Scholar
Adriana Romero-Soriano
Google Scholar ID: Sm15FXIAAAAJ
Fundamental AI Research, Meta
Citations & Impact
Citations
42,635
H-index
30
i10-index
43
Publications
20
Co-authors
46
list available
Contact
Publications
Resume (English only)
Research Experience
- Currently a research scientist at Meta AI (FAIR), an adjunct professor at McGill University, a core industry member at Mila, and a Canada CIFAR AI Chair. Previously, she was a post-doctoral researcher at Mila, working with Prof. Yoshua Bengio.
Education
- Ph.D. from University of Barcelona, Advisor: Dr. Carlo Gatta
Background
- Research interests: inferring full observations from partial observations, building models of the world to improve impactful downstream applications. Recent research explores the potential of conditional visual generative models as synthetic training data sources, with a focus on scaling laws of synthetic data, model sampling techniques, and addressing model collapse.
Miscellany
- Personal website: https://skylerhallinan.com/; GitHub: adri-romsor; Twitter: @adri_romsor; Google Scholar
