Startup NetworxMountain West
DirectoryPeoplePatentsClinical TrialsRFPs & GrantsAnalysisSignal
Sign In
Startup Networx

A commons for deep tech in the Mountain West. Built and maintained by the community it serves. Open data, CC-BY.

© 2026 Startup Networx
Discover
DirectoryOpen RFPsEvents
Community
NewsResourcesDashboard
Contribute
Add an orgSuggest an editClaim an org
About
Embed widgetsModerationPrivacySign in
← News
News

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

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

robotics
Read on arxiv.orgvia RSS

From the feed

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 auxiliary prediction head alone. Across nine simulated tasks, JEPA Policy improves mean success over the action-only MIP baseline and outperforms Diffusion Policy under the evaluated configurations, while adding 0.29 ms to MIP's model latency. A five-task, 630-episode physical-robot study produces the same pooled ranking. Further audits find no complete representation collapse under action supervision and identify a task-conditioned failure-ranking signal in future-prediction error. These results support paired future-representation supervision as a practical approach to low-latency visuomotor imitation without iterative generative sampling.

Continue reading on arxiv.org