@inproceedings{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",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.726/",
doi = "10.63317/37fzwjphsb9y",
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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="deichler-etal-2026-mm">
<titleInfo>
<title>MM-Conv: A Multimodal Dataset and Benchmark for Context-Aware Grounding in 3D Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Deichler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jim</namePart>
<namePart type="family">O’Regan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fethiye</namePart>
<namePart type="given">Irmak</namePart>
<namePart type="family">Dogan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Klezovich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lubos</namePart>
<namePart type="family">Marcinek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iolanda</namePart>
<namePart type="family">Leite</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonas</namePart>
<namePart type="family">Beskow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">deichler-etal-2026-mm</identifier>
<identifier type="doi">10.63317/37fzwjphsb9y</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.726/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>9240</start>
<end>9253</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MM-Conv: A Multimodal Dataset and Benchmark for Context-Aware Grounding in 3D Dialogue
%A Deichler, Anna
%A O’Regan, Jim
%A Dogan, Fethiye Irmak
%A Klezovich, Anna
%A Marcinek, Lubos
%A Leite, Iolanda
%A Beskow, Jonas
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F deichler-etal-2026-mm
%X 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.
%R 10.63317/37fzwjphsb9y
%U https://aclanthology.org/2026.lrec-1.726/
%U https://doi.org/10.63317/37fzwjphsb9y
%P 9240-9253
Markdown (Informal)
[MM-Conv: A Multimodal Dataset and Benchmark for Context-Aware Grounding in 3D Dialogue](https://aclanthology.org/2026.lrec-1.726/) (Deichler et al., LREC 2026)
ACL