Awesome Robotics Manipulation · full_paper

VIPA-VLA: Spatial-Aware VLA Pretraining through Visual-Physical Alignment from Human Videos

CVPR 2026 · 2025-12-15 · Low-Level Learning-Based Action Modelling / Input Modelling / 3D Vision Language Action Models

3D 表征视频规划VLA基础模型感知机器人学习
新标签打开 AlphaXiv新标签打开 Paper新标签打开 Code
VIPA-VLA: Spatial-Aware VLA Pretraining through Visual-Physical Alignment from Human Videos figure
AlphaXiv 中文论文页面（可滚动查看）