Embodied AI TopConf · ICLR2025

GravMAD: Grounded Spatial Value Maps Guided Action Diffusion for Generalized 3D Manipulation

ICLR2025 / Policies

3D 视觉策略学习
新标签打开 AlphaXiv新标签打开 Project
GravMAD: Grounded Spatial Value Maps Guided Action Diffusion for Generalized 3D Manipulation figure
AlphaXiv 中文论文页面（可滚动查看）