Research Statement

My research focuses on machine learning, with a particular interest in medical data analysis and related applications. I enjoy exploring different aspects of ML — from computer vision techniques for image segmentation to novel data representations like Gaussian Splatting for 3D reconstruction.

Research Areas

Medical Data Analysis

Applying machine learning methods to analyze and process multimodal medical data for diagnostic and research purposes

Gaussian Splatting

Used Gaussian Splatting for representing medical volumetric data, interpolation, and 3D mesh reconstruction

Adversarial Attacks with Reinforcement Learning

Exploring the use of LLMs and RL to generate adversarial prompts for image generation models

Latest 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.