Xin Chen, Cynthia

Xin Chen, Cynthia

Hi! I’m currently working with Prof. Stuart Russell’s group at UC Berkeley on Beneficial AI research. I recently graduated from The University of Hong Kong, and I’ve spent my time at Stanford University and Columbia University as a visiting student. I am deeply passionate about developing AI systems that are beneficial to society and align with human values. You can call me Cynthia or Chen Xin (陈欣). My current research interests span across:

  • Improving robustness and reliability in decision making algorithms (reinforcement learning / imitation learning),
  • Safe exploration, and
  • Representation learning.

To help with growing the AI alignment research field, I am among the main organizers of SafeAI workshop at AAAI and AISafety workshop at IJCAI. I am grateful to be supported by HKU Foundation Scholarship (ranked top 0.02% in Chinese National College Entrance Exam, Gaokao). The best way to reach me is through my email cyn0531 AT connect DOT hku DOT hk.


Out of my concern for poverty, animal, and climate change, I donate a considerable portion of my income to the most effective charities every year. I enjoy reading, playing the piano, and marathon running outside of my academic pursuits.

Recent Publications

CATCH: Context-based Meta Reinforcement Learning for Transferrable Architecture Search (ECCV2020)

Xin Chen*, Yawen Duan*, Zewei Chen, Hang Xu, Zihao Chen, Xiaodan Liang, Tong Zhang, Zhenguo Li

[Paper] [Website]

TransNAS-Bench-101: Improving transferability and Generalizability of Cross-Task Neural Architecture Search (CVPR2021)

Yawen Duan*, Xin Chen*, Hang Xu, Zewei Chen, Xiaodan Liang, Tong Zhang, Zhenguo Li

[Paper] [Benchmark]