Author name: Yingjian Zhu, Xinming Wang, Kun Ding, Ying Wang, Bin Fan, Shiming Xiang

arXiv:2604.05818v2 Announce Type: replace
Abstract: Multi-modal Retrieval-Augmented Generation (RAG) has emerged as a highly effective paradigm for Knowledge-Based Visual Question Answering (KB-VQA). Despite recent advancements, prevailing methods sti…

arXiv:2604.05818v1 Announce Type: new
Abstract: Multi-modal Retrieval-Augmented Generation (RAG) has emerged as a highly effective paradigm for Knowledge-Based Visual Question Answering (KB-VQA). Despite recent advancements, prevailing methods still p…