@inproceedings{ma-etal-2025-latte, title = "{LATTE}: Learning to Think with Vision Specialists", author = "Ma, Zixian and Zhang, Jianguo and Liu, Zhiwei and Zhang, Jieyu and Tan, Juntao and Shu, Manli and Niebles, Juan Carlos and Heinecke, Shelby and Wang, Huan and Xiong, Caiming and Krishna, Ranjay and Savarese, Silvio", 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.564/", pages = "11203--11240", ISBN = "979-8-89176-332-6" }