Embodied AI TopConf · CVPR2026

SaPaVe: Towards Active Perception and Manipulation in Vision-Language-Action Models for Robotics

CVPR2026 / Vision-Language-Action Models

VLA感知
新标签打开 AlphaXiv新标签打开 Project
SaPaVe: Towards Active Perception and Manipulation in Vision-Language-Action Models for Robotics figure
AlphaXiv 中文论文页面（可滚动查看）