Skip to content
Review

AnyStep-WAM: Budget-Aligned Distillation and Adaptive Inference for World Action Models

Sep 2026 · arXiv.org · Vol abs/2609.33748 · 0 citations · 27 references
Computer Science

TL;DR

AnyStep World Action Model is introduced, a general framework for tunable-budget prediction and scene-dependent computation allocation and a lightweight risk-benefit scheduler predicts teacher-curvature-based difficulty and budget-specific student-teacher fidelity from a single one-step preview, selecting the smallest budget predicted to satisfy risk-adaptive fidelity requirements.

Abstract

World-action models (WAMs) couple predictive visual modeling with action generation, typically relying on iterative denoising with a fixed denoising steps. However, manipulation tasks contain actions chunks with varying sensitivity to generation errors: critical actions require precision, while less sensitive actions allow faster generation with fewer denoising steps. Here we introduce AnyStep World Action Model, a general framework for tunable-budget prediction and scene-dependent computation allocation. Our budget-aligned teacher-trajectory distillation trains interval-conditioned flow maps using explicit frozen-teacher transitions and shared low-rank adapters, supporting action generation from one-step prediction to multi-step refinement. Building on this capability, a lightweight risk-benefit scheduler predicts teacher-curvature-based difficulty and budget-specific student-teacher fidelity from a single one-step preview, selecting the smallest budget predicted to satisfy risk-adaptive fidelity requirements. We evaluate our framework on three widely used WAMs Motus, FastWAM, and LingBotVA using RoboTwin 2.0. Our method reduces average denoising steps by 60.2%, 49.8%, and 85.28%, respectively, while maintaining baseline task success rates. In particular, our AnyStep training substantially improves model performance under a one-step denoising budget, increasing task success rates by 7.07%, 12.08%, and 8.94% on Motus, FastWAM, and LingBotVA, respectively. Experiments on six real-world manipulation tasks further validate its effectiveness.

View source

Similar papers

#machine learning Preprint Oct 2026

RealtimeWAM: One-Step Asynchronous World Action Models

World Action Models (WAMs) incorporate visual representations from video generation backbones to guide action prediction. Recent efficient WAMs adopt Mixture-of-Transformers (MoT) architectures and compute video representations once for reuse by the action expert. However, intra-expert iteration (\ie, multi-step action...

Cheng-Tao Lv, Jin-Yang Du, Shu-Yi Feng et al. · 0 citations
Preprint Oct 2026

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

1Step-WAM is introduced, a framework that transforms multi-step action denoising into one single forward and enables action generation to execute in parallel with visual prefilling, completely breaking the sequential bottleneck of the traditional imagination-then-action paradigm.

Run-Dong Su, Pengtao Chen, Hao-Han Geng et al. · 0 citations
#machine learning Preprint Oct 2026

WAM-Cache: Staleness-Bounded KV Reuse for Efficient World Action Models

World Action Models (WAMs) enable generalist robot manipulation by conditioning an action expert on representations from a pretrained video Diffusion Transformer (DiT). In closed-loop control, the video DiT runs at every chunk to encode the current observation into layerwise key-value (KV) pairs that the action expert...

Kai-Qi Ding, Yang He, Rui-Jie Quan et al. · 0 citations
Preprint Oct 2026

MARS: Systematic Multi-Level Acceleration for World Action Models

World Action Models (WAMs) have emerged as a promising alternative for embodied intelligence by jointly predicting future world states and robot actions. However, their heavy visual encoding and iterative generative inference incur substantial latency, limiting their applicability to high-frequency closed-loop control....

Zeng-Yuan Zuo, Yong-Chang Zhang, Guang-Yu Zhao et al. · 0 citations
Preprint Oct 2026

StreamingWAM: Streaming World Action Modeling via Chunk-Wise Staircase Flow Matching

World Action Models (WAMs), often built upon pretrained video-generation world models, have emerged as a promising framework for general-purpose and open-ended robot control. However, their real-world deployment often suffers from discontinuous and jerky execution. Existing methods typically address this issue by eithe...

Shao-Jie Ren, Jing-Wen Sun, Ze-Zhi Liu et al. · 0 citations
#artificial intelligence Preprint Aug 2026

PAVE: Predictive Alignment and Value-Guided Evolution for World-Action Policies

Every valid trajectory can teach what physically happened, while the actor is deployed only under the condition associated with relatively better actions, in \method, a direct world-action policy that combines outcome-agnostic predictive learning with outcome-aware policy improvement.

Bo-Tong Zhao, Fangjie Yu, Tim Yu et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.