AsyncVLA: Asynchronous Flow Matching for Vision-Language-Action Models

TL;DR

AsyncVLA introduces an asynchronous flow matching framework for vision-language-action models, enabling flexible, self-correcting action generation that improves robotic manipulation performance in long-horizon tasks.

Contribution

It proposes a novel asynchronous flow matching approach with self-correction and confidence-based refinement, enhancing VLA models' stability and efficiency.

Findings

Outperforms existing methods on robotic benchmarks.

Demonstrates data efficiency and self-correction in experiments.

Works effectively in both simulation and real-world settings.

Abstract

Vision-language-action (VLA) models have recently emerged as a powerful paradigm for building generalist robots. However, traditional VLA models that generate actions through flow matching (FM) typically rely on rigid and uniform time schedules, i.e., synchronous FM (SFM). Without action context awareness and asynchronous self-correction, SFM becomes unstable in long-horizon tasks, where a single action error can cascade into failure. In this work, we propose asynchronous flow matching VLA (AsyncVLA), a novel framework that introduces temporal flexibility in asynchronous FM (AFM) and enables self-correction in action generation. AsyncVLA breaks from the vanilla SFM in VLA models by generating the action tokens in a non-uniform time schedule with action context awareness. Besides, our method introduces the confidence rater to extract confidence of the initially generated actions, enabling the model to selectively refine inaccurate action tokens before execution. Moreover, we propose a unified training procedure for SFM and AFM that endows a single model with both modes, improving KV-cache utilization. Extensive experiments on robotic manipulation benchmarks demonstrate that AsyncVLA is data-efficient and exhibits self-correction ability. AsyncVLA outperforms existing methods across both simulation and real-world evaluations. Our code is available at https://github.com/YuhuaJiang2002/AsyncVLA.