Xiangyu Qi
OpenAI
—
Member of Technical Staff
Links
Focus
Scalable Oversight, Control, Monitoring, Interpretability, Adversarial Robustness, Red-Teaming, Alignment Training, Security, Scheming and Deception, Multi-Agent Safety
Stream
OpenAI Safety Team
Xiangyu is a researcher at OpenAI, where he works to make LLMs robust. Previously, he obtained his Ph.D. from Princeton University, advised by Prof. Prateek Mittal and Prof. Peter Henderson.