About me

I’m a PhD student at the Jagiellonian University, working on machine learning with the GMUM group under supervision of Prof. Jacek Tabor. My main research interests are centered around the issue of efficiency in deep learning, highlighting the following questions in particular:

  • Continual Learning – how to remember the past and reuse it efficiently when learning from a stream of data.
  • Reinforcement Learning – how to increase the sample efficiency and leverage models pre-trained on offline data.
  • Conditional Computation – how to adapt the computing power of the model to a given example.
  • Generative Models – how to perform weakly supervised conditional generation and adapt existing models for conditional generation.

News

Selected publications

Example transfer matrix from the paper
Disentangling Transfer in Continual Reinforcement Learning
Maciej Wołczyk*, Michał Zając*, Razvan Pascanu, Łukasz Kuciński, Piotr Miłoś
NeurIPS 2022
[Paper]
General idea of InterContiNet
Continual Learning with Guarantees via Weight Interval Constraints
Maciej Wołczyk*, Karol Piczak*, Bartosz Wójcik, Łukasz Pustelnik, Paweł Morawiecki, Jacek Tabor, Tomasz Trzciński, Przemysław Spurek
ICML 2022
[Paper][Code]
Scheme of PluGeN
PluGeN: Multi-Label Conditional Generation From Pre-Trained Models
Maciej Wołczyk*, Magdalena Proszewska*, Łukasz Maziarka, Maciej Zięba, Patryk Wielopolski, Rafał Kurczab, Marek Śmieja
AAAI 2022
[Paper][Code]
Scheme of the Zero Time Waste model
Zero Time Waste: Recycling Predictions in Early Exit Neural Networks
Maciej Wołczyk*, Bartosz Wójcik*, Klaudia Bałazy, Igor Podolak, Jacek Tabor, Marek Śmieja, Tomasz Trzciński
NeurIPS 2021
[Paper] [Code]
CW20 from Continual World
Continual World: A Robotic Benchmark For Continual Reinforcement Learning
Maciej Wołczyk*, Michał Zając*, Razvan Pascanu, Łukasz Kuciński, Piotr Miłoś
NeurIPS 2021
[Webpage] [Paper] [Code]