ForeAct: Steering Your VLA with Efficient Visual Foresight Planningg

作者：Zhuoyang Zhang Shang Yang Qinghao Hu, Luke J. Huang, James Hou, Yufei Sun, Yao Lu, Song Han · 单位：MIT, NVIDIA, Caltech · 会议/期刊：CVPR 2026 · 日期：2026-02-12 · 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