Group of Machine Learning Research

GMUM (Group of Machine Learning Research) is a group of researchers working on various aspects of machine learning, and in particular deep learning - in both fundamental and applied setting. The group is led by prof. Jacek Tabor. We are based in the Jagiellonian University in the beautiful city of Kraków, Poland.

Some of the research directions our group pursues include:

We are proud to announce that the study program 'Artificial Intelligence' was created in cooperation with our group. This program equips students to excel in utilizing AI methods, making them valuable assets in the rapidly evolving job landscape.

In 2023, we organized the second edition of Machine Learning Summer School (MLSS^S) with a focus on Applications in Science. We invite the participants to collaborate with us on various ongoing research projects - learn more here.

Recent achievements

AdaGlimpse: Active Visual Exploration with Arbitrary Glimpse Position and Scale (paper)

Adam Pardyl, Michał Wronka, Maciej Wołczyk, Kamil Adamczewski, Tomasz Trzciński, Bartosz Zieliński
ECCV 2024

A deep cut into Split Federated Self-Supervised Learning (paper)

Marcin Przewięźlikowski, Marcin Osial, Marek Śmieja, Bartosz Zieliński

Sparser, Better, Deeper, Stronger: Improving Sparse Training with Exact Orthogonal Initialization (paper)

Aleksandra Nowak, Łukasz Gniecki, Filip Szatkowski, Jacek Tabor
ICML 2024

Prediction Error-based Classification for Class-Incremental Learning (paper)

Michał Zając, Tinne Tuytelaars, Gido M. van de Ven
ICLR 2024

Divide and not forget Ensemble of selectively trained experts in Continual Learning (paper)

Grzegorz Rypeść, Sebastian Cygert, Valeriya Khan, Tomasz Trzcinski, Bartosz Zieliński, Bartłomiej Twardowski
ICLR 2024

Modelling the Rise and Fall of Two-Sided Mobility Markets with Microsimulation (paper)

Farnoud Ghasemi, Rafał Kucharski
AAMAS 2024

Contact Us

Group of Machine Learning Research
Faculty of Mathematics and Computer Science
ul. Lojasiewicza 6
30-342, Cracow, Poland