<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="you-etal-2026-llada">
    <titleInfo>
        <title>LLaDA-o: An Effective and Length-Adaptive Omni Diffusion Model</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Zebin</namePart>
        <namePart type="family">You</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiaolu</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jun</namePart>
        <namePart type="family">Zhou</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chongxuan</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ji-Rong</namePart>
        <namePart type="family">Wen</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>We present **LLaDA-o**, an effective and length-adaptive omni diffusion model for multimodal understanding and generation. LLaDA-o is built on a Mixture of Diffusion (MoD) framework that decouples discrete masked diffusion for text understanding and continuous diffusion for visual generation, while coupling them through a shared, simple, and efficient attention backbone that reduces redundant computation for fixed conditions. Building on MoD, we further introduce a data-centric length adaptation strategy that enables flexible-length decoding in multimodal settings without architectural changes. Extensive experiments show that LLaDA-o achieves strong performance on multimodal understanding and generation benchmarks, reaching 87.04 on DPG-Bench and 0.86 on GenEval. To support future work on omni-diffusion models, we release the model and training/evaluation code at https://github.com/ML-GSAI/LLaDA-o.</abstract>
    <identifier type="citekey">you-etal-2026-llada</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.221/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>4645</start>
            <end>4664</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T LLaDA-o: An Effective and Length-Adaptive Omni Diffusion Model
%A You, Zebin
%A Zhang, Xiaolu
%A Zhou, Jun
%A Li, Chongxuan
%A Wen, Ji-Rong
%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 you-etal-2026-llada
%X We present **LLaDA-o**, an effective and length-adaptive omni diffusion model for multimodal understanding and generation. LLaDA-o is built on a Mixture of Diffusion (MoD) framework that decouples discrete masked diffusion for text understanding and continuous diffusion for visual generation, while coupling them through a shared, simple, and efficient attention backbone that reduces redundant computation for fixed conditions. Building on MoD, we further introduce a data-centric length adaptation strategy that enables flexible-length decoding in multimodal settings without architectural changes. Extensive experiments show that LLaDA-o achieves strong performance on multimodal understanding and generation benchmarks, reaching 87.04 on DPG-Bench and 0.86 on GenEval. To support future work on omni-diffusion models, we release the model and training/evaluation code at https://github.com/ML-GSAI/LLaDA-o.
%U https://aclanthology.org/2026.findings-emnlp.221/
%P 4645-4664

Markdown (Informal)

[LLaDA-o: An Effective and Length-Adaptive Omni Diffusion Model](https://aclanthology.org/2026.findings-emnlp.221/) (You et al., Findings 2026)

• LLaDA-o: An Effective and Length-Adaptive Omni Diffusion Model (You et al., Findings 2026)

ACL

• Zebin You, Xiaolu Zhang, Jun Zhou, Chongxuan Li, and Ji-Rong Wen. 2026. LLaDA-o: An Effective and Length-Adaptive Omni Diffusion Model. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 4645–4664, Budapest, Hungary. Association for Computational Linguistics.