arXiv CS AI
techCenter
ARC-Bench: Closed-Loop Replanning Masks Broken Action Ranking in Frozen JEPA World Modelstranslating…
arXiv:2609.05461v1 Announce Type: new
Abstract: Reward-free latent world models plan by scoring candidate actions with distances in a frozen latent space: an action is preferred if its predicted future embedding lands closer to the goal embedding. This silently assumes that…
Keywords#Action#Frozen#Models#Action Ranking#ARC-Bench