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.

Publications

Paper thumbnail

Leveraging Semantic Attribute Binding for Free-Lunch Color Control in Diffusion Models

Héctor Laria, Alexandra Gomez-Villa, Jiang Qin, Muhammad Atif Butt, Bogdan Raducanu, Javier Vazquez-Corral, Joost van de Weijer, Kai Wang

Under review

Paper thumbnail

Assessing Open-world Forgetting in Generative Image Model Customization

Héctor Laria, Alex Gomez-Villa, Kai Wang, Bogdan Raducanu, Joost van de Weijer

Under review

Paper thumbnail

NeRF-Diffusion for 3D-Consistent Face Generation and Editing

Héctor Laria, Kai Wang, Joost van de Weijer, Bogdan Raducanu, Yaxing Wang

VISAPP 2024

Paper thumbnail

Transferring Unconditional to Conditional GANs with Hyper-Modulation

Héctor Laria, Yaxing Wang, Joost van de Weijer, Bogdan Raducanu

CVPR 2022

Paper thumbnail

TransferI2I: Transfer Learning for Image-to-Image Translation from Small Datasets

Yaxing Wang, Hector Laria Mantecon, Joost van de Weijer, Laura Lopez-Fuentes, Bogdan Raducanu

ICCV 2021

Paper thumbnail

A Pac-Man bot based on grammatical evolution

Héctor Laria Mantecón, Jorge Sánchez Cremades, José Miguel Tajuelo Garrigós, Jorge Vieira Luna, Carlos Cervigon Rückauer and Antonio A. Sánchez-Ruiz-Granados

CoSECivi 2017