Jun Zhu
Prof. @ THU
About me

My research focuses on developing statistical machine learning methods to understand complex scientific and engineering data. My current interests are in latent variable models, large-margin learning, Bayesian nonparametrics, and deep learning. Before joining Tsinghua in 2011, I was a post-doc researcher and project scientist at the Machine Learning Department in Carnegie Mellon University. From 2015 to 2018, I was an adjunct faculty at the Machine Learning Department in Carnegie Mellon University.

  • We open-sourced ZhuSuan, a GPU library for Bayesian Deep Learning (a conjoin of Bayesian methods and deep learning) buit on TensorFlow. Check out the white paper and some news reports (in Chinese) for more details.
  • We open-sourced TianShou, an elegant, flexible, and superfast PyTorch deep Reinforcement Learning (RL) library.
  • We open-sourced Ares (Adversarial Robustness Evaluation for Safety), a Python library for adversarial machine learning research focusing on benchmarking adversarial robustness on image classification correctly and comprehensively, together with the CVPR Oral paper.
  • Looking for highly motivated post-docs to work on large-scale machine learning and/or its applications in image, text, and network analysis. Various types of fellowship are avaiable for outstanding applicants, such as Tsinghua Fellowship [doc, link] , Innovation Fellow, and Exchange Program.
  • I was selected as one of "pioneers" by MIT TR35 China, 2017.
  • I recieved the support from the National Youth Top-notch Talent Support Program, 2015.
  • I recieved the "CVIC SE Talents" Award, 2015.
  • I recieved the Best Collaboration Award by Tsinghua-MSRA Joint Research Lab, 2014.
  • I was selected as one of "AI's 10 to Watch" by IEEE Intelligent Systems, 2013.
  • I recieved the "Excellent Young Scholar" Award by NSF of China (NSFC), 2013.
  • I recieved the "CCF Young Scientist" Award by China Computer Federation (CCF), 2013.
Recent publications (full list)

Last updated on Dec. 10th, 2019. Count: .