@inproceedings{sun-etal-2025-emma,
    title = "Emma-{X}: An Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial Reasoning",
    author = "Sun, Qi  and
      Hong, Pengfei  and
      Pala, Tej Deep  and
      Toh, Vernon  and
      Tan, U-Xuan  and
      Ghosal, Deepanway  and
      Poria, Soujanya",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/acl25-workshop-ingestion/2025.acl-long.695/",
    pages = "14199--14214",
    ISBN = "979-8-89176-251-0"
}