HuggingFace Papers

• HuggingFace Papers Today Week Month
• 共 30 条
• 1 Bilevel Coordinated Reflection: A Game-Theoretic Approach to Multi-Agent LLM Systems

  2609.02750 ▲ 102
• 2 Iris: Climbing to the Search Frontier

  2609.04304 ▲ 51
• 3 Motion-Omni: End-to-End Joint Speech and Full-Body Motion for Spoken Dialogue

  2609.04250 ▲ 38
• 4 Dr. Claw: An AI Scientist Workspace for Vibe Research

  2609.00365 ▲ 30
• 5 The Attention Triangle in Audio-Video Models

  2609.03586 ▲ 25
• 6 WorldSculpt: Generating Compositional Worlds from Grounded Videos

  2609.05416 ▲ 21
• 7 Enoki: Efficient Multi-Level Hallucination Detection

  2609.00581 ▲ 17
• 8 Ask Before You Optimize: Dynamic Pre-Formulation Clarification for Interactive Optimization

  2609.05258 ▲ 15
• 9 Don't Drop Dropout: Optimizing Layer Sparsity for Efficient LLM Training and Inference

  2609.05275 ▲ 15
• 10 UniMate: One Unified Model to Animate Diverse Skeletons

  2609.05415 ▲ 13
• 11 Beneath the Surface of Chains-of-Thought: A Mechanistic Interpretation of Reasoning Operations in LLMs

  2609.04753 ▲ 10
• 12 MaxKernel: Agentic Kernel Generation for TPUs

  2609.04523 ▲ 10
• 13 RISE: Recursive Improvement via Self-Extrapolating Policy Distillation

  2609.05295 ▲ 9
• 14 One Editor, Many Edits: A Unified Training-Free Framework for Diverse Video Editing

  2609.04190 ▲ 6
• 15 τ^τ-Bench: An Environment for End-To-End, Realistic Agent Construction

  2609.04611 ▲ 5
• 16 When Models Edit Too Much: On the Fidelity of Minimal Code Edits

  2609.04061 ▲ 5
• 17 Group Adaptive Clipping Policy Optimization

  2609.00444 ▲ 5
• 18 AdaptVPR: Route-Aware Hard Positive Generation for Robust Visual Place Recognition

  2609.04369 ▲ 4
• 19 Verify Before You Distill: Prompt-Level Teacher Gating for On-Policy Distillation

  2609.02998 ▲ 4
• 20 Training-Free Speech-Centric Omni Understanding with Frozen VLMs

  2609.04242 ▲ 4
• 21 HarvestBench: Measuring Whether LLM Agents Will Pay to Avoid Killing Animals

  2609.04444 ▲ 3
• 22 When Quantization Breaks Memory: Recurrent-State Write-Back in Low-Precision Temporal Inference

  2609.04490 ▲ 3
• 23 ShallowStream: Index Shallow then Answer Deep for Streaming Video Understanding

  2609.02780 ▲ 3
• 24 To See a World in a Living Context: Unified Indoor-Outdoor Urban World Generation

  2608.05879 ▲ 3
• 25 Real-World Knowledge-Guided Change Data Synthesis for Remote Sensing

  2608.24263 ▲ 3
• 26 Knowing What Not to Answer: Selective Non-Compliance in Vision-Language Models

  2609.04720 ▲ 2
• 27 Refuse without Refusal: A Structural Analysis of Safety-Tuning Responses for Reducing False Refusals in Language Models

  2609.04714 ▲ 2
• 28 The 2026 PNPL Competition: Word Classification and Efficient Cross-Subject Generalisation in LibriBrain100

  2609.03231 ▲ 2
• 29 What Else Needs Fixing? Exploring Cost-Effective Test-Time Compute for Revision Propagation in Artifacts Generated Through Conversation

  2609.03254 ▲ 1
• 30 Unfold The World: Factorize 4D Properties in Reinforcing Spatial Reasoning

  2609.03729 ▲ 1