SmoothVLA: Aligning Vision-Language-Action Models with Physical Constraints via Intrinsic Smoothness Optimization

作者：Jiashun Li, Xiaoyu Shi, Hong Xie, Mingsheng Shang, Yun Lu · 单位：Chongqing University of Posts and Telecommunications, Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences · 会议/期刊：arXiv · 日期：2026-03-14 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with RL