publications

2025

  1. On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning
    Magdalena Proszewska, Nikolay Malkin, and N. Siddharth
    arXiv preprint arXiv:2506.00136, May 2025
    HTML
  2. B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data
    Magdalena Proszewska, Tomasz Danel, and Dawid Rymarczyk
    arXiv preprint arXiv:2505.22252, May 2025
    HTML
  3. Bernoulli Priors as Efficient Denoising Guides for Diffusion Models
    Magdalena Proszewska, Nikolay Malkin, and N. Siddharth
    3rd Workshop on Generative Models for Computer Vision at the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2025 (CVPR), Jun 2025
    HTML

2024

  1. Optimising Network Efficiency in the Epidemic Scenario
    Magdalena Proszewska, Michal Bujak, Rafał Kucharski, and 2 more authors
    Available at SSRN 4976648, Oct 2024
    HTML
  2. Multi-Label Conditional Generation From Pre-Trained Models
    Magdalena Proszewska, Maciej Wołczyk, Maciej Zieba, and 3 more authors
    IEEE Transactions on Pattern Analysis and Machine Intelligence, Aug 2024
    HTML
  3. Graph Kernel Convolutions for Interpretable Classification
    Magdalena Proszewska, and Siddharth N
    Data-centric Machine Learning Research (DMLR) Workshop at the International Conference on Learning Representations (ICLR), May 2024
    HTML
  4. HyperCube: Implicit Field Representations of Voxelized 3D Models (Student Abstract)
    Magdalena Proszewska, Marcin Mazur, Tomasz Trzciński, and 1 more author
    In Proceedings of the AAAI Conference on Artificial Intelligence , Feb 2024
    HTML
  5. Face Identity-Aware Disentanglement in StyleGAN
    Adrian Suwała, Bartosz Wójcik, Magdalena Proszewska, and 3 more authors
    In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision , Jan 2024
    HTML

2023

  1. Remap, warp and attend: Non-parallel many-to-many accent conversion with normalizing flows
    Abdelhamid Ezzerg, Thomas Merritt, Kayoko Yanagisawa, and 6 more authors
    In 2022 IEEE Spoken Language Technology Workshop (SLT) , Jan 2023
    HTML

2022

  1. GlowVC: Mel-spectrogram space disentangling model for language-independent text-free voice conversion
    Magdalena Proszewska, Grzegorz Beringer, Daniel Sáez-Trigueros, and 3 more authors
    In Interspeech 2022 , Sep 2022
    HTML
  2. Text-Free Non-Parallel Many-To-Many Voice Conversion Using Normalising Flow
    Thomas Merritt, Abdelhamid Ezzerg, Piotr Biliński, and 4 more authors
    In ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) , May 2022
    HTML
  3. PluGeN: Multi-Label Conditional Generation From Pre-Trained Models
    Maciej Wołczyk, Magdalena Proszewska, Łukasz Maziarka, and 4 more authors
    In Proceedings of the AAAI Conference on Artificial Intelligence , Feb 2022
    HTML

2021

  1. HyperCube: Implicit Field Representations of Voxelized 3D Models
    Magdalena Proszewska, Marcin Mazur, Tomasz Trzciński, and 1 more author
    arXiv preprint arXiv:2110.05770, Oct 2021
    HTML