Yuhao Zhang 张煜皓

About Me

I am a second-year PhD student in computer science at the University of Wisconsin–Madison. I am now doing research at madPL group, supervised by Loris D'Antoni and Aws Albarghouthi. I received my B.S. in Computer Science at Peking University (PKU) in 2019, supervised by Yingfei Xiong.

I am good at algorithms and data structures. I was one of the teaching assistants of Algorithm Design and Analysis in 2018 spring semester. I was a contestant of ACM-ICPC and I had won four gold medals at Regional and China-Final contests. When I was in high school, I won a gold medal at the National Olympiad of Informatics.

Here is my CV.

Research Interest

My main research interest is software engineering and programming languages, especially program analysis and program synthesis. One goal of my research is to develop formal methods for trustworthy deep learning. Specifically, I am interested in developing formal methods to certify and improve the robustness of neural networks and verify the correctness of deep learning software.

Publications

• Robustness to Programmable String Transformations via Augmented Abstract Training
  Yuhao Zhang, Aws Albarghouthi, Loris D'Antoni
  To appear at International Conference on Machine Learning (ICML 2020)
  Github
• Detecting Numerical Bugs in Neural Network Architectures
  ACM SIGSOFT Distinguished Paper Award
  Yuhao Zhang, Luyao Ren, Liqian Chen, Yingfei Xiong, Shing-Chi Cheung, Tao Xie
  To appear at ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE 2020)
  Github
• An Empirical Study on TensorFlow Program Bugs
  Yuhao Zhang, Yifan Chen, Shing-Chi Cheung, Yingfei Xiong, Lu Zhang
  ISSTA 2018 Proceedings of the 27th ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA 2018)
  Github

• Certified Robustness to Programmable Transformations in LSTMs
  Yuhao Zhang, Aws Albarghouthi, and Loris D'Antoni
  Github
• MULDEF: Multi-model-based Defense Against Adversarial Examples for Neural Networks
  Siwakorn Srisakaokul, Yuhao Zhang, Zexuan Zhong, Wei Yang, Tao Xie, and Bo Li
  

Honors

• Top 10 undergraduate thesis (School of EECS, Peking University)
• ACM-ICPC gold medals
• Xi’an Regional 2017, Ho-Chi-Minh City Regional 2017 (4th place);
• Dalian Regional 2016, Yangon Regional 2016 (7th place), China-Final 2016;
• Hefei Regional 2015.
• Scholarships
• SenseTime Scholarship (2019, SenseTime);
• Suzhou Industrial Park Scholarship (2017-2018, Peking University);
• Schlumberger Scholarship (2016-2017, School of EECS, Peking University);
• iPinYou Scholarship (2015-2016, School of EECS, Peking University).

Service

• FoMLAS 21, Program Committee
• CAV 21, Artifact Evaluation Committee
• ICML 21, Reviewer

Some Things

I love swimming. My best record of 2km-swimming is 42 minutes. I find swimming is a good way to ease my anxiety. Currently, I focus on keeping fit and I go to gym three times a week. I also love cooking. I hope that I could open a blog to record my dishes throughout my PhD study. Yo estudio español.

My girlfriend Haotang Liu has her lovely personal website.

Contact

1210 W. Dayton Street, Room 6352

yuhaoz ~at~ cs ~dot~ wisc ~dot~ edu