Embodied AI TopConf · CVPR2026

Evo-1: Lightweight Vision-Language-Action Model with Preserved Semantic Alignment

CVPR2026 / Vision-Language-Action Models

VLA感知
新标签打开 AlphaXiv新标签打开 Code
Evo-1: Lightweight Vision-Language-Action Model with Preserved Semantic Alignment figure
AlphaXiv 中文论文页面（可滚动查看）