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
Computer Vision
My (work in progress) master thesis is connected to medical data segmentation
Gaussian Splatting
Used Gaussian Splatting for representing medical volumetric data, interpolation, and 3D mesh reconstruction
Medical Data Analysis
Applying machine learning methods to analyze and process medical data for diagnostic and research purposes
Adversarial Attacks with Reinforcement Learning
Exploring the use of LLMs and RL to generate adversarial prompts for image generation models
Current Projects
Efficient Sequential Modeling with Mixture of Experts for Medical Image Segmentation
Designing and evaluating a new network architecture that combines transformers or state-space models with mixture-of-experts mechanisms for 2D and 3D medical image segmentation using open public datasets.
Adversarial Attacks on Image Generation Models using RLVR LLMs
Exploring the use of Reainforcement Learning with verifiable rewards (RLVR) large language models (LLMs) to generate adversarial prompts to see if unlearned models can be exploited to generate forgotten content.