publications

Research on structured representations and neurosymbolic learning, including scientific applications.

My work covers learned discrete representations and neural guidance for program synthesis, with applications in vision and scientific machine learning. For citation counts, see my Google Scholar profile.

2026

  1. Preprint
    Structure over Pixels: Learning Variable-Length Visual Programs
    Piotr Wyrwiński, Kacper Dobek, and Krzysztof Krawiec
    arXiv preprint arXiv:2605.27696, 2026

2025

  1. Preprint
    Learning Regional Weather Dynamics from Global Weather Foundation Models
    Wiktor Kamzela, Jakub Kubiak, Adam Dobosz, and 5 more authors
    2025
    Preprint
  2. EurIPS AICC
    Bridging Scales in Weather Forecasting: Learning High-Resolution Dynamics from Coarse Inputs
    Wiktor Kamzela, Jakub Kubiak, Adam Dobosz, and 5 more authors
    2025
    Accepted at the AI for Climate and Conservation Workshop at EurIPS; selected for oral presentation
  3. GECCO
    Learning Semantics-aware Search Operators for Genetic Programming
    Piotr Wyrwiński and Krzysztof Krawiec
    In Proceedings of the Genetic and Evolutionary Computation Conference Companion, 2025
  4. AAAI
    Neuro-Guided Graph Search for Symbolic Regression (Student Abstract)
    Piotr Wyrwiński and Krzysztof Krawiec
    In Proceedings of the AAAI Conference on Artificial Intelligence, 2025

2024

  1. GECCO
    Guiding Genetic Programming with Graph Neural Networks
    Piotr Wyrwiński and Krzysztof Krawiec
    In Proceedings of the Genetic and Evolutionary Computation Conference Companion, 2024

2020

  1. MCSS
    Ensemble Malware Classification Using Neural Networks
    Piotr Wyrwiński, Jakub Dutkiewicz, and Czesław Jędrzejek
    In Multimedia Communications, Services and Security, 2020