@inproceedings{gu-etal-2024-rwkv,
    title = "{RWKV}-{CLIP}: A Robust Vision-Language Representation Learner",
    author = "Gu, Tiancheng  and
      Yang, Kaicheng  and
      An, Xiang  and
      Feng, Ziyong  and
      Liu, Dongnan  and
      Cai, Weidong  and
      Deng, Jiankang",
    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://aclanthology.org/2024.emnlp-main.276/",
    doi = "10.18653/v1/2024.emnlp-main.276",
    pages = "4799--4812"
}