Embodied AI TopConf · CVPR2026

OptimusVLA: Global Prior Meets Local Consistency: Dual-Memory Augmented Vision-Language-Action Model for Efficient Robotic Manipulation

CVPR2026 / Vision-Language-Action Models

VLA感知加速/部署
新标签打开 AlphaXiv新标签打开 Code
OptimusVLA: Global Prior Meets Local Consistency: Dual-Memory Augmented Vision-Language-Action Model for Efficient Robotic Manipulation figure
AlphaXiv 中文论文页面（可滚动查看）