Yuhao Zhang

Yuhao Zhang

He/him/his

Ph.D. student in Computer Science

University of Wisconsin-Madison

yuhaoz@cs.wisc.edu

I am an applied scientist at Amazon Q Developer.

I was on the academic job market! Here are my statements: [Research Statement], [Teaching Statement], [Diversity Statement].

Welcome! I'm Yuhao. I got my Ph.D. in computer science at the University of Wisconsin–Madison, conducting research at the madPL group, under the guidance of Prof. Loris D'Antoni and Prof. Aws Albarghouthi. I received my B.S. in Computer Science at Peking University (PKU) in 2019, mentored by Prof. Yingfei Xiong.

I am good at algorithms and data structures. 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.

My primary research focuses on the fields of software engineering, programming languages, and deep learning. The goal of my research is to provide provable guarantees for deep learning, ensuring its safety, security, and reliability via formal methods. I am also interested in integrating program synthesis with deep learning techniques, such as large language models, to generate programs in a interpretable and verifiable manner.

Research Summary

The goal of my research is to provide provable guarantees for deep learning, ensuring its safety, security, and reliability via formal methods.

Publications

  • A One-Layer Decoder-Only Transformer is a Two-Layer RNN, With an Application to Certified Robustness

    Yuhao Zhang, Aws Albarghouthi, Loris D’Antoni

    PrePrint

  • CodeFort, Robust Training for Code Generation Models

    Yuhao Zhang, Shiqi Wang, Haifeng Qian, Zijian Wang, Mingyue Shang, Linbo Liu, Sanjay Krishna Gouda, Baishakhi Ray, Murali Krishna Ramanathan, Xiaofei Ma, Anoop Deoras

    PrePrint

  • PECAN, A Deterministic Certified Defense Against Backdoor Attacks

    Yuhao Zhang, Aws Albarghouthi, Loris D’Antoni

    PrePrint

  • Verified Training for Counterfactual Explanation Robustness under Data Shift

    Anna P. Meyer*, Yuhao Zhang*, Aws Albarghouthi, Loris D’Antoni

    The 5th Workshop on Data-Centric Machine Learning Research (DMLR 2024@ICLR)
    Github

  • Reliability Assurance for Deep Neural Network Architectures Against Numerical Defects

    Linyi Li, Yuhao Zhang, Luyao Ren, Yingfei Xiong, Tao Xie

    45th International Conference on Software Engineering (ICSE 2023)
    Github

  • BagFlip: A Certified Defense Against Data Poisoning

    Yuhao Zhang, Aws Albarghouthi, Loris D’Antoni

    Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS 2022)
    Github

  • Overwatch: Learning Patterns in Code Edit Sequences

    Yuhao Zhang*, Yasharth Bajpai*, Priyanshu Gupta*, Ameya Ketkar*, Miltiadis Allamanis, Titus Barik, Sumit Gulwani, Arjun Radhakrishna, Mohammad Raza, Gustavo Soares, and Ashish Tiwari

    Object-Oriented Programming, Systems, Languages & Applications (OOPSLA 2022)
    Video

  • Certified Robustness to Programmable Transformations in LSTMs

    Yuhao Zhang, Aws Albarghouthi, Loris D’Antoni

    The 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP 2021)
    Oral Presentation
    Github Video

  • Detecting Numerical Bugs in Neural Network Architectures

    Yuhao Zhang, Luyao Ren, Liqian Chen, Yingfei Xiong, Shing-Chi Cheung, Tao Xie

    ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE 2020)
    ACM SIGSOFT Distinguished Paper Award
    Github Video

  • Robustness to Programmable String Transformations via Augmented Abstract Training

    Yuhao Zhang, Aws Albarghouthi, Loris D’Antoni

    International Conference on Machine Learning (ICML 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

    • News

    [2024-06-14] I graduated with a PhD in Computer Science
    [2023-11-19] I am a top reviewer at NeurIPS 2023
    [2023-10-06] I give a talk at MWPLS 2023.
    [2023-07-28] I give a joint talk with my advisor Aws at WFVML 23.
    [2023-05-22] I start my summer internship at AWS CodeWhisperer.

    Awards

    Recognized as a top reviewer for NeurIPS 2023 (2023, NeurIPS)
    Midwest Programming Languages Summit Travel Awards (2023, MWPLS)
    Recognized as a top reviewer for NeurIPS 2022 (2022, NeurIPS)
    Selected as a (top-ten) finalist for Two Sigma PhD Fellowship (2022, Two Sigma)
    ACM SIGSOFT Distinguished Paper Award (2020, FSE)
    Top 10 undergraduate thesis (2019, School of EECS, Peking University)
    SenseTime Scholarship (2019, SenseTime)
    Suzhou Industrial Park Scholarship (2018, Peking University)
    ACM-ICPC 4-th place (2017, Asia Pacific Regional, Ho-Chi-Minh City Site)
    ACM-ICPC gold medal (2017, Asia East Continent Regional, Xi’an Site)
    Schlumberger Scholarship (2017, School of EECS, Peking University)
    ACM-ICPC gold medal (2016, Asia East Continent Final, Shanghai, China)
    ACM-ICPC 7-th place (2016, Asia Pacific Regional, Yangon Site)
    ACM-ICPC gold medal (2016, Asia East Continent Regional, Dalian Site)
    iPinYou Scholarship (2016, School of EECS, Peking University)
    ACM-ICPC gold medal (2015, Asia East Continent Regional, Hefei Site)

    Service

  • NeurIPS 2023, 2022, Reviewer
  • ICML 2023, 2022, 2021, Reviewer
  • WFVML 2023, Reviewer
  • FoMLAS 2023, 2022, 2021, Program Committee
  • BANDS 2023, Program Committee
  • VMCAI 2023, Artifact Evaluation Committee
  • CAV 2021, Artifact Evaluation Committee
  • Wrote a tutorial on requesting CPT for international students in the CS department at UW-Madison.

    • Personal

    🧗 I fell in love with indoor bouldering during my Ph.D. and have climbed once to twice a week since May 2022. I won the third place in the beginner category of the 2023 climbing competition in UW-Madison! I’m tackling V3-V5 routes and will continue improving and practicing in the coming years.
    When I’m not hanging from cliffs, I usually hit the gym about three to four times a week since September 2021. After cutting nearly 20 pounds of pandemic weight gain, I embarked on a body-fat-cutting journey in April 2023. I achieved the single-digit-body-fat goal in September of the same year and shifted to clean bulking mode afterward.
    But it’s not all about physical pursuits for me. I’ve been immersing myself in (non-CS) books since September 2021, dedicating more than one hour every day to reading. I love reading novels by Fyodor Dostoevsky and writers Lationamericano like as Mario Vargas Llosa and Gabriel García Márquez. On the other side, I delved into Lacanian Psychoanalysis and am currently studying the German Idealism Philosophy of Hegel. My journey won’t stop there; I’m eager to explore Phenomenology, courtesy of Husserl and Merleau-Ponty, and (post-) structuralism critique of ideology by Althusser.

    Contact