RESEARCH PAPER

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

Jie Xu; Kangjin Yu; Ziyi Jin; Junjie Gao; Liqing Chen; Yixian Li; Shuai Tian; Zhongpu Xia

Classification

View four quadrants
Major category
WAMs
Architecture
One Model
Prediction paradigm
Joint prediction
Source review status
Not assigned

Category review. One mutually visible Transformer predicts executable action chunks and future visual representations together; the paired prediction architecture is supported even though deployment uses no candidate search. A shared mutually visible Transformer predicts actions and future-latent tokens together. Reading evidence

AT A GLANCE

Contribution

JEPA Policy trains a shared Transformer to predict an action chunk and the visual representation observed later in the same demonstration. Two deterministic passes refine both outputs. Its strongest evidence is improved simulated control relative to action-only MIP, supported by topology controls; future error also offers a delayed, task-dependent rollout diagnostic.

Abstract

An abstract has not been added yet.

Affiliations

Anyverse Dynamics