All people
Aaron Defazio portrait

Researcher

Aaron Defazio

Member of Technical Staff at OpenAI

Defazio develops methods that make AI models easier to train. He co-created Schedule-Free learning, which removes the need to plan how training speeds change over time, and D-Adaptation, which automatically tunes the size of learning steps. His work reduces the manual trial and error involved in training models.

Career & education

Current role
Sep 2026-present
Member of Technical Staff
Previously
May 2017-2026
Research Scientist, FAIR

Work and education history is primarily focused on AI-relevant roles and may not be comprehensive.

Citation Trend

Total citations to scholarly work, including research papers, technical reports, books and theses, as recorded by Google Scholar. Each point is a dated snapshot.
1 snapshots
Citation snapshot on Oct 6, '268,416Oct 6, '26
citations8,416As of Oct 6, '26
For today’s citation count and per work, visit Google Scholar.

Updates 1

About this profile

Based on public sources. If accuracy is important, verify details using the links or references.

For corrections, updates, or requests to remove information, contact us.

Reviewed October 6, 2026 · Checked for accuracy and new information.

Sharing card