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.

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

Evolutionary-Neural Hybrid Agents for Architecture Search (paper)

Krzysztof Maziarz, Mingxing Tan, Andrey Khorlin, Marin Georgiev, Andrea Gesmundo

ICML Workshop on AutoML 2019; 1st place in Data Science Masters - best Master's thesis competition, Applied track

Bio-inspired artificial neural networks (grant)

Jacek Tabor

2019-2023, FNP TEAM-NET

The Break-Even Point on the Optimization Trajectories of Deep Neural Networks (paper)

Stanisław Jastrzębski, Maciej Szymczak, Stanislav Fort, Devansh Arpit, Jacek Tabor, Kyunghyun Cho*, Krzysztof Geras*

ICLR 2020 (Spotlight)

Persistence bag of words for topological data analysis (paper)

Bartosz Zieliński, Michał Lipiński, Mateusz Juda, Matthias Zeppelzauer, Paweł Dłotko

IJCAI 2019

Parameter-Efficient Transfer Learning for NLP (paper)

Neil Houlsby, Andrei Giurgiu, Stanisław Jastrzębski, Bruna Morrone, Quentin de Laroussilhe, Andrea Gesmundo, Mona Attariyan, Sylvain Gelly

ICML 2019