@inproceedings{xu-etal-2026-human,
    title = "Human-Perception-Aware but Not Yet Physically Grounded: Strengths and Failure Modes of Frontier Multimodal {LLM}s and the {G}round{VQA} Benchmark",
    author = "Xu, Qinwu  and
      Liu, Xin  and
      Jiang, Yifan",
    editor = "Wang, Yimu  and
      Choi, Yee Man  and
      Wu, Di  and
      Ouyang, Siqi  and
      Azadani, Mozhgan Nasr  and
      Fung, Yi R. (May)",
    booktitle = "Proceedings of the 1st Workshop on Grounding Language Models: Learning Faithfully and Efficiently ({G}round{LM} 2026)",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.groundlm-1.55/",
    pages = "743--750",
    ISBN = "979-8-89176-478-1"
}