ForeAct: Steering Your VLA with Efficient Visual Foresight Planning
arXiv:2602.12322v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models convert high-level language instructions into concrete, executable actions, a task that is especially challenging in open-world environments. …
Zhuoyang Zhang, Shang Yang, Qinghao Hu, Luke J. Huang, James Hou, Yufei Sun, Yao Lu, Song Han
18 views