@article{deichler-etal-2026-mm,
    title = "{MM}-Conv: A Multimodal Dataset and Benchmark for Context-Aware Grounding in 3{D} Dialogue",
    author = "Deichler, Anna  and
      O'Regan, Jim  and
      Dogan, Fethiye Irmak  and
      Klezovich, Anna  and
      Marcinek, Lubos  and
      Leite, Iolanda  and
      Beskow, Jonas",
    editor = "Piperidis, Stelios  and
      Bel, N{\'u}ria  and
      van den Heuvel, Henk  and
      Ide, Nancy  and
      Krek, Simon  and
      Toral, Antonio",
    journal = "International Conference on Language Resources and Evaluation",
    volume = "main",
    month = may,
    year = "2026",
    address = "Palma de Mallorca, Spain",
    publisher = "ELRA Language Resource Association",
    url = "https://preview.aclanthology.org/ingest-lrec/2026.lrec-main.726/",
    pages = "9240--9253",
    abstract = "Grounding language in the physical world requires AI systems to interpret references that emerge dynamically during conversation. While current vision-language models (VLMs) excel at static image tasks, they struggle to resolve ambiguous expressions in spontaneous, multi-turn dialogue. We address this gap by introducing MM-Conv{---}speak, point, look{---}a benchmark for referential communication in dynamic 3D environments, built from 6.7 hours of egocentric VR interaction with synchronized speech, motion, gaze, and 3D scene geometry. The benchmark includes over 4,200 manually verified referring expressions spanning full, partitive, and pronominal types, enabling systematic evaluation of multimodal reference resolution."
}