Bio
I obtained a B.Eng. in Automation and Robotics from
Wrocław University of Science and Technology (WUST) in 2024. Currently, I am pursuing a Master’s degree in Computer Science with a specialization in Artificial Intelligence at the
Warsaw University of Techonlogy (WUT), under the supervision of
Prof. Przemysław Musialski.
I am deeply passionate about science and engineering and aspire to contribute to high-impact fields within Machine Learning. My research interests focus on developing interpretable models with large learning capacities. At present, I am particularly interested in the science of cognition, as well as Variational Autoencoders (VAEs), Implicit Neural Representations (INRs) and Diffusion models.
Beyond my current work in machine learning, I also have a strong interest in Robotics and Reinforcement Learning.
Academic Achievements
†Equal Contribution, * Corresponding Author(s)
Conference Papers
[1] Gruszczynski, G., Meixner, J.J., Włodarczyk, M.J., and Musialski, P.,
"Beyond Blur: A Fluid Perspective on Generative Diffusion Models",
International Conference on Computer Vision (ICCV), 2025.
[2] Yin, H., Plocharski, A., Włodarczyk, M.J., Kida, M., and Musialski, P.,
"FlatCAD: Fast Curvature Regularization of Neural SDFs for CAD Models",
Pacific Graphics, 2025.
Conference Presentation
[3] Włodarczyk, M.J. and Musialski, P.,
"Photorealistic Reconstruction with Differentiable Rendering",
Presentation at the Data Science Summit — Machine Learning Edition, June 13, 2024.
Research Experiences
-
IDEAS NCBR, Warsaw, Poland
Research Intern in Computer Graphics Group
October 2023 – February 2025
- Developed, trained, and fine-tuned machine learning models
- Designed and executed large-scale experiments and benchmarks
- Orchestrated distributed high-performance computing workflows
- Analyzed results and presented insights to guide research directions
- Co-authored contributions to peer-reviewed research publications
- Presented technical findings to academic and non-specialist audiences
-
Mi2Lab, Warsaw, Poland
Contract Developer
April 2025 – June 2025
- Conducted literature review to identify key research directions
- Mapped research findings to highlight directions worth exploring
- Designed and implemented a reproducible data analysis framework
- Developed and refined neural network–based reconstruction methods
- Evaluated performance across architectures and parameter spaces
- Leveraged HPC resources for large-scale training and optimization
- Compiled final report integrating research and experimental findings
Connections