作者:Wangtian Shen, Jinming Ma, Mingliang Zhou, Ziyang Meng · 单位:Tsinghua University, Xiaomi (China) · 会议/期刊:arXiv · 日期:2026-01-18 · 来源:Low-Level Learning-Based Action Modelling / Input Modelling / 2D Non-LLM-based Vision Language Action Models