All people

Researcher

Yong Zheng-Xin

Yong Zheng-Xin portrait

Member of Technical Staff, RSI preparedness/safety at OpenAI

Yong studies how advanced AI systems can fail after training and how researchers can catch those failures before deployment. His work includes tests of frontier-model risks, methods for monitoring hidden reasoning, and award-winning research showing that safety protections can break across languages.

See something inaccurate or outdated?

Background

Current role
Member of Technical Staff, RSI preparedness/safety Aug 2026-present
Previously
Jan 2026-Jun 2026Astra Fellow,
About this data

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

Last editorial review: August 20, 2026

News 1

moveAI safety researcher Yong Zheng-Xin joins OpenAI

After completing his Brown PhD and an Astra fellowship at OpenAI, Yong returned as a full-time member of technical staff working on safety and preparedness.

August 16, 2026

Citation Trend

1 snapshots
Citation snapshot on Aug 20, '269,649Aug 20, '26
9,649citations as of Aug 20, '26
For today’s citation count and citations per paper, visit Google Scholar.

You may also be interested in