cs.RONov 17, 2026

Making Future-Predictive Representations Actionable

Authors: Fangchuan Wang, Hao Zhang, Qiyan Zhao, Huanqi Zhao, Guanting Ye, Xu-Yao Zhang, Yuqing Gao

Organizations: Xinjiang University · Tongji University · Institute of Automation, Chinese Academy of Sciences · University of Science and Technology of China

Abstract

Recent world action models (WAMs) drop future prediction at inference, assuming that representations learned through auxiliary future supervision still benefit action generation. However, our layerwise analysis of Fast-WAM reveals a depth-dependent mismatch: while probes decode future state transitions more accurately from deeper visual layers, the gradients and visual focuses of the future and action objectives increasingly diverge with depth, leaving much of this predictive information unused by the action pathway. To address this issue, we introduce RelayWAM, which adds an explicit transition space between the video and action backbones. Conditioned on the task instruction, robot state, and current action estimate, recurrent transition layers extract step-relevant predictive cues across depth and relay them directly into the action attention, without generating future frames at inference. Experiments show that RelayWAM substantially amplifies the benefit of future supervision, translating into stronger generalization under distribution shifts in both simulation and real-world robot tasks. On LIBERO-Plus, RelayWAM achieves 72.03% mean success, compared to 56.42% without future supervision and 51.50% for Fast-WAM.

Figures & tables

Appendix figures & tables2 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. MT-WAM: Reorienting the One-Pass Predictive Representation Toward Action Generation

    Sep 18, 2026Yiguang Yang, Jiankun Peng, Xiaoming Wang +2World Action ModelsMotion Representation Learning

  2. De-Diffusing WAMs: Action-Sufficient Direct Prediction for Robot Control

    Oct 20, 2026Shaoyi Zheng, Zhongtao Jiang, Yue Peng +4Efficient Inference for World Action ModelsWorld Models for VLAs

  3. MoWAM: Explicit Future Motion Prediction for Efficient World Action Models

    Sep 17, 2026Jiayu Wang, Bin Zhu, Yue Yu +1World Models for RoboticsWorld Model-Based Planning