# Physis-Lang

Physis-Lang treats physical language as a shared, optimizable representation across data curation, model training and video generation, using a physics-aware critic and PhysCapBench to drive an agentic loop that refines physical captioning instructions and language-guided retrieval to cover missing physical processes, yielding consistent gains on four physical video benchmarks with Wan and Cosmos backbones, where models built on the open-source Cosmos3-Nano surpass Veo 3.1 on Physics-IQ Verified, PhyGround and PhyGenBench.

Physis-Lang treats physical language as a shared, optimizable representation across data curation, model training and video generation, using a physics-aware critic and PhysCapBench to drive an agentic loop that refines physical captioning instructions and language-guided retrieval to cover missing physical processes, yielding consistent gains on four physical video benchmarks with Wan and Cosmos backbones, where models built on the open-source Cosmos3-Nano surpass Veo 3.1 on Physics-IQ Verified, PhyGround and PhyGenBench.