Yong Zheng-Xin

I am a final-year PhD student at Brown University, advised by Stephen Bach. I am fortunate to be supported by the Open Philanthropy (now Coefficient Giving) grant for technical AI safety.

I am currently an Astra Safety Research Fellow with OpenAI, mentored by Miles Wang and Olivia Watkins.

Google Scholar X LinkedIn

Research

I spend a lot of time thinking about safe and beneficial AI, with the current focus on AGI preparedness. I previously worked on multilingual LLMs so that existing AI systems benefit everyone equitably and safely, and now I want to make sure future AI systems would be aligned.

My current research interests include:

CoT oversight such as CoT monitorability and controllability.
Frontier risk and preparedness evaluations such as Kimi K2.5 safety and preparedness report (preprint 2026).
Understanding why alignment does or does not generalize (EMNLP 2024; ICLR 2026).
Adversarial robustness to (multilingual) jailbreaks (Best Paper @ NeurIPS 2023 SoLaR; NAACL 2025).

Some previous work on multilingual LLMs: ACL 2023; Best Paper @ ACL 2024; INTERSPEECH 2025.