@inproceedings{luo-etal-2024-codis, title = "{CODIS}: Benchmarking Context-dependent Visual Comprehension for Multimodal Large Language Models", author = "Luo, Fuwen and Chen, Chi and Wan, Zihao and Kang, Zhaolu and Yan, Qidong and Li, Yingjie and Wang, Xiaolong and Wang, Siyu and Wang, Ziyue and Mi, Xiaoyue and Li, Peng and Ma, Ning and Sun, Maosong and Liu, Yang", editor = "Ku, Lun-Wei and Martins, Andre and Srikumar, Vivek", booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", month = aug, year = "2024", address = "Bangkok, Thailand", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.acl-long.573/", doi = "10.18653/v1/2024.acl-long.573", pages = "10639--10659" }