Àlex Pujol Vidal PhD Fellow at Aalborg University 2025 april

I am a first year PhD student at Aalborg University (AAU), advised by Prof. Kamal Nasrollahi and Prof. Sergio Escalera. My research interests converge at the intersection of Hyperbolic Learning, Concept Representation, and Machine Unlearning. My recent contributions have focused on exploring the emerging paradigm of Hyperbolic Machine Unlearning for concept removal in contrastive learning frameworks.

In 2024, I completed dual Master's degrees: an M.Sc. in Mathematics and an M.Sc. in Data Science from University of Barcelona (UB). I developed my Master's theses within the HuPBA group, led by Prof. Sergio Escalera and jointly supervised by Prof. Carles Casacuberta. My research investigated the foundational principles of Variational Autoencoders and Diffusion Models, where I proposed a Binary VQ-VAE as an expressive method for encoding motion in latent space. The aim was to efficiently generate human motion from text descriptions following a Bernoulli Diffusion process. Results didn't fully meet expectations, but the project was tremendously fun. Since then, I've been exploring various approaches to create more expressive latent space embeddings.

Álex Pujol Vidal

news

Mar 31, 2025
I attended the Generative Modeling Summer School (GeMSS'25) in Nice 🇫🇷. It was a great experience to learn from experts in the field, connect with fellow researchers and present a poster on my ongoing research in Hyperbolic Contrastive Unlearning. 🧠
Dec 19, 2024
I presented a poster on "Machine Unlearning and Explainable AI Verification" at DLBCN'24 in Barcelona 🇪🇸.
Dec 1, 2024
I attended the ICPR'24 and did an oral presentation on my accepted paper "Verifying Machine Unlearning with Explainable AI" in Kolkata 🇮🇳. It was my first visit to India, and I was impressed by Kolkata's rich cultural heritage and the vibrant academic community there. नमस्ते 🙏
Sep 29, 2024
I attended the ECCV'24 in Milan 🇮🇹. It was my first time in a big conference. I found the workshop "Beyond Euclidean: Hyperbolic and Hyperspherical Learning for Computer Vision particularly inspiring, as it demonstrated how non-Euclidean geometries can better capture the hierarchical and complex relationships in visual data, potentially leading to more efficient representation learning models. 💡🌀
Sep 2, 2024
I submitted the Master's thesis on Fundamental principles of Binary Latent Diffusion for the M.Sc. in Mathematics. I am grateful to my supervisors Prof. Sergio Escalera and Prof. Carles Casacuberta for their guidance and support throughout this journey. I also want to thank the HuPBA group and VAP lab for their valuable feedback and discussions. 🙏
Mar 01, 2024
I joined the Visual Analysis and Perception Lab at Aalborg University as a part-time research assistant. I will be working on Machine Unlearning at the REPAI project. I am excited to contribute to this important multidisciplinary research area and collaborate with a talented team of researchers from law, ethics and government. 🤝
Jan 15, 2024
I submitted the Master's thesis on Motion Binary Latent Diffusion for the M.Sc. in Data Science. I am grateful to my supervisors Prof. Sergio Escalera, Germán Barquero and Cristina Palmero for their exceptional guidance and expertise in human motion recognition, and motion generation. 🤸

projects

Project 1
new

Project Name 1

Brief description of the research project and its significance.

publications

2025

Publication Title Here

Author 1, Your Name, Author 3

Journal or Conference Name, 2025

2024

Another Publication Title

Your Name, Author 2

Conference Name, 2024