cs.RONov 10, 2026

Elastic-WAM: Adaptive Spatiotemporal Imagination for Efficient Robot Control

Authors: Haitian Li, Tianfu Li, Xuxi Zhao, Zizheng Liu, Yangcheng Yu, Yiwen Hou, Zeyu Xiao, Mutian Xu, 

Organizations: National University of Singapore · RoboScience · The Hong Kong University of Science and Technology (Guangzhou) · Zhejiang University · 

Abstract

World-Action Models improve robot control by predicting future visual dynamics, but iterative video denoising incurs substantial inference overhead. Recent approaches reduce this cost through partial future denoising, yet typically rely on fixed refinement budgets. Our empirical observations reveal that preferred refinement depths vary across tasks and states, while different future regions exhibit varying relevance to action generation. Motivated by these findings, we propose Elastic-WAM, which adaptively allocates world refinement computation across temporal denoising time and spatial future space. A unified spatiotemporal refinement demand field governs when to stop world refinement, how far to advance each denoising step, and which regions to refresh. We parameterize this field with a shared temporal basis and spatial amplitudes, and learn it through a three-stage action-grounded supervised procedure. At inference, the learned field guides recurrent sparse world refinement to improve task success while reducing inference overhead. Evaluations across diverse simulation benchmarks and real-world long-horizon manipulation demonstrate state-of-the-art control performance with reduced inference latency.

Figures & tables

Appendix figures & tables2 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Efficient-WAM: A 1B-Parameter World-Action Model with Low-Cost Future Imagination

    Jun 8, 2026Jiajun Li, Tiecheng Guo, Yifan Ye +9World Models for RoboticsEfficient Inference for World Action Models

  2. DualWAM: Dual-System World Action Models for Asynchronous Global Planning and Local Refinement

    Sep 21, 2026Yixin Zheng, Jiangran Lyu, Yuntian Deng +6Long-Horizon Robotic ManipulationWorld Models for Robotics

  3. Rolling-WAM: World Action Models with Rolling Imagination

    Sep 24, 2026Yinghua Zhou, Junjie Ye, Yiqi Zhao +8Efficient InferenceWorld Models for Robotics