作者：Haoxuan Wang, Gengyu Zhang, Yan Yan, Ramana Rao Kompella, Gaowen Liu · 单位：University of Illinois Chicago · 会议/期刊：arXiv · 日期：2026-02-24 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with Model-agnostic Strategies
