@inproceedings{hyun-bin-etal-2026-spatio, title = "Spatio-Temporal Audio Language Modeling for Dynamic Sound Sources", author = "Hyun-Bin, Oh and Shimada, Kazuki and Takida, Yuhta and Sung-Bin, Kim and Uesaka, Toshimitsu and Shibuya, Takashi and Lee, Kyeongyoon and Oh, Tae-Hyun and Mitsufuji, Yuki", 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.2043/", pages = "46568--46590", ISBN = "979-8-89176-459-0" }