@inproceedings{sim-etal-2025-vlms, title = "Can {VLM}s Actually See and Read? A Survey on Modality Collapse in Vision-Language Models", author = "Sim, Mong Yuan and Zhang, Wei Emma and Dai, Xiang and Fang, Biaoyan", 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/landing_page/2025.findings-acl.1256/", pages = "24452--24470", ISBN = "979-8-89176-256-5" }