@inproceedings{mi-etal-2026-overtone, title = "Overtone: Fine-Grained Audio Reasoning via Diagnostic-Driven Delayed Acoustic Fusion", author = "Mi, Zhuoyan and Sun, Kangle and Yang, Yikai and Fu, Yujie and Wang, Yuehai", editor = "Lee, Hung-Yi and Dev, Sunipa and Li, Jessy and Elliott, Desmond", booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing", month = oct, year = "2026", address = "Budapest, Hungary", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2026.emnlp-main.573/", pages = "13146--13164", ISBN = "979-8-89176-459-0" }