About Me

I’m a Computer Science student at the Jagiellonian University, currently pursuing my master’s degree. My main interests focus on machine learning and computer vision, especially their applications in medical imaging and data analysis. At the same time, I’m passionate about software engineering — I enjoy low-level programming in C++, designing systems and architectures, and creating practical tools that actually solve problems. I like understanding how things work and turning ideas into something real and useful.

Education

• 2024 - 2026(expected)

  Master’s in Computer Science

  Jagiellonian University • Krakow, Poland

  Focused on machine learning and computer vision, with involvement in practical research projects and publications. Continued developing programming skills, including low-level languages such as assembler.

  ---

• 2021 - 2024

  Bachelor’s in Computer Science

  Jagiellonian University • Krakow, Poland

  Developed a strong foundation in computer science and mathematics, along with practical experience in software development for web, mobile, and desktop platforms.

  ---

Experiences

• 05.2024 - 11.2024

  Software Engineer Internship

  HERE Technologies

  Refactored legacy code in Java and Swift, improving structure and readability, and updated unit and integration tests to increase coverage and reliability. Optimized older C++ components by enhancing memory usage and execution time. Collaborated closely with the team in Agile ceremonies and daily work to clarify requirements and align technical decisions. Used GitLab for version control and CI, and worked with internal tooling for builds and testing.

  ---

Skills

Last publications

• ReLAPSe: Reinforcement-Learning-trained Adversarial Prompt Search for Erased concepts in unlearned diffusion models

  Authors: Ignacy Kolton, Kacper Marzol, Paweł Batorski, Marcin Mazur, Paul Swoboda, Przemysław Spurek

  arXiv preprint arXiv:2602.00350 • January 2026

  Machine unlearning is a key defense mechanism for removing unauthorized concepts from text-to-image diffusion models, yet recent evidence shows that latent visual information often persists after unlearning. Existing adversarial approaches for exploiting this leakage are constrained by fundamental limitations: optimization-based methods are computationally expensive due to per-instance iterative search. At the same time, reasoning-based and heuristic techniques lack direct feedback from the target model's latent visual representations. To address these challenges, we introduce ReLAPSe, a policy-based adversarial framework that reformulates concept restoration as a reinforcement learning problem. ReLAPSe trains an agent using Reinforcement Learning with Verifiable Rewards (RLVR), leveraging the diffusion model's noise prediction loss as a model-intrinsic and verifiable feedback signal. This closed-loop design directly aligns textual prompt manipulation with latent visual residuals, enabling the agent to learn transferable restoration strategies rather than optimizing isolated prompts. By pioneering the shift from per-instance optimization to global policy learning, ReLAPSe achieves efficient, near-real-time recovery of fine-grained identities and styles across multiple state-of-the-art unlearning methods, providing a scalable tool for rigorous red-teaming of unlearned diffusion models.

• MedGS: Gaussian Splatting for Multi-Modal 3D Medical Imaging

  Authors: Kacper Marzol, Ignacy Kolton, Weronika Smolak-Dyżewska, Joanna Kaleta, Marcin Mazur, Przemysław Spurek

  arXiv preprint arXiv:2509.16806 • September 2025

  Multi-modal three-dimensional (3D) medical imaging data, derived from ultrasound, magnetic resonance imaging (MRI), and potentially computed tomography (CT), provide a widely adopted approach for non-invasive anatomical visualization. Accurate modeling, registration, and visualization in this setting depend on surface reconstruction and frame-to-frame interpolation. Traditional methods often face limitations due to image noise and incomplete information between frames. To address these challenges, we present MedGS, a semi-supervised neural implicit surface reconstruction framework that employs a Gaussian Splatting (GS)-based interpolation mechanism. In this framework, medical imaging data are represented as consecutive two-dimensional (2D) frames embedded in 3D space and modeled using Gaussian-based distributions. This representation enables robust frame interpolation and high-fidelity surface reconstruction across imaging modalities.