Oriel — AI & technology worth noticing, every day.

MedICL: Modality-Anatomy-Aware Visual In-Context Learning for Medical Visual Question Answering

Paper · https://arxiv.org/abs/2611.00067

arXiv:2611.00067v1 Announce Type: new Abstract: Training-free adaptation of medical vision-language models (LVLMs) is a deployment requirement, yet visual in-context learning (ICL) injects modality- and style-mismatched demonstrations into medical contexts, teaching a frozen model the wrong answering style. We present MedICL, which curates demonstrations instead of retraining the model. MADS selects modality-anatomy aligned demonstrations that cover complementary interpretation dimensions; W2C curates them with weak retrieval signals and a strong verification vote that checks demonstrations rather than the model's own outputs; ECC answers with W anchored demonstration sets, aggregates by abnormality-aware signatures, and re-answers once on conflict. On VQA-RAD, SLAKE, and PathVQA under the LLaVA-Med zero-shot protocol, MedICL improves the strongest zero-shot baseline by +11 - +14 points on open-ended and +7 - +14 on closed questions, recovers 71% of fine-tuned open-ended performance on VQA-RAD at zero training cost, and stays robust to shifted or corrupted demonstration banks.

First seen by Oriel on .

No saved summary available.

Aliases

SourceExternal IDURL
arXiv AI Papersoai:arXiv.org:2611.00067v1https://arxiv.org/abs/2611.00067 Read discussion