作者:Wenjun Lin, Jensen Zhang, Kaitong Cai, Keze Wang · 单位:Sun Yat-sen University, Guangzhou, China · 会议/期刊:arXiv · 日期:2025-12-20 · 来源:Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with Auxiliary Tasks - World Model & Visual Prediction / World Model