MapReader: a framework for learning a visual language model for map analysis

Yifan Zhang, Wei Luo

Keywords: Map analysis, map understanding, cartography, visual language model

TL;DR: We developed MapReader, a specialized VLM for map analysis, using a data collection strategy that combines self-instruction and expert refinement.

Confirmation Of Submission Requirements: I submit a previously published paper. It was published in an archival peer–reviewed venue on or after September 8th 2024, I specify the DOI in the field below, and I submit the camera-ready version of the paper.

DOI: https://doi.org/10.1080/13658816.2025.2455112

Submission Number: 156