Researchers propose InertialWorld, an inertia-prior video world model
What happened
Researchers led by Yuan Gao propose InertialWorld, a video world model that treats inertia as a structural prior for autoregressive video prediction: existing scene evidence is carried forward over time instead of being rebuilt at every step. Its core component, Inertial Memory, maintains both a dense Eulerian grid and persistent Lagrangian carriers, moves carrier content according to action conditions, 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 predictions are comparable to strong video world model baselines, and the code is open-sourced on GitHub.
AI-written from the coverage · updated 4 d ago
Coverage timeline
Follow the coverage to see the story from different sides.
- arXiv Game World Models & GenerationPickInertialWorld: A video world model with inertia as a prior
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.
Heat trend for this story
- Current (comparable)
- 3
- Peak (comparable)
- 6Nov 18 12:00
- 24-hour change
- -50%
The trend only compares participants observed continuously and completely, so it may cover fewer than the current heat count. Hover over or tap the chart to see each hour's heat; with a keyboard, use the left and right arrow keys.