Training-method researcherTheoretical researcher
Mohammad Gheshlaghi Azar
Developed IPO, giving preference optimization a theoretical footing distinct from RLHF's reward modeling.
Works in the archive (1) · lead author on 1
“Lead” marks the first-listed author — a byline fact, not a measure of influence; co-authorship is shown as recorded.
Co-authors in the archive
View co-author network (8 people)
Loading graph…