Scaling up biomedical vision-language models: Fine-tuning, instruction tuning, and multi-modal learning
- 24 October 2025
- journal article
- Published by Elsevier in Journal of Biomedical Informatics
- Vol. 171, 104946
Abstract
No abstract availableKeywords
All Related Versions
Funding Information
- Advanced Research Projects Agency for Health
- National Institute of Allergy and Infectious Diseases (R01AI172875)
- National Institutes of Health National Cancer Institute
- Patient-Centered Outcomes Research Institute (ME-2023C3-35934)
- Patient-Centered Outcomes Research Institute (ME-2018C3-14754)
- Clinical and Translational Science Institute, University of Florida
- NVIDIA AI Technology Center, University of Florida
- Nvidia
- National Science Foundation (ATD-2427915)
- National Science Foundation (CRII-2246067)
- National Heart Lung and Blood Institute (R01HL169277)
- National Library of Medicine
- National Institute on Aging
- National Institute on Drug Abuse (R01DA057886)
- National Institute on Drug Abuse (R01DA050676)
This publication has 34 references indexed in Scilit:
- Benchmarking large language models for biomedical natural language processing applications and recommendationsNature Communications, 2025
- Toward expert-level medical question answering with large language modelsNature Medicine, 2025
- A generalist vision–language foundation model for diverse biomedical tasksNature Medicine, 2024
- Adapted large language models can outperform medical experts in clinical text summarizationNature Medicine, 2024
- Large language models in medicineNature Medicine, 2023
- Large language models encode clinical knowledgeNature, 2023
- MedViT: A robust vision transformer for generalized medical image classificationComputers in Biology and Medicine, 2023
- MedMNIST v2 - A large-scale lightweight benchmark for 2D and 3D biomedical image classificationScientific Data, 2023
- Transformers in medical image analysisIntelligent Medicine, 2022
- Question-driven summarization of answers to consumer health questionsScientific Data, 2020