AI RESEARCH
Overview of the EReL@MIR 2025 Multimodal Document Retrieval Challenge (Track 1)
arXiv CS.AI
•
ArXi:2606.04240v1 Announce Type: cross Retrieval over visually-rich documents, pages that interleave text with figures, tables, and charts, is essential for multimodal retrieval-augmented generation, yet most retrievers still discard the visual channel. The \emph{Multimodal Document Retrieval Challenge}, Track~1 of the MIR Challenge at the first EReL