作者：Qingda Hu, Ziheng Qiu, Zijun Xu, Kaizhao Zhang, Xizhou Bu, Zuolei Sun, Bo Zhang, Jieru Zhao, Zhongxue Gan, Wenchao Ding · 单位：Fudan Academy for Engineering and Technology, Fudan University, Department of Computer Science and Engineering, Shanghai Jiao Tong University, China · 会议/期刊：arXiv · 日期：2025-12-31 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Non-LLM-based Vision Language Action Models
