Embodied AI TopConf · CORL2025

LaVA-Man: Learning Visual Action Representations for Robot Manipulation

CORL2025 / Vision-Language-Action Model

视觉语言动作感知
新标签打开 AlphaXiv新标签打开 Project
LaVA-Man: Learning Visual Action Representations for Robot Manipulation figure
AlphaXiv 中文论文页面（可滚动查看）