InertialWorld: A video world model with inertia as a prior
Inertial Video World Models
Researchers propose InertialWorld, which treats inertia as a structural prior for autoregressive video prediction, letting existing scene evidence carry over time instead of being rebuilt at every step. Its core Inertial Memory maintains both a dense Eulerian grid and persistent Lagrangian carriers, transports carrier content according to action-conditioned motion, and then fuses old and new content with a learned gate. In experiments on robotic manipulation, 3D game simulation, and open-world navigation, the model's autoregressive prediction performs comparably to strong video world model baselines, and the code is open-sourced on GitHub.
The paper treats inertia as a structural prior for autoregressive video world models, letting readers see how its memory mechanism reduces error accumulation in long-sequence prediction.
Source: arXiv Game World Models & Generation · arxiv.org