Diego Garcia-Olano (Preferred)
Diego Garcia-Olano
Researcher, GenAI Trust and Safety ( prior Responsible AI ), Meta AI
Joined
September 2020
Names
Emails
****@gmail.com (Confirmed)
****@meta.com (Confirmed)
Personal Links
Career & Education History
Researcher
GenAI Trust and Safety ( prior Responsible AI ), Meta AI (meta.com)
2022 – Present
PhD student
University of Texas, Austin (utexas.edu)
2017 – 2022
MS student
Universitat Politècnica de Catalunya (upc.edu)
2013 – 2015
Undergrad student
University of Texas, Austin (utexas.edu)
1999 – 2004
Advisors, Relations & Conflicts
Expertise
LLM explanation/evaluation
, data quality/mislabeling
, memorization
2020 – Present
explainable AI
, influence functions
, mechanistic interpretability
, prototypical learning
, concept bottlenecks
2018 – Present
Publications
Co-Authors
- Alan H. Gee
- Alessandro Presta
- Aobo Yang
- Aram H. Markosyan
- Byron C Wallace
- Byron C. Wallace
- Chantal Shaib
- Daniel Gillick
- David A. Smith
- David Paydarfar
- Eugene Ie
- Fulton Wang
- Ioana Baldini
- Irina-Elena Veliche
- Jason Baldridge
- Jaydeep Borkar
- Joydeep Ghosh
- Julius Adebayo
- Karan Chadha
- Kush R. Varshney
- Larry Lansing
- Lei Yu
- Lorenzo Baraldi
- Marcella Cornia
- Narine Kokhlikyan