Guillermo Ortiz-Jiménez
¡Hola! 👋 I’m a research scientist at Google DeepMind making AI more reliable and trustworthy.
I obtained my PhD at EPFL🇨🇭 under the supervision of Pascal Frossard where I focused on the empirical understanding of deep learning. During my PhD, I interned at Google Research in Zürich and visited Philip Torr’s lab at the University of Oxford 🇬🇧 as part of the ELLIS PhD Program. Prior to that, I obtained my MSc. from TU Delft 🇳🇱 and my BSc. from Universidad Politécnica de Madrid 🇪🇸.
Research interests: I work in responsible AI, developing tools to make models more reliable, fair, safe and universally useful. I am also interested in the science of deep learning, with a focus on understanding how editions in the weights affect the behavior of AI systems.
If you’re not sure how to to pronounce my name you can watch this video. Here’s a quick tip: the double “ll” in Spanish sounds like a “y” and the “u” in “Gui” is silent. So altogether, it’s “ghee-YAIR-moh.”
news
Jan 2024 | I started a new job at Google DeepMind. |
---|---|
Dec 2023 | We presented Task Arithmetic in the Tangent Space as and Oral in NeurIPS 2024. |
Dec 2023 | I defended my PhD at EPFL 🎉! |
selected publications
- Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained ModelsIn Advances in Neural Information Processing Systems (NeurIPS) , 2023
- PRIME: A few primitives can boost robustness to common corruptionsIn European Conf. on Computer Vision (ECCV) , 2022
- A Structured Dictionary Perspective on Implicit Neural RepresentationsIn IEEE Conf. on Computer Vision and Pattern Recognition ( CVPR) , 2022
- What can linearized neural networks actually say about generalization?In Advances in Neural Information Processing Systems (NeurIPS) , 2021
- Neural Anisotropy DirectionsIn Advances in Neural Information Processing Systems (NeurIPS) , 2020