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 am deeply passionate about developing AI solutions that are beneficial to society and align with human values. Recently, I graduated from The University of Hong Kong under the supervision of Prof. Ping Luo, and I also spent some of my undergrad semesters at Stanford University and Columbia University as a visiting student. 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.

(More)

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.

News: I will be joining the Learning & Adaptive Systems Group led by Prof. Andreas Krause at ETH as a direct PhD in Fall 2022. I’m greateful to receive support from the Open Phil AI Fellowship and the Vitalik Buterin PhD Fellowship.

Recent Publications

Arch-Graph: Acyclic Architecture Relation Predictor for Task-Transferable Neural Architecture Search (CVPR2022)

Minbin Huang, Zhijian Huang, Changlin Li, Xin Chen, Hang Xu, Zhenguo Li, Xiaodan Liang

[Paper]

An Empirical Investigation of Representation Learning for Imitation (NeurIPS2021) Undergraduate thesis

Xin Chen*, Sam Toyer*, Cody Wild*, Scott Emmons, Ian Fischer, Kuang-Huei Lee, Neel Alex, Steven H Wang, Ping Luo, Stuart Russell, Pieter Abbeel, Rohin Shah

[Paper] [Code] [Talk]


Exploring Geometry-aware Contrast and Clustering Harmonization for Self-supervised 3D Object Detection (ICCV2021)

Hanxue Liang*, Dapeng Feng*, ChenHan Jiang, Xin Chen, Hang Xu, Xiaodan Liang, Zhenguo Li, Wei Zhang, Luc Van Gool

[Paper]


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]


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]

Blog Posts

Suggestions on Research-based Thesis