Mato Gudelj

I recently graduated with a Master's degree in Computer Science from the Technical University of Munich. The focus of my thesis was Machine Unlearning in LLMs. I did my Bachelor's degree in Computing at the University of Zagreb in 2022.

My main areas of interest are generally applicable ML methods, foundation models (CV, NLP) and applications of deep learning for building tools for thought.

Projects

Periplus

2024/25
Periplus graph view Periplus course view Periplus focus view Periplus panel view Periplus landing page

A novel system for interacting and learning with LLMs, revolving around rich interconnected generative documents. Includes courses, spaced repetition, LaTeX support and more! Initial version built in two weeks for the Build with Claude contest.

OpenAI Preparedness Challenge

2024

In 2024 I was selected as one of the winners of the OpenAI Preparedness Challenge for providing novel ideas for catastrophic misuse of frontier models and societal harm prevention. This included a prize worth $25,000 in API credits.

Vibesim.com

2023
Vibesim landing page Vibesim song view

An ML powered song recommendation website based on finding songs with similar vibes. Uses an audio embedding model with database spanning > 1 million songs.

Raytracer

2021
Raytraced power 8 Mandelbulb Raytraced cornell box

A small modular raytracer written in C++. Includes SSE optimized sphere intersection calculation, raymarched implementation of the mandelbulb fractal and JSON scene representation.

Contact

Email will be loaded with javascript to prevent scraping.