cs.RONov 19, 2026

WAMotor: Accelerating World Action Models via Speculative Inference under Dual Nonuniform Denoising Dynamics

Authors: Zexun Lin, Yuan Feng, Xike Xie

Organizations: University of Science and Technology of China (USTC) · Data Darkness Lab, MIRACLE Center, Suzhou Institute for Advanced Research, USTC

Abstract

World Action Models (WAMs) unify world modeling and action generation for robotic control by integrating flow-matching velocities, yet suffer from high multi-step denoising latency. Recent studies have explored speculative inference to accelerate WAMs by drafting and verifying denoising steps in parallel. However, existing methods either require training task-specific draft models or overlook critical WAM denoising dynamics when reusing past velocities as drafts. We revisit the denoising dynamics of WAMs and identify a dual nonuniformity that breaks standard velocity-reuse assumptions: velocity smoothness is nonuniform as adjacent velocity residuals differ sharply at early and final steps, so reuse there yields large residuals, which nonuniform integration time steps further translate into local state errors that accumulate into the final action distribution. Accordingly, we formalize this by theoretically deriving a trajectory error tolerance bound that characterizes how velocity residuals and integration time steps affect the final action distribution. Based on this, we propose WAMotor, the first speculative inference method tailored to the dual nonuniformity in WAMs. It selects reliable anchor velocities by deferring speculation and employs time-step-aware verification that scales acceptance thresholds by integration time step size. WAMotor offers plug-and-play benefits, enabling seamless integration with prior WAMs. Extensive evaluations on LIBERO, RoboTwin 2.0, and LIBERO-Plus show that WAMotor achieves 2.86×\times--4.28×\times end-to-end speedups while maintaining task success rates. Our code is available at: https://github.com/Overdue-Lin/WAMotor

Figures & tables

Appendix figures & tables8 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Efficient World Action Model Inference with Adaptive Intermediate States

    Sep 28, 2026Zhinnan Liu, Haozhi Han, Ruge Zhang +8Efficient Transformer InferenceWorld Model-Based Planning

  2. 1Step-WAM: Your World Action Model but Faster using 1-Step Action Generation

    Oct 11, 2026Rundong Su, Pengtao Chen, Haohan Geng +6Efficient Inference for World Action ModelsWorld Action Models

  3. 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