作者位次 #10/10ECCV 2026Poster
LaMP: Learning Vision-Language-Action Policies with 3D Scene Flow as Latent Motion Prior
Xinkai Wang · Chenyi Wang · Yifu Xu · Mingzhe Ye · Fu-Cheng Zhang · Jialin Tian · Xinyu Zhan · Lifeng Zhu · Cewu Lu · Lixin Yang
多模态3D Reconstruction, Registration and Scene ModelingEmbodied AI, Robotics & Autonomous DrivingOpenReview