Paper Pulse

The day-by-day history of every Hugging Face Daily Papers entry since March 2024: upvotes over time, where each paper ranked on its day, and the labs and authors behind the top papers.

Daily Papers of 2026-10-02

  1. On-Policy or Off-Policy Learning? A Systematic Study of Distillation Dynamics 175 upvotes, #1 of 2026-10-02
  2. OneStreamer: Unifying Perception, Memory, and Proactive Response in Streaming Video Interaction 165 upvotes, #2 of 2026-10-02
  3. GraphForge: Training Working Agents with Graph-Anchored Workspace Synthesis 144 upvotes, #3 of 2026-10-02
  4. Adaptive Reward Routing: Dynamic Multi-Reward Optimization for Joint Audio-Video Diffusion via Forward-Process RL 124 upvotes, #4 of 2026-10-02
  5. Predictive Credit: Measuring What Scientific Explanations Add to Experimental Forecasts 90 upvotes, #5 of 2026-10-02
  6. Sharpening Tax in Post-Training 83 upvotes, #6 of 2026-10-02
  7. Beyond Memory: Harnessing Long-Horizon Agents with Explicit Belief States 82 upvotes, #7 of 2026-10-02
  8. Hierarchical Continuous Diffusion Language Models 79 upvotes, #8 of 2026-10-02
  9. Agent Priors-guided Policy Learning 76 upvotes, #9 of 2026-10-02
  10. World Observer: Joint Actor-Observer Generation for Persistent World Modeling 74 upvotes, #10 of 2026-10-02
  11. A Missing Piece for Trustworthy AI Reviewers: From Benchmarking Rhetorical Robustness to SciCore Review 71 upvotes, #11 of 2026-10-02
  12. Transformers Stop Thinking Too Early, and a Tiny LoRA Fixes It 69 upvotes, #12 of 2026-10-02
  13. Prefill-Free Cross-Family KV Cache Transfer for Heterogeneous Multi-Agent LLMs 64 upvotes, #13 of 2026-10-02
  14. ActiveSaddler: Automated Curriculum Learning for Agent Harness Optimization 64 upvotes, #13 of 2026-10-02
  15. ROWBench: Do Video Models Render What the Program Specifies? 64 upvotes, #13 of 2026-10-02
  16. E-MoE: Enhanced Mixture-of-Experts for Non-Factorized Diffusion Language Models 60 upvotes, #16 of 2026-10-02
  17. X-Tree: Tokenizing Reusable Experience for Efficient Agent Generalization 59 upvotes, #17 of 2026-10-02
  18. EgoTools: Towards Tool-Centric Reasoning in Real-World Egocentric Videos 57 upvotes, #18 of 2026-10-02
  19. Make Sparse Rewards Count: Density-Aware Reward Aggregation for Multi-Reward RL 57 upvotes, #18 of 2026-10-02
  20. Retrieval-Augmented Skill Optimization via Cross-Harness Adaptation 56 upvotes, #20 of 2026-10-02
  21. Video Generation Models: A Survey of Post-Training and Alignment 55 upvotes, #21 of 2026-10-02
  22. InterEvolve: Test-Time Evolution of Reward Programs for Humanoid Loco-Manipulation 55 upvotes, #21 of 2026-10-02
  23. AutoGUIWorld: Image Generators as Visual World Models for GUI Agent 54 upvotes, #23 of 2026-10-02
  24. Decentralized Master-Mind: Joint Action Refinement through Iterative Intent Denoising in Multi-Agent Pathfinding 51 upvotes, #24 of 2026-10-02
  25. Scaling and Distilling Text Embeddings for Better Diffusibility 50 upvotes, #25 of 2026-10-02
  26. Persona Dosing: Calibrated Activation Steering for Graded Trait Control 48 upvotes, #26 of 2026-10-02
  27. Beyond the Current Scene: Event-Referential Grasping with Active View Selection 46 upvotes, #27 of 2026-10-02
  28. Fewer Tokens, Better Action: GPT-6 Astra Robot Agents with 14% Higher Success Rate but 65% Fewer Tokens 45 upvotes, #28 of 2026-10-02
  29. Architect-Ant: Editable Automatic Furnishing of Architectural Floor Plans 41 upvotes, #29 of 2026-10-02
  30. Decoding Looped Transformers Better for (Almost) Free 41 upvotes, #29 of 2026-10-02

Labs with the most top-3 papers

  1. NVIDIA 23 top-3 papers
  2. ByteDance Seed 21 top-3 papers
  3. Tencent 16 top-3 papers
  4. ByteDance 16 top-3 papers
  5. Tencent Hunyuan 13 top-3 papers
  6. Peking University 13 top-3 papers
  7. Qwen 12 top-3 papers
  8. AMAP-ML 12 top-3 papers
  9. Shanghai Jiao Tong University 11 top-3 papers
  10. AGI Lab 11 top-3 papers
  11. OpenMOSS 9 top-3 papers
  12. National University of Singapore 8 top-3 papers
  13. KAIST AI 8 top-3 papers
  14. Microsoft Research 8 top-3 papers
  15. inclusionAI 8 top-3 papers
  16. Google 7 top-3 papers
  17. AI at Meta 7 top-3 papers
  18. StepFun 7 top-3 papers
  19. TongyiLab 7 top-3 papers
  20. OpenDataLab 6 top-3 papers

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.