A pretty cool paper that explains what a world model’s latent space should look like if it is used for planning.
Planning here means the agent is given a goal image, imagines in latent space where different action sequences would take it, and picks the one that gets closest to
Can a JEPA learn a latent map of the world?
We released a new paper with @yingwww_ @choang333 @KuangYilun @ylecun 🧵




