@inproceedings{li-etal-2025-foundation,
    title = "Foundation Models Meet Embodied Agents",
    author = "Li, Manling  and
      Li, Yunzhu  and
      Mao, Jiayuan  and
      Huang, Wenlong",
    editor = "Lomeli, Maria  and
      Swayamdipta, Swabha  and
      Zhang, Rui",
    booktitle = "Proceedings of the 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 5: Tutorial Abstracts)",
    month = may,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/Author-page-Marten-During-lu/2025.naacl-tutorial.3/",
    pages = "15--24",
    ISBN = "979-8-89176-193-3",
    abstract = "This tutorial will present a systematic overview of recent advances in foundation models for embodied agents, covering three types of foundation models based on input and output: Large Language Models (LLMs), Vision-Language Models (VLMs), Vision-Language-Action Models (VLAs)"
}