Sharif University of Technology
University of Barcelona
Université de Montréal
Agnieszka Grabska BarwińskaSenior Research Scientist · Google DeepMindResearcher↗
Researcher
Mehdi Mirza
Google DeepMindResearch Scientist
Mirza co-authored the original generative adversarial networks paper, in which one model learns to create data by trying to fool another.[1] With Simon Osindero, he introduced conditional GANs, letting users guide what a model generates—for example, requesting a particular digit or image category.[2]
Career & education
Current role
Research Scientist
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.
citations273,748As of Nov 1, '26
citations+3,780Since last snapshot, Oct 1, '26
Selected contributions
Generative Adversarial Networks
With Ian Goodfellow, Jean Pouget-Abadie, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville and Yoshua BengioGANs pit two networks against each other: one creates examples while the other learns to spot fakes.
References
- Generative Adversarial Networks — original paperarxiv.org
Mirza co-authored the original generative adversarial networks paper, in which one model learns to create data by trying to fool another.
- Conditional Generative Adversarial Nets — Mirza and Osinderoarxiv.org
With Simon Osindero, he introduced conditional GANs, letting users guide what a model generates—for example, requesting a particular digit or image category.
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 August 7, 2026 · Checked for accuracy and new information.
