HuggingFace Papers

• HuggingFace Papers Today Week Month
• 共 105 条
• 1 Spectral-Spatial Interpretation

  2610.21114 ▲ 759
• 2 OmniCompass: A Holistic Benchmark for Omni-Modal Video Grounding and Understanding

  2610.18829 ▲ 751
• 3 StreamEval: Evaluating Interactive Streaming Video Generation Models

  2610.28402 ▲ 658
• 4 BizBench: Unveiling Hidden Challenges in Deploying Long-Horizon Agents for Real-World Business

  2610.20424 ▲ 497
• 5 LoopVL: Recurrent Visual Intelligence

  2609.38426 ▲ 420
• 6 ChronoReplay: One Answer Interface Is Not Enough for Streaming Spatial Intelligence

  2610.34283 ▲ 399
• 7 The Trinity:Capability-Driven Recursive Self-Improvement for Multimodal Agents

  2610.36077 ▲ 384
• 8 Multiscale Policy Optimization for Long-Horizon LLM Agents

  2610.35013 ▲ 379
• 9 Jeva: System One Models from First Principles

  2610.18773 ▲ 375
• 10 Trajectory2Gym: Decision-Grounded Compositional Interaction Synthesis for Tool-Use Agents

  2610.33568 ▲ 367
• 11 Has GPT-6-Astra Achieved Embodied Intelligence?

  2610.22471 ▲ 327
• 12 Trial by Trace: Benchmarking AI Agent Harnesses for Reliability and Failure Attribution

  2610.32285 ▲ 299
• 13 RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations

  2610.01780 ▲ 297
• 14 Reading, Writing, Sharing, and Interacting with the World through Video

  2610.31668 ▲ 295
• 15 S-Space: Exploring Spatial Workspace in Multimodal Language Models

  2610.13527 ▲ 272
• 16 MJev-Spatial: System One Spatial Intelligence via Native Attention Matching

  2610.22276 ▲ 263
• 17 WeVisOne-VL: Unified Visual Perception from Objects to Pixels

  2610.31329 ▲ 258
• 18 Player-1: Learning to Play from Synthetic Experience

  2610.20584 ▲ 257
• 19 VideoJev: System One Model for Video Understanding and Interaction

  2610.18615 ▲ 240
• 20 Any Time, Any Space: A World-State-Centric Framework for Agentic Video Generation

  2610.20571 ▲ 238
• 21 False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents

  2609.39102 ▲ 234
• 22 Focused Omni-Modal GUI Agents

  2610.26203 ▲ 230
• 23 Rethinking Latent Visual Reasoning: Grounding Latent Reasoning in Visual Evidence

  2609.34563 ▲ 226
• 24 Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation

  2610.21601 ▲ 224
• 25 DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Models

  2610.12572 ▲ 215
• 26 OR-License: Evaluating LLM Agents as Real-World Operations Research Practitioners

  2610.24087 ▲ 209
• 27 On-Policy or Off-Policy Learning? A Systematic Study of Distillation Dynamics

  2609.35259 ▲ 205
• 28 UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement

  2609.38721 ▲ 202
• 29 Matrix-Game 4.0: Harnessing Video Models for Real-Time Playable Game Worlds

  2610.27999 ▲ 197
• 30 Right Screen, Wrong Transition: World Models as Verifiers for GUI Agents

  2610.11942 ▲ 189
• 31 EgoXperience: Learning World-Grounded Egocentric Representations from Human Experience

  2610.26625 ▲ 189
• 32 Thinking Inertia: LLMs Keep Thinking When Told Not To

  2610.11765 ▲ 189
• 33 Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight

  2610.08077 ▲ 189
• 34 Deep Search in Real-World Web Environments

  2610.30181 ▲ 187
• 35 The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation

  2609.36484 ▲ 185
• 36 AgentGarten: Code Worlds for Evolving Agents

  2610.12374 ▲ 180
• 37 Kandinsky 6.0 Video: Foundation Models for Synchronized Video and Audio Generation

