@inproceedings{ding-etal-2026-inter,
    title = "{I}nter-3{D} {VQA}: A Roadside Multimodal Benchmark for 3{D} Spatiotemporally Grounded Visual Question Answering",
    author = "Ding, Shaozu  and
      Song, Linan  and
      Suo, Dajiang",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.emnlp-main.1518/",
    pages = "34661--34686",
    ISBN = "979-8-89176-459-0"
}