SOURCE-LINKED INTELLIGENCE

JEPA Policy: Diffusion-Free Imitation Learning via Paired Action and Future Representation Prediction

arXiv · AI, language, vision and robotics · article · Sep 9, 2026 · UTC

Standard behavior cloning supervises actions without explicitly constraining the future representation paired with each demonstrated action chunk. We introduce JEPA Policy, a diffusion-free framework that uses the action chunk and its observed future representation as paired training targets. Action and future-representation tokens interact in a shared Transformer and are refined through two forward passes. Future prediction can therefore shape the representation used to generate actions. Dual-branch and gradient-routing controls attribute the gain to this shared topology rather than to an aux

Read original source ↗ Open in workspace

recordType

paper

region

Global