按需反应：VLA 策略的事件触发异步推理
React When You Need To: Event-Triggered Asynchronous Inference for VLA Policies
- Technical University of Munich（慕尼黑工业大学）
- Mohamed Bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）
机构由 AI 辅助整理，请以论文原文为准。
中文总结 AI 辅助
针对VLA模型反应性不足，提出事件触发动态推理策略，自适应调整推理间隔，在真实场景中实现95%成功率，显著优于基线。
中文摘要 AI 辅助
视觉-语言-动作（VLA）模型通常预测动作块，限制了其在执行过程中对环境变化的反应能力。现有的异步推理方法虽能提高反应性，但通常依赖于固定的推理间隔。本文提出了一种事件引导的动态推理策略，该策略根据自上次推理以来观察到的场景变化来调整推理间隔。由此，该方法同时保持了运动一致性和即时反应性。在静态和动态的真实世界场景中，我们的方法始终表现最佳，平均成功率达95%，比最强基线高出55个百分点。代码将在论文接收后公开，项目页面见本https URL。
英文摘要
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 and exceeding the strongest baseline by 55 percentage points. The code will be made publicly available upon acceptance. The project page is available at https://react-when-you-need-to.github.io/.
