Learning How the World Evolves: Extrapolative Video World Models via Latent Dynamics Reasoning

The world evolves following its dynamics, i.e., its laws of motion.

The world evolves following its dynamics, i.e., its laws of motion. However, leading video diffusion models largely fit the pixels without modeling how the pixels transit over time. Thus, they render visually plausible frames but may not accurately obey the laws. To capture the…