World model
A world model learns or encodes environment dynamics so a system can predict, simulate, or plan before acting.
Why it matters
It turns perception into a substrate for counterfactual prediction and planning.
Relationships
informsVision-Language Model → World modelpredicts forWorld model → Plannerfeeds back toDigital twin → World modelcontainsWorld model → Latent stateinformsUncertainty → World modelinformsInteractive control → World modelinformsSelf-supervised pretraining → World model
Related models
WML · World Model Laboratory
Explore the connection between perception, prediction, planning, and action studied in WFM through experiments in WML. Compare predictions with simulated outcomes in interactive physics scenes, then explore a different action from the same decision point.
Educational simulation: WML uses simplified predictors; it does not validate the performance of learned foundation world models or transfer to the real world.
Open the experiment in WML