@inproceedings{wang-etal-2025-train, title = "Train a Unified Multimodal Data Quality Classifier with Synthetic Data", author = "Wang, Weizhi and Lin, Rongmei and Li, Shiyang and Lockard, Colin and Sarkhel, Ritesh and Lokegaonkar, Sanket and Shang, Jingbo and Yan, Xifeng and Zalmout, Nasser and Li, Xian", editor = "Christodoulopoulos, Christos and Chakraborty, Tanmoy and Rose, Carolyn and Peng, Violet", booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025", month = nov, year = "2025", address = "Suzhou, China", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2025.findings-emnlp.104/", pages = "1972--1986", ISBN = "979-8-89176-335-7" }