QG-CoC: Question-Guided Chain-of-Captions for Large Multimodal Models

Kuei-Chun Kao, Hsu Tzu-Yin, Yunqi Hong +2

Recently, Multimodal Large Language Models (MLLMs) encounter two key issues in multi-image contexts: (1) a lack of fine-grained perception across disparate images, and (2) a dimini…