<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xueyun-etal-2026-roma">
    <titleInfo>
        <title>ROMA: Real-time Omni-Multimodal Assistant with Interactive Streaming Understanding</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Tian</namePart>
        <namePart type="family">Xueyun</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wei</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Bingbing</namePart>
        <namePart type="family">Xu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Heng</namePart>
        <namePart type="family">Dong</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yuanzhuo</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Huawei</namePart>
        <namePart type="family">Shen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: ACL 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Maria</namePart>
            <namePart type="family">Liakata</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Viviane</namePart>
            <namePart type="given">P</namePart>
            <namePart type="family">Moreira</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jiajun</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Jurgens</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">San Diego, California, United States</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-395-1</identifier>
    </relatedItem>
    <abstract>Recent Omni-multimodal Large Language Models show promise in unified audio, vision, and text modeling. However, streaming audio-video understanding remains challenging, as existing approaches suffer from disjointed capabilities: they typically exhibit incomplete modality support or lack autonomous proactive monitoring. To address this, we present ROMA, **a real-time omni-multimodal assistant for unified reactive and proactive interaction**. ROMA processes continuous inputs as synchronized multimodal units, aligning dense audio with discrete video frames to handle granularity mismatches. For online decision-making, we introduce a lightweight *speak head* that decouples response initiation from generation to ensure precise triggering without task conflict. We train ROMA with a curated streaming dataset and a two-stage curriculum that progressively optimizes for streaming format adaptation and proactive responsiveness. To standardize the fragmented evaluation landscape, we reorganize diverse benchmarks into a unified suite covering both proactive (alert, narration) and reactive (QA) settings. Extensive experiments across 12 benchmarks demonstrate ROMA achieves state-of-the-art performance on proactive tasks while competitive in reactive settings, validating its robustness in unified real-time omni-multimodal understanding. Code and benchmark are available [here](https://eureka-maggie.github.io/ROMA_show/).</abstract>
    <identifier type="citekey">xueyun-etal-2026-roma</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-acl.1153/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>23018</start>
            <end>23039</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T ROMA: Real-time Omni-Multimodal Assistant with Interactive Streaming Understanding
%A Xueyun, Tian
%A Li, Wei
%A Xu, Bingbing
%A Dong, Heng
%A Wang, Yuanzhuo
%A Shen, Huawei
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F xueyun-etal-2026-roma
%X Recent Omni-multimodal Large Language Models show promise in unified audio, vision, and text modeling. However, streaming audio-video understanding remains challenging, as existing approaches suffer from disjointed capabilities: they typically exhibit incomplete modality support or lack autonomous proactive monitoring. To address this, we present ROMA, **a real-time omni-multimodal assistant for unified reactive and proactive interaction**. ROMA processes continuous inputs as synchronized multimodal units, aligning dense audio with discrete video frames to handle granularity mismatches. For online decision-making, we introduce a lightweight *speak head* that decouples response initiation from generation to ensure precise triggering without task conflict. We train ROMA with a curated streaming dataset and a two-stage curriculum that progressively optimizes for streaming format adaptation and proactive responsiveness. To standardize the fragmented evaluation landscape, we reorganize diverse benchmarks into a unified suite covering both proactive (alert, narration) and reactive (QA) settings. Extensive experiments across 12 benchmarks demonstrate ROMA achieves state-of-the-art performance on proactive tasks while competitive in reactive settings, validating its robustness in unified real-time omni-multimodal understanding. Code and benchmark are available [here](https://eureka-maggie.github.io/ROMA_show/).
%U https://aclanthology.org/2026.findings-acl.1153/
%P 23018-23039

Markdown (Informal)

[ROMA: Real-time Omni-Multimodal Assistant with Interactive Streaming Understanding](https://aclanthology.org/2026.findings-acl.1153/) (Xueyun et al., Findings 2026)

• ROMA: Real-time Omni-Multimodal Assistant with Interactive Streaming Understanding (Xueyun et al., Findings 2026)

ACL

• Tian Xueyun, Wei Li, Bingbing Xu, Heng Dong, Yuanzhuo Wang, and Huawei Shen. 2026. ROMA: Real-time Omni-Multimodal Assistant with Interactive Streaming Understanding. In Findings of the Association for Computational Linguistics: ACL 2026, pages 23018–23039, San Diego, California, United States. Association for Computational Linguistics.