MARS - A Foundational Map Auto-Regressor
Qi Zhang, Suvam Bag, Rupanjali Kukal, Mikael Figueroa, Rishi Madhok, Nikolaos Karianakis, Fuxun Yu
Abstract
Map generation tasks, featured by extensive non-structural vectorized data (e.g., points, polylines, and polygons), pose significant challenges to common pixel-wise generative models. Past works, by segmenting and then performing various vectorized post-processing, usually sacrifice accuracy. Motivated by the recent huge success of auto-regressive visual-language modeling, we propose the first map foundational model: Map Auto-Regressor (MARS), that is capable of generating both multi-polyline road networks and polygon buildings in a unified manner. We collected by far the largest multi-class map dataset, MAP-3M, to support the robust training. Extensive benchmarks highlight the superiority of MARS against literature works. Meanwhile, benefited from the auto-regressive and teaching-forcing based training, we develop the “Chat with MARS” capability that enables interactive human-in-the-loop map generation and correction.
BibTeX
@inproceedings{
zhang2026mars,
title={{MARS} - A Foundational Map Auto-Regressor},
author={Qi Zhang and Suvam Bag and Rupanjali Kukal and Mikael Figueroa and Rishi Madhok and Nikolaos Karianakis and Fuxun Yu},
booktitle={The Fourteenth International Conference on Learning Representations},
year={2026},
url={https://openreview.net/forum?id=QV4sV5cbLl}
}