Vision-Language Agents for Active Perception in Optics Laboratories
It is found that, given task-specific natural-language guidance, VLMs can estimate actuator-response relationships, resolve ambiguous observations through intervention, and actively create informative visual feedback when signals are sparse, suggesting that pretrained multimodal models can serve as important decision-m...
Ryan Lopez, Sachin Vaidya, Seouing-Ho Choi et al.
· 0 citations