@inproceedings{chen-etal-2025-multimodal, title = "Multimodal Language Models See Better When They Look Shallower", author = "Chen, Haoran and Lin, Junyan and Chen, Xinghao and Fan, Yue and Dong, Jianfeng and Jin, Xin and Su, Hui and Fu, Jinlan and Shen, Xiaoyu", editor = "Christodoulopoulos, Christos and Chakraborty, Tanmoy and Rose, Carolyn and Peng, Violet", booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing", month = nov, year = "2025", address = "Suzhou, China", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.339/", pages = "6688--6706", ISBN = "979-8-89176-332-6" }