Awesome Robotics Manipulation · full_paper

LaMP: Learning Vision-Language-Action Policies with 3D Scene Flow as Latent Motion Prior

arXiv · 2026-03-26 · Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with Auxiliary Tasks - Visual Goal Extraction

3D 表征辅助任务VLALatent Learning感知机器人学习
新标签打开 AlphaXiv新标签打开 Paper新标签打开 Project
LaMP: Learning Vision-Language-Action Policies with 3D Scene Flow as Latent Motion Prior figure
AlphaXiv 中文论文页面（可滚动查看）