<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ryumina-etal-2026-tacme">
    <titleInfo>
        <title>TACME: Task-Aware Cross-Modal Experts for Disjoint-Corpus Multimodal Behavioral Understanding</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Elena</namePart>
        <namePart type="family">Ryumina</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Alexandr</namePart>
        <namePart type="family">Axyonov</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dmitry</namePart>
        <namePart type="family">Ryumin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-462-0</identifier>
    </relatedItem>
    <abstract>Multimodal behavioral analysis is typically studied using separate task-specific corpora. Practical applications, however, would benefit from unified models that can support several behavioral predictions despite fragmented supervision. We study this problem as disjoint-corpus multimodal multi-task learning across emotion recognition on CMU-MOSEI, apparent Big Five personality assessment on ChaLearn FIv2, and ambivalence recognition on BAH. We propose Task-Aware Cross-Modal Experts (TACME), a multimodal fusion model with a shared bank of directed cross-modal Transformer experts and task-specific expert gates. Each expert models one ordered modality interaction, while task-specific gates select different expert mixtures for different behavioral tasks. We further adapt feature- and prediction-level flow-matching regularization to this disjoint-corpus behavioral setting and propose a Progress-Aware Gradient Balancing (PAGB) multi-task learning strategy for heterogeneous task optimization. Across three independent corpora and six task-specific metrics, TACME with PAGB and feature- and prediction-level flow-matching regularization achieves the best average rank of 1.00 among the compared multimodal fusion models. Although single-task TACME is stronger on the source-corpus metrics, the multi-task TACME model improves zero-shot unweighted average recall (UAR) on the unseen MELD test set from 28.9% to 35.9%, demonstrating improved generalization to unseen data.</abstract>
    <identifier type="citekey">ryumina-etal-2026-tacme</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.957/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>20210</start>
            <end>20234</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T TACME: Task-Aware Cross-Modal Experts for Disjoint-Corpus Multimodal Behavioral Understanding
%A Ryumina, Elena
%A Axyonov, Alexandr
%A Ryumin, Dmitry
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F ryumina-etal-2026-tacme
%X Multimodal behavioral analysis is typically studied using separate task-specific corpora. Practical applications, however, would benefit from unified models that can support several behavioral predictions despite fragmented supervision. We study this problem as disjoint-corpus multimodal multi-task learning across emotion recognition on CMU-MOSEI, apparent Big Five personality assessment on ChaLearn FIv2, and ambivalence recognition on BAH. We propose Task-Aware Cross-Modal Experts (TACME), a multimodal fusion model with a shared bank of directed cross-modal Transformer experts and task-specific expert gates. Each expert models one ordered modality interaction, while task-specific gates select different expert mixtures for different behavioral tasks. We further adapt feature- and prediction-level flow-matching regularization to this disjoint-corpus behavioral setting and propose a Progress-Aware Gradient Balancing (PAGB) multi-task learning strategy for heterogeneous task optimization. Across three independent corpora and six task-specific metrics, TACME with PAGB and feature- and prediction-level flow-matching regularization achieves the best average rank of 1.00 among the compared multimodal fusion models. Although single-task TACME is stronger on the source-corpus metrics, the multi-task TACME model improves zero-shot unweighted average recall (UAR) on the unseen MELD test set from 28.9% to 35.9%, demonstrating improved generalization to unseen data.
%U https://aclanthology.org/2026.findings-emnlp.957/
%P 20210-20234

Markdown (Informal)

[TACME: Task-Aware Cross-Modal Experts for Disjoint-Corpus Multimodal Behavioral Understanding](https://aclanthology.org/2026.findings-emnlp.957/) (Ryumina et al., Findings 2026)

• TACME: Task-Aware Cross-Modal Experts for Disjoint-Corpus Multimodal Behavioral Understanding (Ryumina et al., Findings 2026)

ACL

• Elena Ryumina, Alexandr Axyonov, and Dmitry Ryumin. 2026. TACME: Task-Aware Cross-Modal Experts for Disjoint-Corpus Multimodal Behavioral Understanding. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 20210–20234, Budapest, Hungary. Association for Computational Linguistics.