CVPR 2025 (Oral) / 规划与操作

RoboSpatial: Teaching Spatial Understanding to 2D and 3D Vision-Language Models for Robotics

作者：Chan Hee Song · 单位：The Ohio State University, NVIDIA · 会议/期刊：CVPR 2025 (Oral) · 分类：规划与操作 · 发布日期：2024

具身智能视觉语言动作机器人学习三维感知
新标签打开 AlphaXiv新标签打开 Project新标签打开 Code
RoboSpatial: Teaching Spatial Understanding to 2D and 3D Vision-Language Models for Robotics figure
AlphaXiv 中文概览（可滚动查看）