Machine learning · Data science · AI

Kjell Runar Horvli

Exploring models, and building things people can use. Master’s student in Information Science at the University of Bergen.

Selected projects

Optimisation · Live demo

Counter-Strike fantasy optimiser

Finding five-player lineups under budget, team and tournament constraints. Built in Python, with a Streamlit interface, packaged with Docker and deployed on Azure.

Try live demo ↗ View project →

Recommender systems · Group project

Beer recommender system

Helping people discover beers through patterns in user ratings. We compared collaborative filtering methods and explored a hybrid approach that balances personalised predictions with broader recommendation coverage.

View project →

Your rating history

↓ 11–45 reviews Popular picks Community favourites

↓ More than 45 reviews Personalised picks Patterns learned with SVD

↓

Discover your next beer

Master’s thesis · Ongoing research

AI-generated image detection

Investigating whether image inversion improves detection of AI-generated images. Adapting techniques from image editing, my method learns from the original image, its inverted noise and its reconstruction.

View research →

BLIP captioning · FLUX + FireFlow inversion

Original

Inverted noise

Reconstruction

ResNet50 Real / AI-generated prediction

About me

I’m a master’s student in Information Science at the University of Bergen, focusing on machine learning and AI. My thesis explores detecting AI-generated images through diffusion inversion.

Alongside my studies, I’ve contributed to Norwegian-language LLM safety research through SafeLLM and worked as a teaching assistant in machine learning and AI courses.

Contact

Interested in discussing my work? Get in touch.