SOURCE-LINKED INTELLIGENCE

React When You Need To: Event-Triggered Asynchronous Inference for VLA Policies

arXiv · AI, language, vision and robotics · article · Sep 18, 2026 · UTC

Vision-Language-Action (VLA) models commonly predict action chunks, limiting their ability to react to environmental changes during execution. Existing asynchronous inference methods improve reactivity but typically rely on a fixed inference gap. In this paper, we propose an event-guided dynamic inference strategy that adapts the inference gap according to scene changes observed since the previous inference. Thereby, it simultaneously preserves motion consistency and prompt reactivity. Across static and dynamic real-world settings, our method consistently performs best, averaging 95% success a

Read original source ↗ Open in workspace

recordType

paper

region

Global