Home | Research | Groups | Ewa Szczurek

Research Group Ewa Szczurek


Link to website at LMU

Ewa Szczurek

Prof. Dr.

Collaborating PI

Ewa Szczurek

is Professor of AI in Life Sciences at LMU Munich, associate professor at University of Warsaw, and Director of the Institute of AI for Health at Helmholtz Munich.

Her lab focuses on developing probabilistic graphical models and deep generative models for applications in medicine. Research areas include cancer, lung diseases, and antibiotic resistance. Current projects explore how tumors develop, interact with surrounding tissues, and become resistant to treatment. The lab also develops generative models to design antimicrobial peptides that can fight antibiotic-resistant bacteria.

Team members @MCML

PostDocs

Link to website

Adam Izdebski

Dr.

Link to website

Martin Pašen

Dr.

PhD Students

Link to website

Pankhil Gawade

Link to website

Dinesh Adhithya Haridoss

Link to website

Michal Kmicikiewicz

Link to website

Rasmus Moller Larsen

Link to website

Gizem Mert

Recent News @MCML

Link to Welcoming Ewa Szczurek to MCML

27.10.2026

Welcoming Ewa Szczurek to MCML

Developing Probabilistic and Generative Models for Cancer, Lung Diseases, and Antibiotic Resistance

Tiny logo
Link to MCML at ICML 2026

03.07.2026

MCML at ICML 2026

89 Accepted Papers (72 Main, and 17 Workshops)

Tiny logo
Link to MCML at NeurIPS 2025

28.11.2025

MCML at NeurIPS 2025

57 Accepted Papers (42 Main, and 15 Workshops)

Publications @MCML

2026


[2] A* Conference
M. Możejko • A. Bielecki • J. Prądzyński • H.-S. Lee • A. Janowski • M. Kmicikiewicz • P. Szymczak • K. Jurasz • M. Traskowski • M. Kucharczyk • M. Der Torossian Torres • C. de la Fuente-Nunez • E. Szczurek
PepCompass: Navigating Peptide Embedding Spaces Using Riemannian Geometry.
ICML 2026 - 43rd International Conference on Machine Learning. Seoul, South Korea, Jul 06-11, 2026. To be published. Preprint available. URL GitHub

2025


[1] A* Conference
M. Kmicikiewicz • V. Fortuin • E. Szczurek
ProSpero: Active Learning for Robust Protein Design Beyond Wild-Type Neighborhoods.
NeurIPS 2025 - 39th Conference on Neural Information Processing Systems. San Diego, CA, USA, Nov 30-Dec 07, 2025. URL

Back to Top