MVISTA-4D: View-Consistent 4D World Model with Test-Time Action Inference for Robotic Manipulation

作者：Jiaxu Wang Yicheng Jiang Tianlun He, Jingkai Sun, Qiang Zhang, Junhao He, Jiahang Cao, Zesen Gan, Mingyuan Sun, Qiming Shao Xiangyu Yue · 单位：MMLab, The Chinese University of Hong Kong The Hong · 会议/期刊：arXiv · 日期：2026-02-10 · 来源：Low-Level Learning-Based Action Modelling / Learning Strategy / World Model / 3D/Physics-consistent WMs