mlsanityData to 14 Oct 2026

Retrieval-Augmented Search for Large-Scale Map Collections with ColPali

arXiv 2510.25718 ↗First posted 29 Oct 2025cs.IR cs.DLcited by 0

On the map: Retrieval-augmented generation → Multimodal RAG

Abstract (arXiv)

Multimodal approaches have shown great promise for searching and navigating digital collections held by libraries, archives, and museums. In this paper, we introduce map-RAS: a retrieval-augmented search system for historic maps. In addition to introducing our framework, we detail our publicly-hosted demo for searching 101,233 map images held by the Library of Congress. With our system, users can multimodally query the map collection via ColPali, summarize search results using Llama 3.2, and upload their own collections to perform inter-collection search. We articulate potential use cases for archivists, curators, and end-users, as well as future work with our system in both machine learning and the digital humanities. Our demo can be viewed at: http://www.mapras.com.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Multimodal RAG, one of 15 directions in Retrieval-augmented generation. Builds on 8 of its 21 references that are in the map. First posted on arXiv 29 Oct 2025.

Builds on

8 of 21 references.

References · 8

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2024PaliGemma: A versatile 3B VLM for transfercited by 696
  4. 2024Long-CLIP: Unlocking the Long-Text Capability of CLIPcited by 300
  5. 2025ArtSeek: Deep artwork understanding via multimodal in-context reasoning and late interaction retrievalcited by 5
  6. 2025Digital Collections Explorer: An Open-Source, Multimodal Viewer for Searching Digital Collectionscited by 2
  7. 2024Integrating Visual and Textual Inputs for Searching Large-Scale Map Collections with CLIPcited by 1
  8. 2025RiverEcho: Real-Time Interactive Digital System for Ancient Yellow River Culturecited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Explainable Search and Discovery of Visual Cultural Heritage Collections with Multimodal Large Language Models
  2. 2026Improving Access to Historical Archives with Real-time RAG-based Systems ↗
  3. 2026CultureBot: A Framework for Retrieval-Augmented Exploration of Cultural Heritage Data
  4. 2024ColPali: Efficient Document Retrieval with Vision Language Models
  5. 2026Generalizable Multiscale Segmentation of Heterogeneous Map Collections
  6. 2025A Preliminary Study of RAG for Taiwanese Historical Archives
  7. 2025Retrieval-Augmented Generation for Natural Language Art Provenance Searches in the Getty Provenance Index
  8. 2023Multimodal Search on Iconclass using Vision-Language Pre-Trained Models