@inproceedings{fu-etal-2025-multimodal, title = "Multimodal Large Language Models for Text-rich Image Understanding: A Comprehensive Review", author = "Fu, Pei and Guan, Tongkun and Wang, Zining and Guo, Zhentao and Duan, Chen and Sun, Hao and Chen, Boming and Jiang, Qianyi and Ma, Jiayao and Zhou, Kai and Luo, Junfeng", editor = "Che, Wanxiang and Nabende, Joyce and Shutova, Ekaterina and Pilehvar, Mohammad Taher", booktitle = "Findings of the Association for Computational Linguistics: ACL 2025", month = jul, year = "2025", address = "Vienna, Austria", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/display_plenaries/2025.findings-acl.1023/", pages = "19941--19958", ISBN = "979-8-89176-256-5" }