@inproceedings{huang-etal-2026-zzunlp,
    title = "zzunlp at {C}linical{S}kill{QA}: Perceive-and-Plan with Decomposed In-Context Learning and Saliency-Guided Perception for Clinical Skill Keyframe Reordering",
    author = "Huang, Bin  and
      Luo, Yi  and
      Hua, Zhontian  and
      Zhao, Guanghui  and
      Yuan, Kaixuan  and
      Zhang, Kunli",
    editor = "Gupta, Deepak  and
      Demner-Fushman, Dina",
    booktitle = "Proceedings of the {B}io{NLP} 2026 (Shared Tasks)",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.bionlp-2.4/",
    pages = "24--32",
    ISBN = "979-8-89176-435-4",
    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."
}