Physis-Lang treats natural language as a shared, optimizable representation for physical knowledge across data curation, training, and inference. It uses an agentic loop to refine physical captions and language-guided retrieval to expand training data. On four benchmarks with Wan and Cosmos backbones, it consistently improves physical plausibility, with the enhanced Cosmos3-Nano model surpassing the proprietary Veo 3.1 model.
Evolving physics captions improve video models’ physical plausibility
Physis-Lang iteratively refines physical descriptions, retrieves training videos that address model weaknesses, and improves Wan and Cosmos generators across four benchmarks.
Big Tech
Liming Lu · Xianzheng Ma · Wenkun He · Guanqi Zhan · Yilin Zhao · Junyu Chen · +11 more
NVIDIA · University of Oxford · MIT
Research Digest··3 min read
In one line
Using a self-evolving language framework improves video world model physical plausibility without extra visual signals.
Before you read this
Three ideas this paper builds onworld model for agentsA predictive environment model that agents use to simulate outcomes, enabling planning, reasoning, and long-horizon task execution.119 papers →self-evolving agentAn agent that improves by reusing its own experience, memory, or self-generated feedback, with success depending on verification and design.97 papers →agentic video generationMulti-agent systems collaborate autonomously to produce long-form videos maintaining narrative and visual coherence.21 papers →
Read it as
Lu and colleagues test whether explicit natural-language descriptions can carry enough physical knowledge to improve video world models without requiring a separate numerical or latent representation.
The authors represent each physical process with captions covering relevant entities, causes, interactions, governing principles, temporal progression and effects.
How it works
before and afterThe Daily Edition
The front page in your inbox each weekday morning: the lead, the picks, and why each one earned its place.