Saved in:
Bibliographic Details
Main Authors: Zhao, Wenkai, Wang, Zipei, Fang, Mengjie, Dong, Di, Tian, Jie, Zhang, Lingwei
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.27737
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914430103584768
author Zhao, Wenkai
Wang, Zipei
Fang, Mengjie
Dong, Di
Tian, Jie
Zhang, Lingwei
author_facet Zhao, Wenkai
Wang, Zipei
Fang, Mengjie
Dong, Di
Tian, Jie
Zhang, Lingwei
contents General Multimodal Large Language Models (MLLMs) often underperform in capturing domain-specific nuances in medical diagnosis, trailing behind fully supervised baselines. Although fine-tuning provides a remedy, the high costs of expert annotation and massive computational overhead limit its scalability. To bridge this gap without updating the weights of the pre-trained backbone of the MLLM, we propose a Clinician Mimetic Workflow. This is a novel In-Context Learning (ICL) framework designed to synergize Discriminative Exemplar Coreset Selection (DECS) and Self-Refined Experience Summarization (SRES). Specifically, DECS simulates a clinician's ability to reference "anchor cases" by selecting discriminative visual coresets from noisy data at the computational level; meanwhile, SRES mimics the cognition and reflection in clinical diagnosis by distilling diverse rollouts into a dynamic textual Experience Bank. Extensive evaluation across all 12 datasets of the MedMNIST 2D benchmark demonstrates that our method outperforms zero-shot general and medical MLLMs. Simultaneously, it achieves performance levels comparable to fully supervised vision models and domain-specific fine-tuned MLLMs, setting a new benchmark for parameter-efficient medical in-context learning. Our code is available at an anonymous repository: https://anonymous.4open.science/r/Synergizing-Discriminative-Exemplars-and-Self-Refined-Experience-ED74.
format Preprint
id arxiv_https___arxiv_org_abs_2603_27737
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Synergizing Discriminative Exemplars and Self-Refined Experience for MLLM-based In-Context Learning in Medical Diagnosis
Zhao, Wenkai
Wang, Zipei
Fang, Mengjie
Dong, Di
Tian, Jie
Zhang, Lingwei
Computer Vision and Pattern Recognition
General Multimodal Large Language Models (MLLMs) often underperform in capturing domain-specific nuances in medical diagnosis, trailing behind fully supervised baselines. Although fine-tuning provides a remedy, the high costs of expert annotation and massive computational overhead limit its scalability. To bridge this gap without updating the weights of the pre-trained backbone of the MLLM, we propose a Clinician Mimetic Workflow. This is a novel In-Context Learning (ICL) framework designed to synergize Discriminative Exemplar Coreset Selection (DECS) and Self-Refined Experience Summarization (SRES). Specifically, DECS simulates a clinician's ability to reference "anchor cases" by selecting discriminative visual coresets from noisy data at the computational level; meanwhile, SRES mimics the cognition and reflection in clinical diagnosis by distilling diverse rollouts into a dynamic textual Experience Bank. Extensive evaluation across all 12 datasets of the MedMNIST 2D benchmark demonstrates that our method outperforms zero-shot general and medical MLLMs. Simultaneously, it achieves performance levels comparable to fully supervised vision models and domain-specific fine-tuned MLLMs, setting a new benchmark for parameter-efficient medical in-context learning. Our code is available at an anonymous repository: https://anonymous.4open.science/r/Synergizing-Discriminative-Exemplars-and-Self-Refined-Experience-ED74.
title Synergizing Discriminative Exemplars and Self-Refined Experience for MLLM-based In-Context Learning in Medical Diagnosis
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.27737