作者位次 #3/8ACL 2026Findings· Findings of ACL
Sculpting the Vector Space: Towards Efficient Multi-Vector Visual Document Retrieval via Prune-then-Merge Framework
Yibo Yan · Mingdong Ou · Yi Cao · Xin Zou · Jiahao Huo · Shuliang Liu · James Kwok · Xuming Hu
摘要
Visual Document Retrieval (VDR), which aims to retrieve relevant pages within vast corpora of visually-rich documents, is of significance in current multimodal retrieval applications. The state-of-the-art multi-vector paradigm excels in performance but suffers from prohibitive overhead, a problem...