Skip to main content

Profile

Maciej Zięba

Full Professor, Deputy Head of the Department

Maciej Zięba is a research scientist at Tooploox and an Associate Professor at Wroclaw University of Science and Technology, where he received a Ph.D. degree in computer science and a master’s degree in economics. He also obtained a master’s degree in computer science at Blekinge Institute of Technology in Sweden. In 2017, he was a visiting scholar at the University of Wollongong (Australia). His research is directed towards deep learning, especially generative models and representation learning. He was the co-author of a variable number of research papers published in influential journals and presented at the top ML conferences, including NeurIPS, AAAI, ICML, and ICLR.

Research interests

  • Deep learning
  • Generative models
  • representation learning
  • 3D point clouds
  • probabilistic models

Research groups

Education

  1. 2009

    Master of Engineering - MEng, Comupter Science

    Wroclaw University of Science and Technology

  2. 2010

    Master of Engineering - MEng, Computer Science

    Blekinge Tekniska Högskola (Sweden)

  3. 2014

    Doctor of Philosophy - PhD, Computer Science

    Wroclaw University of Science and Technology

  4. 2017

    PosDoc

    University of Wollongong (Australia)

  5. 2021

    DSc (habilitation), computer science

    Wroclaw University of Science and Technology

Publications96

HyperMAML: few-shot adaptation of deep models with hypernetworks

Maciej M Zięba, Marcin Przewięźlikowski, Przemysław Przybysz, Jacek Tabor, Przemysław Spurek

Neurocomputing 2024 vol. 598, art. 128179, [ Publikacja zarejestrowana jako preonline dn. 12.07.2024, rok zaliczenia 2024. Wersja ostateczna zarejestrowana 09.09.2024, rok zaliczenia 2024

2024

Multi-Label conditional generation from pre-trained models

Maciej M Zięba, Patryk E Wielopolski, Magdalena Proszewska, Maciej Wołczyk, Łukasz Maziarka, Marek Śmieja

IEEE Transactions on Pattern Analysis and Machine Intelligence 2024 vol. 46, nr 9, [ Publikacja zarejestrowana jako preonline dn. 02.04.2024, rok zaliczenia 2024. Wersja ostateczna zarejestrowana 09.09.2024, rok zaliczenia 2024

2024

Showing 20 of 96