Skip to main content

Optimisation and Customisation of Biomedical VLMs

Primary supervisor

Chris Bain

Research area

Digital Transformation

Medical VLMs - especially if they can be deployed inside "corporate firewalls" or under the direct governance of health services - potentially offer great advantages over general purpose VLMs for a range of reasons.

However there are fundamental questions over their performance and suitability for deployment inside healthcare, and as to whether they can compete given the mega-infrastructure and ability to upgrade that is available to the big players (OpenAI, Anthropic etc). 

There are many research questions  that can be addressed in this space, including - how do they perform vs general models, how does performance vary across medical topic domains, to what extent do fine tuning or RAG approaches improve performance,  how do medical VLMs compare to each other, what are the trade-offs between model size / accuracy / utility / deploy ability etc 

Required knowledge

Students with existing training in data science and AI will be better placed to complete this work (eg - UG Degree; Post Grad Cert/ Dipo or Masters).

This would need to be combined with some kind of previous training or experience in one of the health disciplines, pharmaceutical science or biomedicine. 


Learn more about minimum entry requirements.