Preprint
Aug 2026
Beyond Visual Similarity: Entity-Aligned Retrieval for Knowledge-Based Visual Question Answering
KBMR is proposed, the first MLLM-based embedding retriever tailored for KB-VQA, and an MLLM-based semantic discriminator that generates continuous entity-consistency weights is introduced to tackle the challenge of noisy supervision in Wikipedia-scale retrieval.
Hangrui Xu, Zhengxian Wu, Yu Yu et al.
· 0 citations