Hi! I’m Guille
I’m a PhD student at EPFL working under the supervision of Pascal Frossard. My research focuses on understanding and enhancing AI systems by studying how weight space and function space are related in deep learning. I am particularly interested in making large pre-trained models more reliable and trustworthy.
Last summer, I was a research intern at Google Research in Zurich, where I worked with Efi Kokiopoulou and Rodolphe Jenatton on scalable solutions for label noise. I have also visited Philip Torr’s lab at the University of Oxford as part of the ELLIS PhD Program, where I conducted research on the robustness of neural networks.
Before starting my PhD, I lived in The Netherlands where I worked on sampling theory for tensors and graphs at TU Delft. I also spent some great time in Hamburg at Philips Research working on self-supervised deep learning for medical imaging. Some time ago, I was a young undergraduate student at Universidad Politecnica de Madrid.
Interests
- Deep learning science
- Trustworthy AI
- Model editing
Education
-
PhD in Machine Learning, Ongoing
École Polytechnique Fédérale de Lausanne
-
MSc in Electrical Engineering, 2018
Delft University of Technology
-
BSc in Telecommunications Eng., 2015
Universidad Politécnica de Madrid
