@inproceedings{gloria-silva-etal-2024-show,
    title = "Show and Guide: Instructional-Plan Grounded Vision and Language Model",
    author = "Gl{\'o}ria-Silva, Diogo  and
      Semedo, David  and
      Magalhaes, Joao",
    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.1191/",
    doi = "10.18653/v1/2024.emnlp-main.1191",
    pages = "21371--21389"
}