@inproceedings{bueno-garg-2026-culturally,
    title = "Culturally Grounded Image Captioning in Indigenous Languages with Vision-Language Models: Cascaded and Single-Stage Approaches",
    author = "Bueno, Mirelle  and
      Garg, Sushil",
    editor = "Mager, Manuel  and
      Ebrahimi, Abteen  and
      Bui, Minh Duc  and
      Pugh, Robert  and
      Oncevay, Arturo  and
      Chiruzzo, Luis  and
      Solano, Rolando Coto  and
      Rijhwani, Shruti  and
      Von Der Wense, Katharina",
    booktitle = "Proceedings of the Sixth Workshop on {NLP} for Indigenous Languages of the {A}mericas ({A}mericas{NLP})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.americasnlp-6.23/",
    pages = "248--256",
    ISBN = "979-8-89176-415-6"
}