DAGroup-PKU (Yuxuan Chen et al.) · Physics-aware self-improvement
PhysLoop
PhysLoop is a harness that uses LLMs' physical knowledge to guide video generation, selection and correction, so that video models can be trained on more physically consistent self-generated data. The authors release 100K videos of indoor and outdoor scenes, generation tools, and two evaluation datasets, PhysLoop-Gen and PhysLoop-Repair. They assess controllable generation and localised repair on these datasets and physical behaviour on the external Physics-IQ Verified benchmark.
Open the source ↗Similar Research & Safety releases
- TOME-Math: Scaling Mathematical Proof Supervision from Structured Textbooks
Intern Large Models (Youqing Fang et al.) · Math Proof Dataset · Week 47, 2026
- AlphaGenome Atlas
Google DeepMind · AlphaGenome Atlas · Week 37, 2026
- Male Fruit Fly Connectome
Google Research and HHMI Janelia · Fly Brain Connectome · Week 36, 2026
- Memorilla
Stanford SNAP group (Jure Leskovec), with co-authors from Toronto, Penn and MIT · Latent Memory Module · Week 47, 2026
- NovaAtom-Lite
Geodesic Intelligence · All-atom structure prediction · Week 47, 2026
- Actor, Judge, or Teacher? Understanding Decision Models in Long-Horizon Agents
Haochen Liu, Qianhao Zhu, Zixuan Wang, Dingming Li, Tongbo Chen, Peng Qiu, Yingqi Qu, Weiming Lu (Zhejiang University) · Decision Model Teachers · Week 47, 2026
Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.