CASIA's PhiZero learns 'physical language' to lead three generation benchmarks without natural language descriptions
jiqizhixin · x · 2026-08-25
The Institute of Automation, Chinese Academy of Sciences (CASIA) presents PhiZero, a world model that learns a "physical language" instead of relying on natural language descriptions of physics.
Core Innovation:
- It learns a compact symbolic system that directly represents fine-grained state changes in the real world.
- The model predicts state evolution in this learned language and decodes it into video or transfers state transitions across different embodiments.
Performance:
- Generation: Leads on Physics-IQ Verified, PhyGround, and WorldModelBench.
- Understanding: Posts competitive results on IntPhys2, LikePhys, and YoCausal.
- Zero-shot Transfer: Successfully transfers motion from humans to G1 humanoids, from human hands to dexterous grippers, and from simulation to reality without paired training data.
More from Embodied
- Vinci Hits 100k Physics Sims in 24 Hours on Single H200 Node — AnneliesGamble · 2026-08-25
- PhysCaP: Physics-Informed Agent for Robotic Manipulation — Chen-Yu Lin · 2026-08-25
- Netizen questions Figure Robotics' production claims — Darpinian · 2026-08-25
- Omarchy Linux to integrate local Qwen 27B for Agentic OS — moeinteractive · 2026-08-25
- Chinese Robots Play Soccer at World Humanoid Robot Games — ZeroStateReflex · 2026-08-25
- China Humanoid Robotics Tracker: A directory of the supply chain and funding — PAstynome · 2026-08-25