Wenlong Fang

Notes-guided MLLM Reasoning: Enhancing MLLM with Knowledge and Visual Notes for Visual Question Answering

The knowledge-based visual question answering (KB-VQA) task involves using external knowledge about the image to assist reasoning. Building on the impressive performance of multimodal large language model (MLLM), recent methods have commenced leveraging MLLM as an implicit knowledge base for reasoni…