@inproceedings{xu-etal-2023-managertower,
    title = "{M}anager{T}ower: Aggregating the Insights of Uni-Modal Experts for Vision-Language Representation Learning",
    author = "Xu, Xiao  and
      Li, Bei  and
      Wu, Chenfei  and
      Tseng, Shao-Yen  and
      Bhiwandiwalla, Anahita  and
      Rosenman, Shachar  and
      Lal, Vasudev  and
      Che, Wanxiang  and
      Duan, Nan",
    editor = "Rogers, Anna  and
      Boyd-Graber, Jordan  and
      Okazaki, Naoaki",
    booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.acl-long.811/",
    doi = "10.18653/v1/2023.acl-long.811",
    pages = "14507--14525"
}