mlsanityData to 14 Oct 2026

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

arXiv 2609.09630 ↗First posted 9 Sep 2026cs.ROcited by 0

On the map: Offline RL and imitation learning from data → Robot manipulation imitation learning

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Robot manipulation imitation learning, one of 13 directions in Offline RL and imitation learning from data. Builds on 43 of its 48 references that are in the map. First posted on arXiv 9 Sep 2026.

Builds on

43 of 48 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025ACT-JEPA: Novel Joint-Embedding Predictive Architecture for Efficient Policy Representation Learning24 Jan
  2. 2023MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations26 Oct
  3. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware23 Apr
  4. 2022Behavior Transformers: Cloning k modes with one stone22 Jun

Other references · 39

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  3. 2022Flow Matching for Generative Modelingcited by 5,702
  4. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  5. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  6. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 3,080
  7. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,887
  8. 2020Exploring Simple Siamese Representation Learningcited by 2,866
  9. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,838
  10. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,407
  11. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  12. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,061
27 more
  1. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,838
  2. 2023Consistency Modelscited by 1,822
  3. 2018World Modelscited by 1,513
  4. 2024Octo: An Open-Source Generalist Robot Policycited by 1,484
  5. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,410
  6. 2021VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learningcited by 1,057
  7. 2023Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecturecited by 1,039
  8. 2025V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planningcited by 809
  9. 2020CURL: Contrastive Unsupervised Representations for Reinforcement Learningcited by 760
  10. 2021What Matters in Learning from Offline Human Demonstrations for Robot Manipulationcited by 725
  11. 2023TD-MPC2: Scalable, Robust World Models for Continuous Controlcited by 512
  12. 2020robosuite: A Modular Simulation Framework and Benchmark for Robot Learningcited by 511
  13. 2021Implicit Behavioral Cloningcited by 452
  14. 2024One Step Diffusion via Shortcut Modelscited by 391
  15. 2021Understanding Dimensional Collapse in Contrastive Self-supervised Learningcited by 378
  16. 2023Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulationcited by 364
  17. 2020Data-Efficient Reinforcement Learning with Self-Predictive Representationscited by 318
  18. 2021Understanding self-supervised Learning Dynamics without Contrastive Pairscited by 256
  19. 2025LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristicscited by 254
  20. 2024Consistency Policy: Accelerated Visuomotor Policies via Consistency Distillationcited by 166
  21. 2024Predictive Inverse Dynamics Models are Scalable Learners for Robotic Manipulationcited by 161
  22. 2022Safe Planning in Dynamic Environments using Conformal Predictioncited by 119
  23. 2026VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Modelcited by 118
  24. 2024Unpacking Failure Modes of Generative Policies: Runtime Monitoring of Consistency and Progresscited by 69
  25. 2025Can We Detect Failures Without Failure Data? Uncertainty-Aware Runtime Failure Detection for Imitation Learning Policiescited by 52
  26. 2025Much Ado About Noising: Dispelling the Myths of Generative Robotic Controlcited by 36
  27. 2026JEPA-VLA: Video Predictive Embedding is Needed for VLA Modelscited by 24

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Demo-JEPA: Joint-Embedding Predictive Architecture for One-shot Cross-Embodiment Imitation
  2. 2026Imitation from Heterogeneous Demonstrations using Grounded Latent-Action World Models
  3. 2025Latent Diffusion Planning for Imitation Learning
  4. 2026Predict in Chunks, Revise in Spans: History-conditioned Action Regeneration for Robotic Manipulation
  5. 2025Masked Generative Policy for Robotic Control
  6. 2026Difference-Aware Retrieval Policies for Imitation Learning
  7. 2024Streaming Diffusion Policy: Fast Policy Synthesis with Variable Noise Diffusion Models
  8. 2026It's Not Just More Demos: Counterfactual Action Sensitivity Coverage for Data-Efficient Robust Robot Imitation