@inproceedings{blasi-nunez-etal-2025-mldataforge,
    title = "{MLD}ata{F}orge: Accelerating Large-Scale Dataset Preprocessing and Access for Multimodal Foundation Model Training",
    author = "Blasi N{\'u}{\~n}ez, Andrea  and
      Achatius Galke, Lukas Paul  and
      Schneider-Kamp, Peter",
    editor = "Angelova, Galia  and
      Kunilovskaya, Maria  and
      Escribe, Marie  and
      Mitkov, Ruslan",
    booktitle = "Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era",
    month = sep,
    year = "2025",
    address = "Varna, Bulgaria",
    publisher = "INCOMA Ltd., Shoumen, Bulgaria",
    url = "https://aclanthology.org/2025.ranlp-1.21/",
    pages = "175--183"
}