodakis代码 ↗
- 7点赞MemFold: Learning Compact Soft Memory for Long-Context Personalization via On-Policy Optimization
arXiv 2609.36435Jingxuan Wu, Yuzhe Yang, Yiqiao Huang 等 9 人代码 ↗项目主页 ↗
- 7点赞OTRetarget: Joint Robot and Object Motion Retargeting via Optimal Transport
arXiv 2609.36602Guillaume Besset, Erwann Carn, Timothée Carecchio 等 8 人项目主页 ↗
- 7点赞
- 6点赞When Does Correction Become Repair? Mechanistic Auditing of Internal Interventions in Tool-Using LLMs
arXiv 2609.36138Jiayi Li, Ruizhe Li代码 ↗
- 5点赞Keyword Harnesses Fail Open: A Cheap Diagnostic Ladder for Tool-Use Claims in Small Language Models
arXiv 2610.02142Juan S. Santillana项目主页 ↗
- 5点赞Honeycomb: Constant-Size Scene Memory Representation for Video World Models
arXiv 2609.37690Jack Wei Lun Shi, Kaichen Zhou, Haoyu Chen 等 9 人代码 ↗项目主页 ↗
- 5点赞Replacing Large Language Models with Jev Decision Models for Low-Latency Edge Service Orchestration
arXiv 2609.22753Delong Li, Xu Wang, Haochen Gong 等 5 人代码 ↗
- 5点赞Before It Fades: Reinforcing Temporal Representations at Inference Time in VideoLLMs
arXiv 2610.01595Youngwoo Shin, Yusung Ro, Minseo Kim 等 4 人代码 ↗
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。