VLM4VLA: Revisiting Vision-Language-Models in Vision-Language-Action Models

作者：Jianke Zhang, Xiaoyu Chen, Qiuyue Wang, Mingsheng Li, Yanjiang Guo, Yucheng Hu, Jiajun Zhang, Shuai Bai, Junyang Lin, Jianyu Chen · 单位：Institute for Interdisciplinary Information Sciences, Tsinghua University · 会议/期刊：arXiv · 日期：2026-01-06 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / Evaluation of Vision Language Action Models