YaGuang Li
Principal Research Scientist @ Google DeepMind
About
I am a Principal Research Scientist at Google DeepMind, working on large language models, post-training, and reinforcement learning (RL) scaling for advanced reasoning.I currently work on Gemini DeepThink, with a focus on improving reasoning capabilities through post-training and efficient RL scaling. Previously, I co-led the fine-tuning efforts for Gemini 1.0 and Gemini 1.5, and contributed to LaMDA and PaLM 2 across pretraining, instruction tuning, and efficient serving.I received my Ph.D. in Computer Science from the University of Southern California, advised by Prof. Cyrus Shahabi and Prof. Yan Liu. My research interests span machine learning, large language models, and deep learning on graphs, including spatiotemporal forecasting, relational inference, and intelligent transportation systems.
United States
San Francisco Bay Area
Computer Software
-
Experience
Principal Research Scientist
Google DeepMind
San Francisco Bay Area
Gemini 3 DeepThink and RL Scaling.
Senior Staff Research Scientist
Google DeepMind
San Francisco Bay Area
- Co-led RL scaling efforts for advanced reasoning, contributing to models achieving ICPC 2025 World Finals Gold, IMO 2025 Gold and IMO 2024 Silver. - Core contributor of Gemini 2.0, 2.5, 3.0, 3.1.
Staff Research Engineer
Google DeepMind
Mountain View, CA
- Co-lead of Bard/Gemini 1.0 Finetuning: https://goo.gle/GeminiPaper - Co-lead of Gemini 1.5 Finetuning, https://arxiv.org/abs/2403.05530 - Pre-training and optimization for PaLM-2.
Senior Research Engineer, Google Brain
Mountain View, CA
- Lead the serving and efficiency work of LaMDA and Bard. - Core contributor of LaMDA and PaLM 2 Pretraining and efficiency.
Research Engineer
San Francisco Bay Area
AutoML (automated machine learning) for Time-series forecasting.
Software Engineer Intern
Menlo Park, Californina
Applied Machine Learning.
Software Engineer Intern
Greater New York City Area
Research Intern
Montreal, Canada Area
Education
University of Southern California
Computer Science
Deep learning on graphs; spatiotemporal prediction; time-series forecasting Dissertation: Spatiotemporal Prediction with Deep Learning on Graphs Advisors: Prof. Cyrus Shahabi and Prof. Yan Liu Annenberg Graduate Fellowship
University of Chinese Academy of Sciences
Computer Science
National Scholarship; Outstanding Graduate; Model Merit Student Award (Top 1%)
YaGuang Li's Contact Information
Phone
Find the Right Leads
Find Verified Contact Data
What LeadContact does well
Find verified emails, phone numbers, and decision-makers with 98% accuracy.
Find Leads
Find the right people by company, role, industry, location, and more.
925M+ professional profiles
Find Emails
Access verified email addresses for your target contacts.
657M+ emails
Find Phone Numbers
Get cross-validated phone data from multiple top sources.
239M+ phone numbers
More Accurate. Lower Cost.
Find contact data in 1 tool with 98% accuracy
LeadContact integrates leading enrichment tools to deliver more accurate contact data—without paying for each one.
Great conversations start with the right contact.
It’s time to find yours.