@inproceedings{wang-etal-2024-m2pt, title = "{M}$^2${PT}: Multimodal Prompt Tuning for Zero-shot Instruction Learning", author = "Wang, Taowen and Liu, Yiyang and Liang, James Chenhao and Zhao, Junhan and Cui, Yiming and Mao, Yuning and Nie, Shaoliang and Liu, Jiahao and Feng, Fuli and Xu, Zenglin and Han, Cheng and Huang, Lifu and Wang, Qifan and Liu, Dongfang", editor = "Al-Onaizan, Yaser and Bansal, Mohit and Chen, Yun-Nung", booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing", month = nov, year = "2024", address = "Miami, Florida, USA", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.emnlp-main.218/", doi = "10.18653/v1/2024.emnlp-main.218", pages = "3723--3740" }