I’m a second year PhD student in the computer science department at the University of California, Santa Barbara (UCSB). I am glad to have professor William Yang Wang as my advisor. I am interested in improving the robustness and generalizability of machine learning algorithms, especially deep learning algorithms. My research currently focuses on causality based methods and the application to NLP tasks.


  • University of California, Santa Barbara, Oct 2020 - Present
    • Ph.D. in Computer Science
  • Hong Kong University of Science and Technology, Sep 2016 - Jul 2020
    • B.Sc. in Applied Mathematics and Computer Science
  • University of California, Los Angeles, Sep 2019 - Dec 2019
    • Fall quater exchange

Scholarships and Academic Honors

  • Chern Class Talent Scholarship (2017 - 2020) from HKUST Math department
  • Chern Class Achievement Scholarship (2020) from HKUST Math department
  • The 15th Epsilon Fund Award (2020) from HKUST Math department
  • University’s Scholarship Scheme for Continuing Undergraduate Students (2017 - 2020) from HKUST
  • Reaching Out Award (2019 - 2020) from HKSAR Government Scholarship Fund
  • Joseph Needham Merit Scholarship (2020) from the Joseph Needham Foundation for Science & Civilisation (Hong Kong)
  • Academic Excellence Fellowship (2020) from UCSB


  • Causal Balancing for Domain Generalization

    Xinyi Wang, Michael Saxon, Jiachen Li, Hongyang Zhang, Kun Zhang, William Yang Wang

    Preprint [paper]

  • Relation Leakage in Elicited Natural Language Inference Datasets

    Michael Saxon, Xinyi Wang, Wenda Xu, William Yang Wang

    Preprint [paper]


  • A Dataset for Answering Time-Sensitive Questions

    Wenhu Chen, Xinyi Wang, William Yang Wang

    Proceedings of NeurIPS 2021 Datasets and Benchmarks Track, Virtual (poster) [paper][code]

  • Counterfactual Maximum Likelihood Estimation for Training Deep Networks

    Xinyi Wang, Wenhu Chen, Michael Saxon, William Yang Wang

    Proceedings of NeurIPS 2021, Virtual (poster) [paper][code]

  • Modeling Discolsive Transparency in NLP Application Descriptions

    Michael Saxon, Sharon Levy, Xinyi Wang, Alon Albalak, William Yang Wang

    Proceedings of EMNLP 2021, Virtual (oral) [paper][code]

  • RefBERT: Compressing BERT by Referencing to Pre-computed Representations

    Xinyi Wang*, Haiqin Yang*, Liang Zhao, Yang Mo and Jianping Shen

    Proceedings of IJCNN 2021, Virtual (oral) [paper]

  • Neural Topic Model with Attention for Supervised Learning

    Xinyi Wang, Yi Yang

    Proceedings of AISTATS 2020, Virtual (poster) [paper][code]

* indiacts equal contribution


  • 2021 Program Committee: NeurIPS Datasets and Benchmarks Track