@inproceedings{wang-etal-2026-learning-compositional,
    title = "Learning Compositional Spatio-Temporal Video Grounding with Synthetic Curriculum",
    author = "Wang, Xingjian  and
      Wang, Shijian  and
      Wang, Yibo  and
      Yu, Zihao  and
      Fu, Runhao  and
      Cheng, Xuelian  and
      Ge, Zongyuan",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.findings-emnlp.18/",
    pages = "355--370",
    ISBN = "979-8-89176-462-0"
}