  2610.05608 ▲ 176
• 38 Holi-World: Building Holistic World Intelligence from Human-Ego Experience

  2610.26549 ▲ 172
• 39 StreamVibe: Proactive Video Agents for Evolving User Intent

  2610.34662 ▲ 171
• 40 PAR: Progress-Aligned Recurrence for Length Generalization in State Tracking

  2610.27628 ▲ 168
• 41 DONIC: Generalist Dexterous Bimanual Tracking Control from Human Demonstrations

  2610.29997 ▲ 162
• 42 Cache Engineering for Agents

  2610.28577 ▲ 161
• 43 Looking Ahead: Modeling Future Evolution in Autoregressive Video Generation

  2610.29989 ▲ 159
• 44 Into the Unknown: Benchmarking AI agents on open scientific research problems

  2610.19159 ▲ 159
• 45 MAI-Gym: An Open All-in-One Platform for GUI Agent Evaluation and RL Training across Mobile and Computer Environments

  2610.20939 ▲ 157
• 46 STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization

  2609.38169 ▲ 156
• 47 SpatialScout: Can VLM Agents Actively Explore and Map 3D Scenes?

  2610.26659 ▲ 155
• 48 OneStreamer: Unifying Perception, Memory, and Proactive Response in Streaming Video Interaction

  2610.01762 ▲ 154
• 49 Ropedia W0: Scaling Loco-Manipulation World Models across Embodiments with Human Experience

  2610.26855 ▲ 151
• 50 Memory Tax: Dissecting the Net Value of Agent Memory

  2610.34073 ▲ 149
• 51 GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives

  2609.39601 ▲ 148
• 52 Scaling Agentic Data for Long-Horizon Terminal Intelligence

  2610.13166 ▲ 148
• 53 Efficient Streaming Audio-Visual Target Speaker Extraction for Real-World Acoustic Scenes

  2610.32749 ▲ 147
• 54 MemT-1.0: Towards Memory-Native Evolution

  2610.26825 ▲ 146
• 55 TokenRouter: Efficient Serving System for Token-Level LLM Routing

  2610.12242 ▲ 144
• 56 PDRVLA: A Vision-Language-Action Model with Physical Dynamics Representations

  2610.37381 ▲ 143
• 57 DynaFlow: Learning Free-Form Multi-Agent Orchestration

  2610.34467 ▲ 142
• 58 Function-Space Temporal Self-Distillation for Policy Optimization

  2610.19687 ▲ 140
• 59 Scaling Parameter-Efficient Fine-Tuning for Brain Encoding

  2610.26802 ▲ 140
• 60 Learning from Fleet Experience: A Collective Learning Paradigm for Robots

  2610.25736 ▲ 138
• 61 Urbex: Agentic Spatial Grounding for City-Scale 3D Scenes

  2610.18356 ▲ 135
• 62 Making MLLM Latents Matter: Factor-Aware Predictive Learning for Cinematic Video Generation

  2610.30926 ▲ 132
• 63 Agent-Reflex: Teaching Language Agents to Act Reflectively

  2610.17953 ▲ 127
• 64 InteractiveWorld: A Verifiable Human-Centric Environment for Building Better Interactive MLLM Assistants

  2610.33966 ▲ 126
• 65 Pack Light, CarryOn: Building Object-Oriented Context for Long-Horizon Agents

  2610.18784 ▲ 125
• 66 Harness^2: Recursive Agent Harnessing for an Open World

  2610.14224 ▲ 125
• 67 HexaShell: A Thin Harness for Exploring the Limits of VLM Agents as Robot Coding Agents

  2610.23479 ▲ 124
• 68 FrameMorrow: Future-guided Frame Selection with Prospective Tokens for Long-Horizon Video Generation

  2609.38839 ▲ 124
• 69 OpenVLHarness: Real World Visual Agentic Tool-Use with Multimodal Memory

