ProbeFlow: Training-Free Adaptive Flow Matching for Vision-Language-Action Models

作者：Zhou Fang, Jiaqi Wang, Yi Zhou, Qiongfeng Shi · 单位：School of Computer Science and Engineering, Southeast University, China, Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary, School of Electronic Science & Engineering, Southeast University, China · 会议/期刊：arXiv · 日期：2026-03-18 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with Efficiency / Action Decoding