Hugging Face's Most Upvoted Papers This Week: World Models and Self-Improving Agents Lead
yshan2u · x · 2026-09-28
HuggingPapers rounded up the most upvoted papers on Hugging Face this week, spanning:
- OmniEdu: open foundation models for learning and teaching
- Realtime-Venus: full-duplex interaction with asynchronous delegation
- RRSI: regularized recursive self-improvement of agent harnesses
- Training Object Permanence in World Models
- WorldCrafter: consistent video world model with implicit 3D-aware memory
- EvoOntology: self-evolving ontology layer for data agents
- The Tasteful Agent: measuring and improving taste in long-horizon tasks
- OmniVChat: native audio-visual dialogue
- CodeMidas: scaling agentic coding RL environments from code itself
- GameHorizon Suite: multi-horizon data and evaluation in gameplay
World models, long-horizon agents, and agentic coding environments dominated community attention this week.
More from Research
- InternW0-Δ open-sources code, weights and 20K+ hours of robot data — arankomatsuzaki · 2026-09-28
- IMLE-VLA replaces flow matching with single-step cIMLE, 3.67x faster robot actions at 55Hz — petitegeek · 2026-09-28
- Red Queen Bio Uses AI and Wet Labs to Build Medicines Against Natural and Synthetic Viruses — _sholtodouglas · 2026-09-28
- Yacine demos general sim2real pipeline: policy trained in just two minutes — yacineMTB · 2026-09-28
- Claude Spots a Missing 1/2 Coefficient in a Physics Preprint — tak3sh8 · 2026-09-28
- Astra saw through perturbed Zork observations, calling it a 'variant' — tw_killian · 2026-09-28