PhD Candidate in Technical Computer Science

Ignacy Kolton

I work on machine learning for medical imaging and I'm a member of the GMUM research group at Jagiellonian University.

Research

What I work on

My PhD focuses on foundation models for multimodal medical data. Beyond my PhD, I also work on 3D representations of medical volumes.

Medical Imaging

Applying machine learning and computer vision to multimodal medical data for diagnostic and research purposes.

Computer Vision & Generative Models

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

Publications

Recent work

Diagnostic Loss: Asymmetric Supervision for Radiology Report Generation

Ignacy Kolton, Wenxuan Li, Zongwei Zhou, Jarosław B. Ćwikła, Arkadiusz Sitek, Pedro R. A. S. Bassi, Szymon Płotka

arXiv preprint arXiv:2610.30980 · 2026 · Poster at ML in PL Conference 2026

Automated radiology report generation requires models to do more than produce fluent clinical narratives: they must explicitly state supported diagnoses while avoiding unsupported ones. However, exist...

Code Read paper

@article{kolton2026diagnostic,
  title = {{Diagnostic Loss: Asymmetric Supervision for Radiology Report Generation}},
  author = {Kolton, Ignacy and Li, Wenxuan and Zhou, Zongwei and Ćwikła, Jarosław B. and Sitek, Arkadiusz and Bassi, Pedro R. A. S. and Płotka, Szymon},
  journal = {arXiv preprint arXiv:2610.30980},
  year = {2026},
  url = {https://arxiv.org/abs/2610.30980}
}

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

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

arXiv preprint arXiv:2602.00350 · 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 unle...

Code Read paper

@article{kolton2026relapse,
  title = {{ReLAPSe: Reinforcement-Learning-trained Adversarial Prompt Search for Erased concepts in unlearned diffusion models}},
  author = {Kolton, Ignacy and Marzol, Kacper and Batorski, Paweł and Mazur, Marcin and Swoboda, Paul and Spurek, Przemysław},
  journal = {arXiv preprint arXiv:2602.00350},
  year = {2026},
  url = {https://arxiv.org/abs/2602.00350}
}

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

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

arXiv preprint arXiv:2509.16806 · 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-...

Code Read paper

@article{marzol2025medgs,
  title = {{MedGS: Gaussian Splatting for Multi-Modal 3D Medical Imaging}},
  author = {Marzol, Kacper and Kolton, Ignacy and Smolak-Dyżewska, Weronika and Kaleta, Joanna and Mazur, Marcin and Spurek, Przemysław},
  journal = {arXiv preprint arXiv:2509.16806},
  year = {2025},
  url = {https://arxiv.org/abs/2509.16806}
}

Contact

Let's talk

Open to research collaboration on ML for medical imaging, or just a good conversation about the field. Reach out if you want to collaborate!

contact@ikolton.com LinkedIn GitHub Scholar