A model uses videos to learn how actions change the world.
Picture a robot eyeing a full cereal bowl. It plays the mess movie first: spoon, wobble, milk on socks.
It helps robots train and plan moves. The AI can guess what its actions will do.
World model
An Embodied Video Model is a video-based branch of a World model.
Embodied AI
It helps Embodied AI predict what real actions will cause.
VLA
A VLA can use it to preview a move before it acts.