Group of Machine Learning Research

GMUM (Group of Machine Learning Research) is a group at Jagiellonian University 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.
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.

Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization (paper)

Stanisław Jastrzębski, Devansh Arpit, Oliver Astrand, Giancarlo Kerg, Huan Wang, Caiming Xiong, Richard Socher, Kyunghyun Cho, Krzysztof Geras

ICML 2021

Explaining Self-Supervised Image Representations with Visual Probing (paper)

Dominika Basaj, Witold Oleszkiewicz, Igor Sieradzki, Michał Górszczak, Barbara Rychalska, Tomasz Trzciński, Bartosz Zieliński

IJCAI 2021

Kernel Self-Attention for Weakly-supervised Image Classification using Deep Multiple Instance Learning (paper)

Dawid Rymarczyk, Adriana Borowa, Jacek Tabor, Bartosz Zieliński

WACV 2021

Combination of Molecular Simulation and Deep Learning for De Novo Drug Design (grant)

Tomasz Danel

Preludium 19

Cramer-Wold AutoEncoder (paper)

Szymon Knop, Jacek Tabor, Przemysław Spurek, Igor Podolak, Marcin Mazur, Stanisław Jastrzębski

JMLR 2020

Finding the Optimal Network Depth in Classification Tasks (paper)

Bartosz Wójcik, Maciej Wołczyk, Klaudia Bałazy, Jacek Tabor

ECML PKDD 2020

Hypernetwork approach to generating point clouds (paper)

Przemysław Spurek, Sebastian Winczowski, Jacek Tabor, Maciej Zamorski, Maciej Zięba, Tomasz Trzciński

ICML 2020

Transformer-based methods for novel active chemical compounds (grant)

Łukasz Maziarka

Preludium 2020