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.

In 2022, we are organizing Machine Learning Summer School with Neuroscience - click for more info or visit the website.

PluGeN: Multi-Label Conditional Generation From Pre-Trained Models (paper)

Maciej Wołczyk, Magdalena Proszewska, Łukasz Maziarka, Maciej Zięba, Patryk Wielopolski, Rafał Kurczab, Marek Śmieja

AAAI 2022

Zero Time Waste: Recycling Predictions in Early Exit Neural Networks (paper)

Maciej Wołczyk, Bartosz Wójcik, Klaudia Bałazy, Igor Podolak, Jacek Tabor, Marek Śmieja, Tomasz Trzciński

NeurIPS 2021

Continual World: A Robotic Benchmark For Continual Reinforcement Learning (paper)

Maciej Wołczyk, Michał Zając, Razvan Pascanu, Łukasz Kuciński, Piotr Miłoś

NeurIPS 2021

Non-Gaussian Gaussian Processes for Few-Shot Regression (paper)

Marcin Sendera, Jacek Tabor, Aleksandra Nowak, Andrzej Bedychaj, Massimiliano Patacchiola, Tomasz Trzciński, Przemysław Spurek, Maciej Zięba

NeurIPS 2021

MEiN scholarship for outstanding young scientists 2021 (scholarship)

Tomasz Trzciński

MEiN scholarship for outstanding young scientists 2021 (scholarship)

Marek Śmieja

START 2021 (scholarship)

Stanisław Jastrzębski

ProtoPShare: Prototypical Parts Sharing for Similarity Discovery in Interpretable Image Classification (paper)

Dawid Rymarczyk, Łukasz Struski, Jacek Tabor, Bartosz Zieliński

SIGKDD 2021

Group of Machine Learning Research

Recent achievements

PluGeN: Multi-Label Conditional Generation From Pre-Trained Models (paper)

Zero Time Waste: Recycling Predictions in Early Exit Neural Networks (paper)

Continual World: A Robotic Benchmark For Continual Reinforcement Learning (paper)

Non-Gaussian Gaussian Processes for Few-Shot Regression (paper)

MEiN scholarship for outstanding young scientists 2021 (scholarship)

MEiN scholarship for outstanding young scientists 2021 (scholarship)

START 2021 (scholarship)

ProtoPShare: Prototypical Parts Sharing for Similarity Discovery in Interpretable Image Classification (paper)

Contact Us