Scholar
Guillermo Ortiz-Jiménez
Google Scholar ID: xAsJnG0AAAAJ
Google DeepMind
Citations & Impact
Citations
998
H-index
15
i10-index
18
Publications
20
Co-authors
46
list available
Resume (English only)
Academic Achievements
- Selected publications:
- - 'On the difficulty of constructing a robust and publicly-detectable watermark' in AISTATS 2025.
- - 'LiNeS: Post-training layer scaling prevents forgetting and enhances model merging' in ICLR 2024.
- - 'Localizing Task Information for Improved Model Merging and Compression' in ICML 2024.
- - 'Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models' in NeurIPS 2023.
- - 'What can linearized neural networks actually say about generalization?' in NeurIPS 2021.
Research Experience
- Senior research scientist at Google DeepMind; interned at Google Research in Zürich; visited Philip Torr’s lab at the University of Oxford, UK.
Education
- PhD from EPFL, Switzerland, under the supervision of Pascal Frossard; MSc from TU Delft, Netherlands; BSc from Universidad Politécnica de Madrid, Spain.
Background
- Senior research scientist, mainly focusing on responsible AI, developing technologies to cultivate a healthier data ecosystem (such as SynthID) and improve GenAI models. Interested in the science of deep learning, specifically understanding how and why neural networks learn.
Miscellany
- Personal interests include the science of deep learning.
