I am a second-year Ph.D. student in the Department of Computer Science and Technology, Tsinghua University, China, advised by Prof. Jun Zhu and Prof. Ting Chen. My research interests lie on the intersection of computer vision, reinforcement learning and deep learning. I have also spent time working at Sensetime Inc., Tencent AI Lab and Carnegie Mellon University.

Recent publications

For a full list, please see my Publications page.
For pre-prints, please see my ArXiv page.

For a complete list, please see my Google Scholar page.

  • Combo-Action: Training Agent For FPS Game with Auxiliary Tasks is accepted by AAAI-19 Workshop on Reinforcement Learning in Games.

  • Expecting the Unexpected: Training Detectors for Unusual Pedestrians with Adversarial Imposters is accepted by Vision Meets Cognition Workshops 2017.
  • Projects

    For more projects, please see my Projects page.
    • We won the first place in Track1 and second place in Track2 of ViZDoom 2018 AI Competition in August.
    • We won the second place in Track2 of ViZDoom 2017 AI Competition.


    • 2017 Tsinghua Excellent Graduates, Tsinghua University
    • 2014-2016 Academic Excellence Award, Tsinghua University


    huangsy13 [at] gmail (dot) com

    Tsinghua University, FIT building 1-509, Beijing, China, 100084

    [GitHub]         [Linkedin]         [知乎]        [微博]        [微信公众号: TART AI]