cs.CVNov 14, 2026

WA-JEPA: Goal-Aware Predictive Feedback Action Refinement for a World-Action Model

Authors: Tao An, Weihang Liang, Tianqi Wang, Chuqing Cao, Wenming Tan, Kai Zhang, Haibo Lei, Tao Xie, 

Organizations: Harbin Institute of Technology · Anhui Polytechnic University · Hikvision Research Institute

Abstract

JEPA-based world models predict action consequences in latent space, but representative planning approaches rely on candidate-action search, requiring repeated evaluation of action sequences and incurring substantial online computational cost. Direct action generation avoids this search, yet how to leverage latent predictions to guide action generation given task goals remains a key challenge in translating learned physical dynamics into effective decisions. We introduce WA-JEPA, a world-action model that couples action generation, action-conditioned latent prediction, and goal-aware feedback. The model first generates an action proposal and predicts the resulting future scenes and proprioceptive states, then refines the proposal through two complementary feedback paths, using the task goal as a reference. Goal-discrepancy residual feedback (GDRF) uses differences between the latent representations of predicted scenes and the task goal to guide chunk-wise action refinement. Future-scene context feedback (FSCF) preserves fine-grained predicted scene representations to guide subsequent action refinement. Jointly learned from offline demonstrations, this process iteratively updates the same plan before execution, making future predictions directly participate in action generation without candidate-action search. We evaluate short-horizon goal reaching, long-horizon tasks, and full-task execution. The results show that goal-aware predictive feedback supports competitive task performance while maintaining a compact model and low online computational cost. Code is available at https://github.com/Dovisya/WA-JEPA.

Figures & tables

Appendix figures & tables9 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Exploring Temporal Context-Aware Physical Grounding in Latent World Models

    Oct 20, 2026Yilei Man, Yang Chen, Jingcai GuoWorld ModelsLatent World Models

  2. D-JEPA: A Decision-Aligned Latent World Model

    Sep 21, 2026Shuaijun Liu, Chengyu Wu, Qifu Wen +5World ModelsWorld Model-Based Planning

  3. Is Forward Prediction Enough? Physical State Grounding for JEPA World Models

    Aug 7, 2026Haodong Yan, Jiaguan Zhu, Mingyuan Jia +12Physical ReasoningWorld Models for Robotics