Sign up to save your podcasts
Or
Share LeWorldModel: A Stable JEPA World Model from Pixels
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
LeWorldModel: A Stable JEPA World Model from Pixels
Stable end-to-end JEPA world model trained directly from pixels using simple MSE prediction loss and SIGReg anti-collapse regularization, enabling efficient latent planning under 1 second on 15M params with emergent spatial structure outperforming prior methods.
View all episodes
By Shaoqing TanStable end-to-end JEPA world model trained directly from pixels using simple MSE prediction loss and SIGReg anti-collapse regularization, enabling efficient latent planning under 1 second on 15M params with emergent spatial structure outperforming prior methods.