Embodied AI TopConf · ICCV2025

Moto: Latent Motion Token as the Bridging Language for Learning Robot Manipulation from Videos

ICCV2025 / Vision-Language-Action Model

视觉语言动作视频感知
新标签打开 AlphaXiv新标签打开 Project
Moto: Latent Motion Token as the Bridging Language for Learning Robot Manipulation from Videos figure
AlphaXiv 中文论文页面（可滚动查看）