Hi! I’m currently a PhD student at ETH Zurich, jointly supervised by Prof. Andreas Krause and Prof. Florian Tramèr. I believe that ensuring increasingly powerful AI benefits humanity rather than causing harm is one of the most important challenges of our time. I previously graduated from The University of Hong Kong, and I also spent some time at UC Berkeley (Center for Human-Compatible AI), Stanford University and Columbia University prior to ETH. You can call me Cynthia or Chen Xin (陈欣). My current research interests span across:

• Technical AI governance,
• The science of LLM (mis)alignment, and
• The science of evaluation.

I am grateful to be supported by the Open Phil AI Fellowship and the Vitalik Buterin PhD Fellowship for my research.

I believe coordinated global efforts are crucial to mitigate the risks of AI, hence I help organize the International Dialogues on AI Safety. The best way to reach me is through my email xin.chen@inf.ethz.ch.

For prospective students who would like to work with me, please apply through the LAS Group student projects page or fill out this form if you are outside of ETH. Due to a large amount of inquiries, I might not be able to read and respond to every individual email asking for supervision.