@inproceedings{fang-etal-2024-vimi,
    title = "{VIMI}: Grounding Video Generation through Multi-modal Instruction",
    author = "Fang, Yuwei  and
      Menapace, Willi  and
      Siarohin, Aliaksandr  and
      Chen, Tsai-Shien  and
      Wang, Kuan-Chieh  and
      Skorokhodov, Ivan  and
      Neubig, Graham  and
      Tulyakov, Sergey",
    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/fix-sig-urls/2024.emnlp-main.254/",
    doi = "10.18653/v1/2024.emnlp-main.254",
    pages = "4444--4456"
}