There is significant and exciting work on world models and video-based training in AI research
There's similar work at DeepMind also taking place, and also at UC Berkeley on world models and video. A lot of people are working on this. I think a lot of good ideas are appearing.
Named things
Danijar Hafner · person · mentions
Pieter Abbeel · person · mentions
Sergey Levine · person · mentions
FAIR · service · mentions