Warsaw Quantum Computing Group

We invite you to attend (online) Episode LXXIII
of Warsaw Quantum Computing Group meetups!

"Quantum generative adversarial networks for healthcare and life sciences"

Dr Julien Baglio

22.01.2026, 18:00 UTC+1

Video recording

Abstract:

High-quality image generation or computer-assisted drug design are critical tasks in healthcare and life sciences: for example, the development of new drugs is a tedious, time-consuming, and expensive process, for which the average costs are estimated to be up to around $2.5 billion. The first step of this long process is the design of the new drug, for which de novo drug design assisted by artificial intelligence has blossomed in the past few years and has revolutionized the field. However, classical methods relying on generative adversarial networks (GANs), either for (medical) image generation or drug design, are known to be difficult to train and subject to mode collapse. Quantum GANs (QGANs) could provide an avenue to overcome these issues by providing more robust models with less parameters. This talk will present a latent style-based QGAN architecture for drug design. The QGAN operates in a latent space thanks to a classical auto-encoder, which maps the original data into an abstract vector space representative of the features of the input molecular structures, as well as a gradient penalty to prevent mode collapse. Results using up to 20 qubits will be shown using MOSES dataset and compared against classical GANs, including sampling on a real quantum computer. A similar approach for image generation using SAT4 (Earth Observation images) dataset with 12 qubits will also be presented.

BIO:

Dr. Julien Baglio is a Senior Research Associate with Associate Professor responsibilities at the Center for Quantum Computing and Quantum Coherence (QC2) at the University of Basel, as well as a Quantum Algorithms Researcher at QuantumBasel. His research focuses on quantum machine learning, in particular quantum generative modelling, as well as quantum Hamiltonian simulation, with a particular emphasis on implementation on actual quantum hardware from IBM or IonQ. Prior to his positions at the University of Basel and QuantumBasel, Julien worked for over 3 years with CERN, where he started investigating quantum machine learning algorithms, parallel to his research activities in high energy physics focused on the understanding of the basic building blocks of Nature.

He holds a PhD in theoretical physics from the University of Paris-Sud 11 in France, with a focus on the study of the infamous Higgs boson, and an MSc from the École Normale Supérieure in Paris. His work played an important role in its discovery, which was awarded the Nobel Prize in physics in 2013. In total, he has authored over 70 peer-reviewed publications and scientific reports.

The meeting is organized by the Fundacja Quantum AI and QPoland.