<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shin-2026-zipfian">
    <titleInfo>
        <title>A Zipfian Analysis of Visual Token Distributions for AI-Generated Images</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Andrew</namePart>
        <namePart type="family">Shin</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>Proceedings of the 4th Workshop on Advances in Language and Vision Research (ALVR)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Qianqi</namePart>
            <namePart type="family">Yan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Syrielle</namePart>
            <namePart type="family">Montariol</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yue</namePart>
            <namePart type="family">Fan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jing</namePart>
            <namePart type="family">Gu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jiayi</namePart>
            <namePart type="family">Pan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Manling</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Parisa</namePart>
            <namePart type="family">Kordjamshidi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Alane</namePart>
            <namePart type="family">Suhr</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Xin</namePart>
            <namePart type="given">Eric</namePart>
            <namePart type="family">Wang</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, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-398-2</identifier>
    </relatedItem>
    <abstract>The rapid evolution of text-to-image generation has blurred the perceptual boundary between natural and synthetic imagery. However, it remains questionable whether the statistical structure of generated visual content mirrors the information density of the physical visual world. Drawing upon principles from statistical linguistics, this study investigates the visual language of generative models through the lens of Zipfian dynamics. By analyzing a large-scale corpus of real and synthetic images, we uncover a fundamental divergence between visual syntax and semantics. We find that while generative models have successfully replicated the low-level physics of light, their high-level texture vocabulary exhibits distinct statistical signatures. Our analysis reveals a spectrum of entropy, identifying architectural fingerprints unique to each model. Furthermore, we investigate the relation ship between generated images and prompt complexity, and find that increasing the semantic specificity of text prompts systematically degrades the statistical realism of the generated output.</abstract>
    <identifier type="citekey">shin-2026-zipfian</identifier>
    <location>
        <url>https://aclanthology.org/2026.alvr-main.2/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>13</start>
            <end>17</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T A Zipfian Analysis of Visual Token Distributions for AI-Generated Images
%A Shin, Andrew
%Y Yan, Qianqi
%Y Montariol, Syrielle
%Y Fan, Yue
%Y Gu, Jing
%Y Pan, Jiayi
%Y Li, Manling
%Y Kordjamshidi, Parisa
%Y Suhr, Alane
%Y Wang, Xin Eric
%S Proceedings of the 4th Workshop on Advances in Language and Vision Research (ALVR)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-398-2
%F shin-2026-zipfian
%X The rapid evolution of text-to-image generation has blurred the perceptual boundary between natural and synthetic imagery. However, it remains questionable whether the statistical structure of generated visual content mirrors the information density of the physical visual world. Drawing upon principles from statistical linguistics, this study investigates the visual language of generative models through the lens of Zipfian dynamics. By analyzing a large-scale corpus of real and synthetic images, we uncover a fundamental divergence between visual syntax and semantics. We find that while generative models have successfully replicated the low-level physics of light, their high-level texture vocabulary exhibits distinct statistical signatures. Our analysis reveals a spectrum of entropy, identifying architectural fingerprints unique to each model. Furthermore, we investigate the relation ship between generated images and prompt complexity, and find that increasing the semantic specificity of text prompts systematically degrades the statistical realism of the generated output.
%U https://aclanthology.org/2026.alvr-main.2/
%P 13-17

Markdown (Informal)

[A Zipfian Analysis of Visual Token Distributions for AI-Generated Images](https://aclanthology.org/2026.alvr-main.2/) (Shin, ALVR 2026)

• A Zipfian Analysis of Visual Token Distributions for AI-Generated Images (Shin, ALVR 2026)

ACL

• Andrew Shin. 2026. A Zipfian Analysis of Visual Token Distributions for AI-Generated Images. In Proceedings of the 4th Workshop on Advances in Language and Vision Research (ALVR), pages 13–17, San Diego, California, USA. Association for Computational Linguistics.