Practical AI · Thursday, October 1, 2026
Mingyu Liu distinguishes 'World Models' from language models, explaining they are built from sensory observations to implicitly encode physics and enable simulation. NVIDIA's Cosmos lab develops these models for tasks like world understanding and simulation, creating a shared representation for physical AI applications.
“And world model is from a different perspective. It is from the perspective of, you know, you have a sensory observation of the world. And you know those sensors are capturing different angles of the world. And those sensors, those cameras also capture the dynamics how physics evolve.”
“And people believe that's a, from modeling these signals, you can implicitly encode the physics of the world. And with the physics, kind of something you model, then you can start to do simulation.”
“In Cosmos, we believe that, you know, One is for world understanding, the other is for world simulation. Although they are for different purposes, but they model the same world.”