  2610.26860 ▲ 121
• 70 Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents

  2609.39982 ▲ 120
• 71 Hy-Nomas: Towards Free-form Interactive World Generation

  2610.36729 ▲ 118
• 72 Work Agents: Systems, Capabilities, and Optimization

  2610.35845 ▲ 118
• 73 nanoMuse: An Open-Source Personal Agent for Every Device You Own

  2610.08699 ▲ 118
• 74 AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks

  2609.38288 ▲ 117
• 75 Learning to Think and Explore in 3D World

  2610.21783 ▲ 116
• 76 Editing Images into Reusable Layers via Compositional Edit-Prior Distillation

  2610.24738 ▲ 114
• 77 UltraText Bench: A Comprehensive Bilingual Benchmark for Evaluating Visual Text Rendering in Image Generation

  2610.09823 ▲ 113
• 78 Can Test-Time Memory Evolution Outperform Test-Time Training for Scientific Discovery?

  2610.32046 ▲ 112
• 79 EvoDuet: Bilevel Co-Evolution of Web Searching and Task Solving for Scientific Discovery

  2609.40340 ▲ 112
• 80 Sharpening Tax in Post-Training

  2610.01509 ▲ 111
• 81 Long-WAM: Scaling the Context of World-Action Models

  2610.10528 ▲ 110
• 82 Rethinking Cross-Tokenizer On-Policy Distillation: From Alignment Coverage to Supervision Reliability

  2610.08448 ▲ 110
• 83 S-Agent 2.0: Spatial Reasoning with a General Coding Agent

  2610.28354 ▲ 109
• 84 MOSS-Image Technical Report

  2610.23374 ▲ 107
• 85 OpenGCUA: Toward a Fully Open Stack for Generalist Computer Use

  2610.22200 ▲ 106
• 86 LEV: Thinking Fast and Deep with Looped Decision Models

  2610.20951 ▲ 105
• 87 SALD: Self-Referenced Advantage Learning for Diffusion Models

  2610.01496 ▲ 104
• 88 Predictive Credit: Measuring What Scientific Explanations Add to Experimental Forecasts

  2610.00314 ▲ 104
• 89 IQuest-Q1: Advancing Foundation Capabilities for Agentic CLI Systems

  2610.30949 ▲ 103
• 90 GreenWAM: A World Foundation Model for Robotics

  2610.18774 ▲ 103
• 91 Prefill-Free Cross-Family KV Cache Transfer for Heterogeneous Multi-Agent LLMs

  2609.32259 ▲ 103
• 92 DuoMatching: Joint-Marginal Distribution Matching for Few-Step Video Generation

  2610.03543 ▲ 102
• 93 Agent World Model in the Wild: Computer-Use Agent Environment Synthesis

  2610.26828 ▲ 101
• 94 Self-Evolving Agent Harness

  2610.18813 ▲ 101
• 95 SoftwareGym: Scaling Computer-Use Agent Training with Diverse Synthesized Software Environments

  2610.12611 ▲ 101
• 96 Reflex: Visually Grounded Reactive Humanoid Control

  2610.12772 ▲ 99
• 97 Speculative Forcing for Efficient Autoregressive Video Generation

  2610.22347 ▲ 97
• 98 World Action Modeling with Progressive Visual Planning

  2610.02508 ▲ 96
• 99 Recursive Game Creator: An Agentic Product-Level Experience-Oriented Game Harness

  2610.08621 ▲ 95
• 100 Beyond Domain-Routed Supervision: Cross-Teacher Guarding for Multi-Teacher On-Policy Distillation

  2610.13521 ▲ 94
• 101 TPPO: Tracking-Value PPO For Language Model Reasoning

  2610.16794 ▲ 94
• 102 WorldAuditBench: Interactive 3D World Auditing with Multimodal Agents

  2609.40325 ▲ 94
• 103 Hierarchical Continuous Diffusion Language Models

  2610.02193 ▲ 93
• 104 CoEvo-RSI: When Harnesses Evolve, Which Models Should Follow?

  2610.25078 ▲ 92
• 105 AgentSWE: Can Coding Agents Build the Agent You Actually Want?

  2610.13361 ▲ 92