Awesome Robotics Manipulation · full_paper

VITRA: Scalable Vision-Language-Action Model Pretraining for Robotic Manipulation with Real-Life Human Activity Videos

arXiv · 2025-10-24 · Manipulation Tasks / Dexterous Manipulation / VLA

灵巧操作视频规划VLA基础模型操作
新标签打开 AlphaXiv新标签打开 Paper新标签打开 Code
VITRA: Scalable Vision-Language-Action Model Pretraining for Robotic Manipulation with Real-Life Human Activity Videos figure
AlphaXiv 中文论文页面（可滚动查看）