SOURCE-LINKED INTELLIGENCE

FlashVLA: Streaming Action Decoding for Fast and Asynchronous VLA Inference

arXiv · AI, language, vision and robotics · article · Aug 27, 2026 · UTC

Vision-Language-Action (VLA) models are increasingly promising for robotic manipulation, yet their real-world deployment remains bottlenecked by high inference latency and unstable asynchronous execution. This challenge is particularly pronounced in flow-matching-based VLA models, where action decoding requires multiple iterative steps conditioned on the VLM context. While efficient inference methods improve control frequency and asynchronous methods reduce execution idle time, existing approaches often fail to jointly achieve low-latency inference and accurate, temporally consistent asynchron

Read original source ↗ Open in workspace

recordType

paper

region

Global