<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2026-learning-reason">
    <titleInfo>
        <title>Learning to Reason Before Masking for Referring Audio-Visual Segmentation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Zhixuan</namePart>
        <namePart type="family">Wu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ye</namePart>
        <namePart type="family">Ni</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yiming</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wenyuan</namePart>
        <namePart type="family">Gu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Bo</namePart>
        <namePart type="family">Cheng</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>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</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">979-8-89176-459-0</identifier>
    </relatedItem>
    <abstract>Existing referring Audio-Visual Segmentation (Ref-AVS) benchmarks primarily focus on explicit expressions whose referents can be resolved through direct visual, acoustic, or linguistic correspondence. Consequently, they provide limited coverage of implicit references that require multi-step reasoning over multimodal evidence. To bridge this gap, we introduce **Reasoning Ref-AVS**, a new task that requires models to infer the referred object from audio-visual-language cues before generating its segmentation mask. We further construct **ReAVS**, a comprehensive dataset with manually annotated referring expressions, multimodal cues, object masks, and reasoning chains, covering diverse reasoning spanning diverse reasoning patterns. Evaluations of representative Ref-AVS models on ReAVS reveal substantial performance degradation when direct cross-modal correspondence is insufficient, exposing a clear gap between multimodal recognition and referent reasoning. Motivated by these challenges, we propose **Re2Seg**, an omni-modal framework that performs object-centric evidence encoding, multi-hop reasoning, and reasoning-conditioned mask decoding. Experiments demonstrate that Re2Seg achieves stronger segmentation performance under reasoning-intensive references and provides interpretable object-inference traces. These results highlight the importance of learning to reason before masking for bridging the gap between multimodal recognition and referring segmentation.</abstract>
    <identifier type="citekey">wu-etal-2026-learning-reason</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.238/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>5446</start>
            <end>5464</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Learning to Reason Before Masking for Referring Audio-Visual Segmentation
%A Wu, Zhixuan
%A Ni, Ye
%A Chen, Yiming
%A Gu, Wenyuan
%A Cheng, Bo
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F wu-etal-2026-learning-reason
%X Existing referring Audio-Visual Segmentation (Ref-AVS) benchmarks primarily focus on explicit expressions whose referents can be resolved through direct visual, acoustic, or linguistic correspondence. Consequently, they provide limited coverage of implicit references that require multi-step reasoning over multimodal evidence. To bridge this gap, we introduce **Reasoning Ref-AVS**, a new task that requires models to infer the referred object from audio-visual-language cues before generating its segmentation mask. We further construct **ReAVS**, a comprehensive dataset with manually annotated referring expressions, multimodal cues, object masks, and reasoning chains, covering diverse reasoning spanning diverse reasoning patterns. Evaluations of representative Ref-AVS models on ReAVS reveal substantial performance degradation when direct cross-modal correspondence is insufficient, exposing a clear gap between multimodal recognition and referent reasoning. Motivated by these challenges, we propose **Re2Seg**, an omni-modal framework that performs object-centric evidence encoding, multi-hop reasoning, and reasoning-conditioned mask decoding. Experiments demonstrate that Re2Seg achieves stronger segmentation performance under reasoning-intensive references and provides interpretable object-inference traces. These results highlight the importance of learning to reason before masking for bridging the gap between multimodal recognition and referring segmentation.
%U https://aclanthology.org/2026.emnlp-main.238/
%P 5446-5464

Markdown (Informal)

[Learning to Reason Before Masking for Referring Audio-Visual Segmentation](https://aclanthology.org/2026.emnlp-main.238/) (Wu et al., EMNLP 2026)

• Learning to Reason Before Masking for Referring Audio-Visual Segmentation (Wu et al., EMNLP 2026)

ACL

• Zhixuan Wu, Ye Ni, Yiming Chen, Wenyuan Gu, and Bo Cheng. 2026. Learning to Reason Before Masking for Referring Audio-Visual Segmentation. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 5446–5464, Budapest, Hungary. Association for Computational Linguistics.