@inproceedings{li-etal-2022-mplug,
    title = "m{PLUG}: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections",
    author = "Li, Chenliang  and
      Xu, Haiyang  and
      Tian, Junfeng  and
      Wang, Wei  and
      Yan, Ming  and
      Bi, Bin  and
      Ye, Jiabo  and
      Chen, He  and
      Xu, Guohai  and
      Cao, Zheng  and
      Zhang, Ji  and
      Huang, Songfang  and
      Huang, Fei  and
      Zhou, Jingren  and
      Si, Luo",
    editor = "Goldberg, Yoav  and
      Kozareva, Zornitsa  and
      Zhang, Yue",
    booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, United Arab Emirates",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.emnlp-main.488/",
    doi = "10.18653/v1/2022.emnlp-main.488",
    pages = "7241--7259"
}