SOURCE-LINKED INTELLIGENCE

Toward Physically Grounded JEPA World Models for Goal-Conditioned Robotic Planning

arXiv · AI, language, vision and robotics · article · Sep 3, 2026 · UTC

Action-conditioned JEPA world models enable planning toward visually specified goals without reconstructing future pixels, yet latent prediction alone does not explicitly encourage the learned representations to retain information relevant to robotic control. We introduce an end-to-end JEPA world model that augments latent prediction with inverse dynamics (IDM) and state alignment (SA). While inverse dynamics discourages latent collapse and makes latent transitions informative of the actions that produced them, state alignment grounds consecutive representations in their associated physical co

Read original source ↗ Open in workspace

recordType

paper

region

Global