Beihang University
Tsinghua University
Peiyi WangResearcher
DeepSeek
Researcher
via DeepSeek
Researcher
Zhihong Shao
ZS
Research Scientist at DeepSeek
Shao is a researcher at DeepSeek known for DeepSeekMath and for co-developing Group Relative Policy Optimization (GRPO), a reinforcement-learning method central to recent reasoning models. He is a research scientist at DeepSeek.
See something inaccurate or outdated?
Background
Current role
Research ScientistDeepSeek
DeepSeekPreviously
About this data
Work and education history is primarily focused on AI-relevant roles and may not be comprehensive.
Last editorial review: August 13, 2026Citation Trend
2 snapshots34,220citations as of Jun 15, '26+23,170 since Aug 25, '25
For today’s citation count and citations per paper, visit Google Scholar.