University of Edinburgh · CHAI AI Hub

VIOS

Collaboratory

Βίος · Life in Greek · pronounced vEEOs

We advance interdisciplinary AI — applying machine learning, computer vision, and causal reasoning to open challenges in medicine, agriculture, and the life sciences.

Scroll

"Life is central to our mission — with advances in AI, computer vision and inverse problems, we address societal challenges by solving key problems in the life and natural sciences."

— Sotirios A. Tsaftaris · Chair in Machine Learning & Computer Vision

Latest Updates

News & highlights

Feb 23, 2026

New Website

Our new website is live! Enjoy the cleaner, modern design and easier navigation. Stay tuned for updates!

Sep 1, 2025

Expanding

Our team is expanding! We have four more PhD students join us!

Dec 9, 2024

New CHAI PhD positions in partnership with Canon Medical

We have now completed recruitment for two PhD positions as part of the CHAI AI Hub in collaboration with Canon Medical. New openings (if any) will be announced here join us page.

View All News
Research Focus

Where AI meets
sciences

01 🫀

Healthcare Systems

Medical imaging and image analysis with a focus on representation learning — doing more with less through semi-supervised, multi-task, and multi-modal approaches. Active work on cardiac MRI, digital twin surgery, and AI-assisted clinical decision making.

Cardiac MRI Digital Twin Surgery Multi-modal Foundation Models
02 ⚛️

Causal AI & Fair Representations

Disentangled representation learning, causal discovery, and equivariant architectures to build AI that reasons rather than correlates — enabling reliable, bias-aware predictions in high-stakes domains. Central to the EPSRC CHAI Hub.

Causal Discovery Disentanglement Bias Mitigation CHAI Hub
03 🌿

Sustainability & Agriculture

Computer vision for plant phenotypic trait estimation, crop breeding, and disease resistance. Open data frameworks and digital research infrastructure — including PhenomUK — supporting sustainable global agriculture.

Plant Phenotyping PhenomUK Open Data Trait Estimation
04

AI for Energy & Inverse Problems

Virtual power plants, AI-driven grid resilience, and data-driven materials innovation for the wearable artificial kidney. Addressing complex inverse problems in energy, environmental, and biomedical sciences.

Energy AI Virtual Power Plant Inverse Problems Wearable Kidney

Active & Recent Funded Projects

EPSRC Real-time Digital Twin Assisted Surgery
Selected Work

Recent publications

arXiv

A Causal Framework for Mitigating Data Shifts in Healthcare

Kurt Butler, Stephanie Riley, Damian Machlanski, Edward Moroshko, Panagiotis Dimitrakopoulos, Thomas Melistas, Akchunya Chanchal, Konstantinos Vilouras, Zhihua Liu, Steven McDonagh, Hana Chockler, Ben Glocker, Niccolo Tempini, Matthew Sperrin, Sotirios Tsaftaris, Ricardo Silva

Zenodo (CERN European Organization for Nuclear Research)

Arabidopsis Thaliana Data for A Conversational Multi-Agent AI System for Automated Plant Phenotyping

Feng Chen, Sotirios A. Tsaftaris, Mario Valerio Giuffrida

International Journal of Computer Vision

Uncertainty-guided Open-Set Source-Free Unsupervised Domain Adaptation with Target-private Class Segregation

Mattia Litrico, Davide Talon, Sebastiano Battiato, Alessio Del Bue, Mario Valerio Giuffrida, Pietro Morerio

View All Publications
Affiliations
The University of Edinburgh CHAI AI Hub Canon Medical Research PhenomUK