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

• URL: http://arxiv.org/abs/2609.09630v1
• Date: Wed, 09 Sep 2026 02:42:20 GMT
• Title: JEPA Policy: Diffusion-Free Imitation Learning via Paired Action and Future Representation Prediction
• Abstract summary: JEPA Policy is a diffusion-free framework that uses the action chunk and its observed future representation as paired training targets.<n>Future prediction can therefore shape the representation used to generate actions.<n>Results support paired future-representation supervision as a practical approach to low-latency visuomotor imitation without iterative generative sampling.
• Score: 6.889062419237111
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Foresight Without Seeing: Latent Futures for World Action Models [31.423405133926334]
  We propose ForeWAM, a dynamics-conditioned direct-policy WAM that provides predictive context for action generation without decoding future videos.<n>We also introduce dynamics supervised by a frozen latent action teacher, encouraging the implicit future states to capture interaction-induced transitions such as object motion, contact changes, and task progress.<n>Without embodied robot data pretraining, the standard and accelerated variants of ForeWAM achieve average success rates of 96.7% and 96.9% on LIBERO, respectively.
  arXiv  Detail & Related papers  (2026-08-12T03:27:43Z)
• SLIM-0.5B: Learning Action-Grounded Predictive Latents for Robot Manipulation [35.54319311306262]
  We present SLIM, a compact latent interaction policy.<n>It learns representations through self-supervised masked trajectory prediction.<n>SLIM matches or exceeds representative large-scale VLA and world-action-model baselines with fewer parameters.
  arXiv  Detail & Related papers  (2026-08-10T15:58:39Z)
• JEPA-WAM: Learning Vision-Language-Action Policies with Joint-Embedding World Modeling [23.76460420882974]
  We introduce JEPA-WAM, a latent WAM built in a pretrained V-JEPA space.<n>It couples latent transition prediction with continuous action generation through a shared predictor.<n>On LIBERO-Plus, JEPA-WAM achieves 79.2%, the best result without large-scale robot-policy pretraining.
  arXiv  Detail & Related papers  (2026-08-10T09:57:54Z)
• FutureRTC: Real-Time Robot Execution with Anticipatory-Conditioned Action Chunking [51.97839311685636]
  FutureRTC is a plug-and-play adaptation framework that predicts execution-time observations and states for asynchronous VLA control without modifying the underlying policy.<n>We show that FutureRTC achieves robustness to inference delays, resulting in smoother trajectories, faster execution, and consistently higher task success rates.
  arXiv  Detail & Related papers  (2026-07-27T05:10:16Z)
• MoP-JEPA: Hard-Assigned Predictor Mixtures for Stochastic JEPA World Models [14.76812870029721]
  MoP-JEPA produces a finite candidate set in one pass.<n>On held-out OGBench transitions, graph search with single-output predictors succeeds on $0.02$--$0.09$ of queries, whereas MoP-JEPA reaches $0.85$.
  arXiv  Detail & Related papers  (2026-07-06T15:47:37Z)
• $ω$-EVA: Envision, Verify, and Act with Latent Interactive World Models [28.544954130906135]
  Embodied policies typically map current observations directly to actions, leaving candidate-action consequences implicit.<n>We introduce $$-EVA, a latent interactive world model that realizes an Envision-Verify-Act loop for embodied action generation.<n>Its three-stage framework learns action-conditioned latent dynamics, trains a language-conditioned flow policy, and feeds the policy's proposal back through the world model.
  arXiv  Detail & Related papers  (2026-06-08T13:12:56Z)
• TapSampling: Inference-Time Sampling with a Task-Progress-Understanding Verifier for Robotic Manipulation [61.35569005726248]
  Existing embodied control research demonstrates remarkable performance improvements by scaling training data and model size.<n>Non-deterministic generative models, such as diffusion and autoregressive models, have been widely adopted in the field of embodied control.<n>We propose textbfTapSampling, a plug-and-play framework for inference-time sampling.
  arXiv  Detail & Related papers  (2026-05-25T08:03:31Z)
• From Imagined Futures to Executable Actions: Mixture of Latent Actions for Robot Manipulation [88.39072412680633]
  We propose MoLA, a control-oriented interface that transforms imagined future videos into executable representations.<n>We evaluate our approach on simulated benchmarks and real-world robot manipulation tasks.
  arXiv  Detail & Related papers  (2026-05-12T14:15:16Z)
• HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model [54.64088247291416]
  A fundamental objective of manipulation policy design is to endow robots to comprehend human instructions, reason about scene cues, and execute generalized actions in dynamic environments.<n>Recent autoregressive vision-language-action (VLA) methods inherit common-sense reasoning capabilities from vision-language models (VLMs) for next action-token prediction.<n>We introduce HybridVLA, a unified framework that absorbs the continuous nature of diffusion-based actions and the contextual reasoning of autoregression.
  arXiv  Detail & Related papers  (2025-03-13T17:59:52Z)
• ACT-JEPA: Novel Joint-Embedding Predictive Architecture for Efficient Policy Representation Learning [90.41852663775086]
  ACT-JEPA is a novel architecture that integrates imitation learning and self-supervised learning.<n>We train a policy to predict action sequences and abstract observation sequences.<n>Our experiments show that ACT-JEPA improves the quality of representations by learning temporal environment dynamics.
  arXiv  Detail & Related papers  (2025-01-24T16:41:41Z)
• Bidirectional Decoding: Improving Action Chunking via Guided Test-Time Sampling [51.38330727868982]
  We show how action chunking impacts the divergence between a learner and a demonstrator.<n>We propose Bidirectional Decoding (BID), a test-time inference algorithm that bridges action chunking with closed-loop adaptation.<n>Our method boosts the performance of two state-of-the-art generative policies across seven simulation benchmarks and two real-world tasks.
  arXiv  Detail & Related papers  (2024-08-30T15:39:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.