Beyond Dense Futures: World Models as Structured Planners for Robotic Manipulation

作者：Minghao Jin, Mozheng Liao, Mingfei Han, Zhihui Li, Xiaojun Chang · 单位：University of Science and Technology of China, Department of CV, MBZUAI · 会议/期刊：arXiv · 日期：2026-03-13 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with Auxiliary Tasks - World Model & Visual Prediction / World Model