作者：Yichao Shen, Fangyun Wei, Zhiying Du, Yaobo Liang, Yan Lu, Jiaolong Yang, Nanning Zheng, Baining Guo · 单位：Microsoft Research Asia, Fudan University · 会议/期刊：NeurIPS 2025 · 日期：2025-12-07 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with Auxiliary Tasks - World Model & Visual Prediction / Visual/State Prediction/Generation
