<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="feng-etal-2025-masked">
    <titleInfo>
        <title>Masked Diffusion Captioning for Visual Feature Learning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Chao</namePart>
        <namePart type="family">Feng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zihao</namePart>
        <namePart type="family">Wei</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Andrew</namePart>
        <namePart type="family">Owens</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2025</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Christos</namePart>
            <namePart type="family">Christodoulopoulos</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Tanmoy</namePart>
            <namePart type="family">Chakraborty</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Carolyn</namePart>
            <namePart type="family">Rose</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Violet</namePart>
            <namePart type="family">Peng</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Suzhou, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-335-7</identifier>
    </relatedItem>
    <abstract>We learn visual features by captioning images with an image-conditioned masked diffusion language model, a formulation we call masked diffusion captioning (MDC). During training, text tokens in each image–caption pair are masked at a randomly chosen ratio, and a decoder conditioned on visual features is trained to reconstruct the original text. After training, the learned visual features can be applied to downstream vision tasks. Unlike autoregressive captioning, the strength of the visual learning signal in MDC does not depend on each token’s position in the sequence, reducing the need for auxiliary objectives. Linear probing experiments across a variety of academic-scale models and datasets show that the learned visual features are competitive with those produced by autoregressive and contrastive approaches.</abstract>
    <identifier type="citekey">feng-etal-2025-masked</identifier>
    <location>
        <url>https://aclanthology.org/2025.findings-emnlp.1376/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>25247</start>
            <end>25263</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Masked Diffusion Captioning for Visual Feature Learning
%A Feng, Chao
%A Wei, Zihao
%A Owens, Andrew
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F feng-etal-2025-masked
%X We learn visual features by captioning images with an image-conditioned masked diffusion language model, a formulation we call masked diffusion captioning (MDC). During training, text tokens in each image–caption pair are masked at a randomly chosen ratio, and a decoder conditioned on visual features is trained to reconstruct the original text. After training, the learned visual features can be applied to downstream vision tasks. Unlike autoregressive captioning, the strength of the visual learning signal in MDC does not depend on each token’s position in the sequence, reducing the need for auxiliary objectives. Linear probing experiments across a variety of academic-scale models and datasets show that the learned visual features are competitive with those produced by autoregressive and contrastive approaches.
%U https://aclanthology.org/2025.findings-emnlp.1376/
%P 25247-25263

Markdown (Informal)

[Masked Diffusion Captioning for Visual Feature Learning](https://aclanthology.org/2025.findings-emnlp.1376/) (Feng et al., Findings 2025)

• Masked Diffusion Captioning for Visual Feature Learning (Feng et al., Findings 2025)

ACL

• Chao Feng, Zihao Wei, and Andrew Owens. 2025. Masked Diffusion Captioning for Visual Feature Learning. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 25247–25263, Suzhou, China. Association for Computational Linguistics.