4 papers · 1 filter
Inverting Multi-Vector Visual Document Indices
Zhuchenyang Liu, Yao Zhang, Yu Xiao
Prevailing multi-vector visual document retrievers store each page as about a thousand patch vectors, often in vector databases run by a third party. Since no one can read a page f…
ColNanoVDR: Document-Free Query Distillation for Multi-Vector Visual Document Retrieval via Optimal Transport
Zhuchenyang Liu, Ziyi Wang, Yao Zhang +1
Multi-vector retrievers built on vision-language models lead visual document retrieval (VDR), but they run a multi-billion-parameter query encoder on every search. Distilling this…
DistilVDR: A Compact End-to-End Visual Document Retriever via Dual-Student Distillation
Zhuchenyang Liu, Ziyi Wang, Yao Zhang +1
Visual document retrieval (VDR) is dominated by multi-billion-parameter models that are slow to index at full corpus scale and expensive to serve. Prior compression routes either t…
NanoVDR: Distilling a 2B Vision-Language Retriever into a 70M Text-Only Encoder for Visual Document Retrieval
Zhuchenyang Liu, Yao Zhang, Yu Xiao
Vision-Language Model (VLM) based retrievers have advanced visual document retrieval (VDR) to impressive quality. They require the same multi-billion parameter encoder for both doc…