OpenMedQ: Broad Open Pretraining for Medical Vision-Language Models

Ibrahim Gulluk, Max Van Puyvelde, Olivier Gevaert
6/11/2026
cs.AIcs.CVcs.LG

No confident code implementation found for this paper. 1 possible match can be shown below.

Abstract

We present OpenMedQ, a medical vision-language model pretrained on the broadest fully-open medical mix to date: 14 datasets totaling ~3.35M pretraining samples spanning pathology, radiology, microscopy, and text-only clinical QA. OpenMedQ reaches state-of-the-art BLEU-1 on PathVQA (75.9), beating Med-PaLM M variants up to 562B parameters (~80x larger), and matches the best reported VQA-MED BLEU-1 (64.5). Its vision encoder, transferred to 8 unseen medical classification benchmarks under an identical downstream recipe, obtains the highest average macro-F1 (0.757) among BiomedCLIP (0.745), PMC-CLIP (0.745), PubMedCLIP (0.746), and a from-scratch baseline (0.616). We release our code and an interactive demo is publicly available as a reproducible baseline for the community.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 1 weaker match is hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

A Reality Check of Vision-Language Pre-training in Radiology: Have We Progressed Using Text?

89% match1 repo42025

MedBLIP: Bootstrapping Language-Image Pre-training from 3D Medical Images and Texts

89% match1 repo572023

Scaling Down to Scale Up: Towards Operationally-Efficient and Deployable Clinical Models via Cross-Modal Low-Rank Adaptation for Medical Vision-Language Models

88% match2025

MultiMedEval: A Benchmark and a Toolkit for Evaluating Medical Vision-Language Models

88% match1 repo892024

Better Tokens for Better 3D: Advancing Vision-Language Modeling in 3D Medical Imaging

88% match1 repo402025

From Panel to Pixel: Zoom-In Vision-Language Pretraining from Biomedical Scientific Literature

88% match2025

Cite this paper

@article{gulluk2026openmedq,
  title  = {OpenMedQ: Broad Open Pretraining for Medical Vision-Language Models},
  author = {Ibrahim Gulluk and Max Van Puyvelde and Olivier Gevaert},
  year   = {2026},
  eprint = {2606.12953},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2606.12953v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2606.12953.svg)](https://codeofpaper.com/paper/2606.12953)

Discussion