SA-VLA: Spatially-Aware Flow-Matching for Vision-Language-Action Reinforcement Learning

作者：Xu Pan ID, Zhenglin Wan, Xingrui Yu ID, Xianwei Zheng ID, Youkai Ke, Ming Sun, Rui Wang, Ziwei Wang ID, Ivor Tsang ID · 单位：State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing (LIESMARS), Wuhan University, Department of Computer Science, National University of Singapore, Singapore, School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore · 会议/期刊：arXiv · 日期：2026-01-31 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with RL