Publications
Héctor Laria
I'm a PhD candidate in Computer Science at the Computer Vision Center (CVC) in Barcelona, where I focus on computer vision and generative models. My research investigates efficient generative modeling techniques under data-constrained scenarios, supervised by Joost van de Weijer and advised by Bogdan Raducanu.
My recent work has transitioned from GANs to diffusion models, with a particular interest in addressing the limitations of foundational models and their applications. This includes studying representational drift in fine-tuned diffusion models and characterizing information and color expression in state-of-the-art models. What I find most exciting and meaningful in my work is exchanging ideas and collaborating with individuals of diverse backgrounds and interests.
Before joining CVC, I worked as a Project Employee in the Extreme Classification Group at Aalto University and as a Research Assistant in their Content-Based Image and Information Retrieval Group.
I hold an MSc in Machine Learning, Data Science and AI with Honours distinction from Aalto University, where my thesis focused on image captioning using recurrent neural networks and reinforcement learning, supervised by Jorma Laaksonen. I completed a BSc in Software Engineering at Complutense University, Madrid, with a thesis on evolutionary computation, developing game agents for the game Ms. Pac-Man using genetic algorithms, supervised by Antonio A. Sánchez-Ruiz and Carlos Cervigón. I've also attended the Cambridge ELLIS Machine Learning Summer School at Cambridge University.