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:

generative models: efficient training and sampling; inpainting; super-resolution,
theoretical understanding of deep learning and optimization,
natural language processing,
drug design and cheminformatics,
unsupervised learning and clustering,
computer vision and medical image analysis.

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.

Fantastic Weights and How to Find Them: Where to Prune in Dynamic Sparse Training (paper)

Aleksandra Nowak, Bram Grooten, Decebal Constantin Mocanu, Jacek Tabor

NeurIPS 2023

Trust Your ∇: Gradient-based Intervention Targeting for Causal Discovery (paper)

Mateusz Olko, Michał Zając, Aleksandra Nowak, Nino Scherrer, Yashas Annadani, Stefan Bauer, Łukasz Kuciński, Piotr Miłoś

NeurIPS 2023

Bucks for Buckets (B4B): Active Defenses Against Stealing Encoders ()

Jan Dubiński, Stanisław Pawlak, Franzisca Boenisch, Tomasz Trzciński, Adam Dziedzic

The Tunnel Effect: Building Data Representations in Deep Neural Networks (paper)

Wojciech Masarczyk, Mateusz Ostaszewski, Ehsan Imani, Razvan Pascanu, Piotr Miłoś, Tomasz Trzciński

NeurIPS 2023

Document Understanding Dataset and Evaluation (DUDE) (paper)

Jordy Van Landeghem, Rubén Tito, Łukasz Borchmann, Michał Pietruszka, Paweł Józiak, Rafał Powalski, Dawid Jurkiewicz, Mickaël Coustaty, Bertrand Ackaert, Ernest Valveny, Matthew Blaschko, Sien Moens, Tomasz Stanisławek

ICCV 2023

ICICLE: Interpretable Class Incremental Continual Learning (paper)

Dawid Rymarczyk, Joost van de Weijer, Bartosz Zieliński, Bartłomiej Twardowski

ICCV 2023

CompLung: Comprehensive Computer-Aided Diagnosis of Lung Cancer (paper)

Adam Pardyl, Dawid Rymarczyk, Joanna Jaworek-Korjakowska, Dariusz Kucharski, Andrzej Brodzicki, Julia Lasek, Zofia Schneider, Iwona Kucybała, Andrzej Urbanik, Rafał Obuchowicz, Zbisław Tabor, Bartosz Zieliński

ECAI 2023

ProMIL: Probabilistic Multiple Instance Learning for Medical Imaging (paper)

Łukasz Struski, Dawid Rymarczyk, Arkadiusz Lewicki, Robert Sabiniewicz, Jacek Tabor, Bartosz Zieliński

ECAI 2023

Group of Machine Learning Research

Recent achievements

Fantastic Weights and How to Find Them: Where to Prune in Dynamic Sparse Training (paper)

Trust Your ∇: Gradient-based Intervention Targeting for Causal Discovery (paper)

Bucks for Buckets (B4B): Active Defenses Against Stealing Encoders ()

The Tunnel Effect: Building Data Representations in Deep Neural Networks (paper)

Document Understanding Dataset and Evaluation (DUDE) (paper)

ICICLE: Interpretable Class Incremental Continual Learning (paper)

CompLung: Comprehensive Computer-Aided Diagnosis of Lung Cancer (paper)

ProMIL: Probabilistic Multiple Instance Learning for Medical Imaging (paper)

Contact Us