<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-etal-2026-zzunlp">
    <titleInfo>
        <title>zzunlp at ClinicalSkillQA: Perceive-and-Plan with Decomposed In-Context Learning and Saliency-Guided Perception for Clinical Skill Keyframe Reordering</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Bin</namePart>
        <namePart type="family">Huang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yi</namePart>
        <namePart type="family">Luo</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zhontian</namePart>
        <namePart type="family">Hua</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Guanghui</namePart>
        <namePart type="family">Zhao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kaixuan</namePart>
        <namePart type="family">Yuan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kunli</namePart>
        <namePart type="family">Zhang</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 BioNLP 2026 (Shared Tasks)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Deepak</namePart>
            <namePart type="family">Gupta</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Dina</namePart>
            <namePart type="family">Demner-Fushman</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">979-8-89176-435-4</identifier>
    </relatedItem>
    <abstract>Multimodal Large Language Models (MLLMs)show strong medical visual understanding,however their capability for continuous per-ception in procedural clinical workflows re-mains underexplored. We present Perceive-and-Plan, a decomposed in-context learningparadigm for clinical skill keyframe reorder-ing. The method separates visual perceptionfrom temporal planning via two stages: (1)structured visual perception with saliency-guided Picture-in-Picture (PiP) compositionthat magnifies critical regions (head, chest)as color-coded insets, and (2) temporal rea-soning with chain-style self-verification viafresh conversation reset and visual-evidenceanchoring (BLS Rules R1-R11). Withoutparameter updates, our system scores 71.43overall (2nd place, ClinSkill QA 2026), with0.86 pairwise accuracy and 1.0 rationale cover-age. Structured prompting with visual saliencyguidance measurably improves MLLMs’ pro-cedural understanding.Our code is pub-lished at https://github.com/NanceTide/clinskillqa-perceive-and-plan.</abstract>
    <identifier type="citekey">huang-etal-2026-zzunlp</identifier>
    <location>
        <url>https://aclanthology.org/2026.bionlp-2.4/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>24</start>
            <end>32</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T zzunlp at ClinicalSkillQA: Perceive-and-Plan with Decomposed In-Context Learning and Saliency-Guided Perception for Clinical Skill Keyframe Reordering
%A Huang, Bin
%A Luo, Yi
%A Hua, Zhontian
%A Zhao, Guanghui
%A Yuan, Kaixuan
%A Zhang, Kunli
%Y Gupta, Deepak
%Y Demner-Fushman, Dina
%S Proceedings of the BioNLP 2026 (Shared Tasks)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-435-4
%F huang-etal-2026-zzunlp
%X Multimodal Large Language Models (MLLMs)show strong medical visual understanding,however their capability for continuous per-ception in procedural clinical workflows re-mains underexplored. We present Perceive-and-Plan, a decomposed in-context learningparadigm for clinical skill keyframe reorder-ing. The method separates visual perceptionfrom temporal planning via two stages: (1)structured visual perception with saliency-guided Picture-in-Picture (PiP) compositionthat magnifies critical regions (head, chest)as color-coded insets, and (2) temporal rea-soning with chain-style self-verification viafresh conversation reset and visual-evidenceanchoring (BLS Rules R1-R11). Withoutparameter updates, our system scores 71.43overall (2nd place, ClinSkill QA 2026), with0.86 pairwise accuracy and 1.0 rationale cover-age. Structured prompting with visual saliencyguidance measurably improves MLLMs’ pro-cedural understanding.Our code is pub-lished at https://github.com/NanceTide/clinskillqa-perceive-and-plan.
%U https://aclanthology.org/2026.bionlp-2.4/
%P 24-32

Markdown (Informal)

[zzunlp at ClinicalSkillQA: Perceive-and-Plan with Decomposed In-Context Learning and Saliency-Guided Perception for Clinical Skill Keyframe Reordering](https://aclanthology.org/2026.bionlp-2.4/) (Huang et al., BioNLP 2026)

• zzunlp at ClinicalSkillQA: Perceive-and-Plan with Decomposed In-Context Learning and Saliency-Guided Perception for Clinical Skill Keyframe Reordering (Huang et al., BioNLP 2026)

ACL

• Bin Huang, Yi Luo, Zhontian Hua, Guanghui Zhao, Kaixuan Yuan, and Kunli Zhang. 2026. zzunlp at ClinicalSkillQA: Perceive-and-Plan with Decomposed In-Context Learning and Saliency-Guided Perception for Clinical Skill Keyframe Reordering. In Proceedings of the BioNLP 2026 (Shared Tasks), pages 24–32, San Diego, California, USA. Association for Computational Linguistics.