About me

I am currently a principal researcher at Tencent AI Lab, working on machine learning and natural language processing. Before joining Tencent in March 2018, I worked in the Deep Learning Technology Center (DLTC) at Microsoft Research, Redmond, WA. I completed my PhD in Electrical Engineering at University of California, Los Angeles (UCLA), in June 2014, where I worked in Adaptive Systems Laboratory (ASL), supervised by Prof. Ali H. Sayed.

Contact information

Email: chenjianshu at gmail dot com OR jianshuchen at tencent dot com

Research interests

My research interests span several areas, including

  • Machine learning (reinforcement learning, deep learning, unsupervised learning)
  • Natural Language Processing
  • Optimization

For more details, see my publications (also google scholar)

Selected publications

  1. Jianshu Chen, “Learning Language Representations with Logical Inductive Bias”, Proc. International Conference on Learning Representations (ICLR), 2023.
  2. Xiaoman Pan, Wenlin Yao, Hongming Zhang, Dian Yu, Dong Yu, Jianshu Chen, “Knowledge-in-Context: Towards Knowledgeable Semi-Parametric Language Models”, Proc. International Conference on Learning Representations (ICLR), 2023.
  3. Adithya M. Devraj and Jianshu Chen, “Stochastic Variance Reduced Primal Dual Algorithms for Empirical Composition Optimization”, Proc. Advances in Neural Information Processing Systems (NeurIPS), 2019.
  4. Yu Liu*, Jianshu Chen* and Li Deng*, "Unsupervised Sequence Classification using Sequential Output Statistics", Proc. 31st Annual Conference on Neural Information Processing Systems (NIPS), 2017. (*Equal contribution)
  5. Simon Du, Jianshu Chen, Lihong Li, Lin Xiao, Dengyong Zhou, "Stochastic Variance Reduction Methods for Policy Evaluation", Proc. International Conference on Machine Learning (ICML), August 2017.