@inproceedings{xiang-etal-2026-multimodal, title = "{M}ulti{M}odal Code-Switching: Interleaving Visual Objects into Language for Explicit Object-Level Alignment", author = "Xiang, Changhao and Xing, Shangyu and Wu, Zhen and Zhang, Jianbing and Dai, Xinyu", 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.2647/", pages = "60235--60256", ISBN = "979-8-89176-459-0" }