Visual Grounding（视觉定位）是一种让多模态大模型能够将自然语言描述精确映射到图像具体区域（Bounding Box）的机制，通过文本指令与像素坐标的语义对齐，提升模型对物理世界的感知与交互能力。这种机制使得大模型不再局限于全局的图像描述，而是能够根据 ...

Comparative overview of two 3DVG approaches. (a) Supervised 3DVG involves input from 3D scans combined with text queries, guided by object-text pair annotations, (b) Zero-shot 3DVG identifies the ...

Abstract: Automatic detection and prevention of open-set failures are crucial in closed-loop robotic systems. Recent studies often struggle to simultaneously identify unexpected failures reactively ...