@inproceedings{guan-etal-2025-cot, title = "{C}o{T}-{VTM}: Visual-to-Music Generation with Chain-of-Thought Reasoning", author = "Guan, Xikang and Gu, Zheng and Huo, Jing and Ding, Tianyu and Gao, Yang", 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.647/", pages = "12493--12510", ISBN = "979-8-89176-256-5" }