world2vec learns mechanistic world models from observations and actions
Latent dynamics use at least ten times fewer parameters than DreamerV3, TD-MPC2 and LeWM, without reward.
3 stories, newest first · one card per story
Latent dynamics use at least ten times fewer parameters than DreamerV3, TD-MPC2 and LeWM, without reward.
Latent rollout consistency checks whether action-conditioned latent prediction matches the environment transition map.
SG-JEPA world model conditions latent prediction on physical parameters, halving open-loop prediction error versus DINO-WM and boosting robotic control success.
Today 1.5K readers · 2.4K views · 754 reads · all time 189K views