Meta Research

Meta Research on Hugging Face Daily Papers: 28 papers, 2 in the top 3 of their day, 1 paper of the day.

  1. HumanCLAW: Can Vision-Language Models Act Through a Body? 76 upvotes, #4 of 2026-07-30
  2. Self-Guided Test-Time Training for Long-Context LLMs 19 upvotes, #7 of 2026-07-13
  3. Remember When It Matters: Proactive Memory Agent for Long-Horizon Agents 14 upvotes, #12 of 2026-07-10
  4. SWE-Together: Evaluating Coding Agents in Interactive User Sessions 14 upvotes, #19 of 2026-06-30
  5. Distilling LLM Feedback for Lean Theorem Proving 3 upvotes, #29 of 2026-06-11
  6. OmniOPD: Logit-Free On-Policy Distillation via Speculative Verification 8 upvotes, #26 of 2026-06-03
  7. WavFlow: Audio Generation in Waveform Space 10 upvotes, #25 of 2026-05-19
  8. ReMix: Reinforcement routing for mixtures of LoRAs in LLM finetuning 25 upvotes, #7 of 2026-03-12
  9. Towards a Neural Debugger for Python 5 upvotes, #15 of 2026-03-11
  10. APRES: An Agentic Paper Revision and Evaluation System 2 upvotes, #29 of 2026-03-04
  11. Gaia2: Benchmarking LLM Agents on Dynamic and Asynchronous Environments 12 upvotes, #19 of 2026-02-13
  12. Likelihood-Based Reward Designs for General LLM Reasoning 8 upvotes, #31 of 2026-02-05
  13. Scaling Small Agents Through Strategy Auctions 5 upvotes, #31 of 2026-02-04
  14. Self-Improving Pretraining: using post-trained models to pretrain better models 15 upvotes, #18 of 2026-01-30
  15. Paying Less Generalization Tax: A Cross-Domain Generalization Study of RL Training for LLM Agents 9 upvotes, #16 of 2026-01-27
  16. Agentic Very Long Video Understanding 17 upvotes, #12 of 2026-01-27
  17. Action100M: A Large-scale Video Action Dataset 26 upvotes, #15 of 2026-01-16
  18. KernelEvolve: Scaling Agentic Kernel Coding for Heterogeneous AI Accelerators at Meta 3 upvotes, #28 of 2025-12-30
  19. Exploring MLLM-Diffusion Information Transfer with MetaCanvas 12 upvotes, #7 of 2025-12-15
  20. Confucius Code Agent: An Open-sourced AI Software Engineer at Industrial Scale 5 upvotes, #16 of 2025-12-12
  21. AI & Human Co-Improvement for Safer Co-Superintelligence 8 upvotes, #15 of 2025-12-08
  22. Self-Improving VLM Judges Without Human Annotations 18 upvotes, #9 of 2025-12-08
  23. Don't Waste It: Guiding Generative Recommenders with Structured Human Priors via Multi-head Decoding 5 upvotes, #12 of 2025-11-17
  24. Scaling Agent Learning via Experience Synthesis 72 upvotes, #3 of 2025-11-07
  25. Embody 3D: A Large-scale Multimodal Motion and Behavior Dataset 6 upvotes, #19 of 2025-10-21
  26. Haystack Engineering: Context Engineering for Heterogeneous and Agentic Long-Context Evaluation 1 upvotes, #36 of 2025-10-16
  27. SPG: Sandwiched Policy Gradient for Masked Diffusion Language Models 14 upvotes, #22 of 2025-10-14
  28. Agent Learning via Early Experience 223 upvotes, #1 of 2025-10-10

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.