Princeton University
University of Michigan
Shanghai Jiao Tong University
Lianmin ZhengResearch Scientist · MetaResearcher↗
Researcher
Yanqi Zhou
MetaAI Research Scientist
Zhou helped create T5, which put translation, summarization and other language tasks into a shared text-to-text framework.[1] She also co-developed GLaM and Expert Choice Routing: ways to build larger AI models efficiently by activating selected specialist networks and balancing how much work each receives.[2]
Career & education
Current roleMetaMay 2026-presentAI Research Scientist
MetaMay 2026-presentPreviously
Google DeepMind2023-May 2026Staff Research Scientist
Google Brain2019-2023Senior Research Scientist
Baidu2017-2019Research Scientist, SVAIL
Google DeepMind2023-May 2026Google Brain2019-2023Baidu2017-2019Work 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.
citations53,218As of Nov 7, '26
citations+6,333Since last snapshot, Jun 15, '26
Selected contributions
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
With Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Wei Li and others ·T5 treats language tasks as text input and text output within one framework.
References
- Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformerarxiv.org
T5 coauthorship and unified text-to-text framework for language tasks.
- Mixture-of-Experts with Expert Choice Routingarxiv.org
Coauthorship; sparse expert activation, expert-side token selection and balanced workloads.
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 12, 2026 · Checked for accuracy and new information.
