LUMA

LUMALUMALUMA
  • Home
  • RESEARCH
    • Overview
    • Generative Digital Twins
    • Agentic Discovery
    • Computational Health
  • PUBLICATIONS
  • PEOPLE
  • NEWS
  • Join us
  • MORE
    • Contact
    • Teaching
    • Events
  • More
    • Home
    • RESEARCH
      • Overview
      • Generative Digital Twins
      • Agentic Discovery
      • Computational Health
    • PUBLICATIONS
    • PEOPLE
    • NEWS
    • Join us
    • MORE
      • Contact
      • Teaching
      • Events

LUMA

LUMALUMALUMA
  • Home
  • RESEARCH
    • Overview
    • Generative Digital Twins
    • Agentic Discovery
    • Computational Health
  • PUBLICATIONS
  • PEOPLE
  • NEWS
  • Join us
  • MORE
    • Contact
    • Teaching
    • Events

Learning and Understanding in Medical AI

At LUMA@UCL, we develop computational models and intelligent systems to understand human health, accelerate scientific discovery and enable more precise medicine.

Latest research

Overview

Our research spans generative digital twins, agentic scientific discovery and computational health.

Generative Digital Twins

Agentic Scientific Discovery

Agentic Scientific Discovery

We develop generative models of anatomy, motion and function to create personalised digital twins of the human body.

Find out more

Agentic Scientific Discovery

Agentic Scientific Discovery

Agentic Scientific Discovery

We develop collaborative AI agents that formulate hypotheses, analyse complex evidence and accelerate biomedical discovery.

Find out more

Computational Health

Agentic Scientific Discovery

Computational Health

We integrate imaging, population and clinical data to understand disease, identify patient subgroups and enable more personalised care.

Find out more

The future is already here — it’s just not evenly distributed.


William Gibson

Luma Lab

Copyright © 2025 Luma Lab - All Rights Reserved.

This website uses cookies.

We use cookies to analyze website traffic and optimize your website experience. By accepting our use of cookies, your data will be aggregated with all other user data.

DeclineAccept