<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2026-med-banana">
    <titleInfo>
        <title>Med-Banana: Learning Quality-Controlled Medical Image Editing from Success-and-Failure Trajectories</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Zhihui</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Qingyuan</namePart>
        <namePart type="family">Lei</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kai</namePart>
        <namePart type="family">He</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yanrui</namePart>
        <namePart type="family">Du</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mengling</namePart>
        <namePart type="family">Feng</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>Text-guided medical image editing must satisfy the requested pathology while preserving anatomy, modality-specific appearance, and clinical plausibility. However, existing datasets largely supervise editors with final accepted edits and discard the failed attempts produced during generation. We argue that these failures provide essential supervision for quality control: they specify what should be rejected, why an edit is medically or visually invalid, and how the instruction should be revised. We present Med-Banana, a trajectory-supervised framework for quality-controlled medical image editing. We introduce Med-Banana-80K, a large-scale resource of success-and-failure editing trajectories with candidate images, verification outcomes, rejection reasons, and prompt refinements. Building on it, Med-Banana jointly trains an editor, verifier, and refiner, enabling edit–verify–refine inference from accepted and rejected attempts. Experiments across MLLM judges, blind expert assessment, source-preservation and real–synthetic separability probes demonstrate consistent improvements over open medical image editors. Code and data are publicly available.</abstract>
    <identifier type="citekey">chen-etal-2026-med-banana</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.1260/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>26633</start>
            <end>26652</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Med-Banana: Learning Quality-Controlled Medical Image Editing from Success-and-Failure Trajectories
%A Chen, Zhihui
%A Lei, Qingyuan
%A He, Kai
%A Du, Yanrui
%A Feng, Mengling
%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 chen-etal-2026-med-banana
%X Text-guided medical image editing must satisfy the requested pathology while preserving anatomy, modality-specific appearance, and clinical plausibility. However, existing datasets largely supervise editors with final accepted edits and discard the failed attempts produced during generation. We argue that these failures provide essential supervision for quality control: they specify what should be rejected, why an edit is medically or visually invalid, and how the instruction should be revised. We present Med-Banana, a trajectory-supervised framework for quality-controlled medical image editing. We introduce Med-Banana-80K, a large-scale resource of success-and-failure editing trajectories with candidate images, verification outcomes, rejection reasons, and prompt refinements. Building on it, Med-Banana jointly trains an editor, verifier, and refiner, enabling edit–verify–refine inference from accepted and rejected attempts. Experiments across MLLM judges, blind expert assessment, source-preservation and real–synthetic separability probes demonstrate consistent improvements over open medical image editors. Code and data are publicly available.
%U https://aclanthology.org/2026.findings-emnlp.1260/
%P 26633-26652

Markdown (Informal)

[Med-Banana: Learning Quality-Controlled Medical Image Editing from Success-and-Failure Trajectories](https://aclanthology.org/2026.findings-emnlp.1260/) (Chen et al., Findings 2026)

• Med-Banana: Learning Quality-Controlled Medical Image Editing from Success-and-Failure Trajectories (Chen et al., Findings 2026)

ACL

• Zhihui Chen, Qingyuan Lei, Kai He, Yanrui Du, and Mengling Feng. 2026. Med-Banana: Learning Quality-Controlled Medical Image Editing from Success-and-Failure Trajectories. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 26633–26652, Budapest, Hungary. Association for Computational Linguistics.