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 are organizing the second edition of Machine Learning Summer School (MLSS^S) with a focus on Applications in Science. More information can be found on the event website as well as here.

Revisiting Offline Compression: Going Beyond Factorization-based Methods for Transformer Language Models (paper)

Klaudia Bałazy, Mohammadreza Banaei, Artur Kasymov, Remi Lebret, Jacek Tabor, Karl Aberer

EACL 2023

Step by Step Loss Goes Very Far: Multi-Step Quantization for Adversarial Text Attacks (paper)

Klaudia Bałazy, Piotr Gaiński

EACL 2023

ProGReST: Prototypical Graph Regression Soft Trees for Molecular Property Prediction (paper)

Dawid Rymarczyk, Daniel Dobrowolski, Tomasz Danel

SDM 2023

Conditional deep generative models (grant)

Marek Śmieja

OPUS 23

Balancing priors in Bayesian Neural Networks (grant)

Tomasz Kuśmierczyk

POLONEZ BIS 2

Improving interpretability in deep neural networks (grant)

Dawid Rymarczyk

PRELUDIUM 21

Better adaptation in Meta-Learning (grant)

Marcin Sendera

PRELUDIUM 21

COeXISTENCE between humans and machines in urban mobility (grant)

Rafał Kucharski

ERC Starting Grant