1. About Me
  2. Papers
  3. Teaching Fellow
  4. Other Skills
  5. Selected Awards
  6. Contact Me

About Me

Hi! My name is Tianle Liu (/tʰjɛn1 lɤ4 ljoʊ2/, Tyler, 刘天乐 or 劉天樂). I am joining the Department of Statistics and Operations Research at UNC Chapel Hill as an Assistant Professor in July 2026. Previously, I worked as a postdoctoral fellow in computational pathology under the supervision of Georg Gerber at Brigham and Women’s Hospital. I obtained my Ph.D. degree in statistics from Harvard University in 2025, advised by Natesh S. Pillai, Morgane Austern, and Xiao-Li Meng. Prior to that, I finished my undergrad in pure and applied mathematics at Tsinghua University in 2020, where I worked with Mingsheng Long and Hanzhong Liu. In 2024, I did a summer intern as a quant researcher at Citadel Securities in Miami. In 2019, I visited Wharton School, University of Pennsylvania (hosted by Edgar Dobriban), and Simons Institute, UC Berkeley.

My research lies at the interface of probabilistic modeling and representation learning. I am interested in uncovering latent structure and complex dependence in high-dimensional, heterogeneous, and partially observed systems, with particular motivation from biological and financial systems. My work spans probability, statistical inference, machine learning, and their applications. Within probability, I am interested in limit theorems under dependence, random matrix, and Markov chain mixing. For machine learning, I am currently interested in understanding generative models and AI agents.

Papers

* denotes equal contribution or alphabetical order.

  • Yu Cheng, T. Liu.
    Generative AI for Subgrid Turbulence in Large-Eddy Simulations. In revision at Physical Review Fluids, 2026+.

  • T. Liu, Xiao-Li Meng, Natesh S. Pillai.
    A Heavily Right Strategy for Statistical Inference with Dependent Studies in Arbitrary Dimensions. In revision at Journal of the American Statistical Association, 2026+. Link

  • Morgane Austern*, Yuanchuan Guo*, Zheng Tracy Ke*, T. Liu*.
    Poisson-Process Topic Model for Integrating Knowledge from Pre-trained Language Models. Journal of the American Statistical Association, 2026+.

  • T. Liu, Morgane Austern.
    Wasserstein-\(p\) Bounds via Cumulant-Based Edgeworth Expansions for \(\alpha\)-Mixing Random Fields. Submitted, 2026+. Link

  • Kenneth Li, T. Liu, Naomi Bashkansky, David Bau, Fernanda Viégas, Hanspeter Pfister, Martin Wattenberg.
    Measuring and Controlling Instruction (In)Stability in Language Model Dialogs. Conference on Language Modeling (COLM), 2024. Oral (7.3%). Link

  • T. Liu, Promit Ghosal, Krishna Balasubramanian, Natesh S. Pillai.
    Towards Understanding the Dynamics of Gaussian-Stein Variational Gradient Descent. Neural Information Processing Systems (NeurIPS), 2023. Link

  • T. Liu, Morgane Austern.
    Wasserstein-\(p\) Bounds in the Central Limit Theorem Under Local Dependence. Electronic Journal of Probability, 2023. Link

  • Xin Lu, T. Liu, Hanzhong Liu, Peng Ding.
    Design-Based Theory for Cluster Rerandomization. Biometrika, 2023. Link

  • Yuchen Zhang*, T. Liu*, Mingsheng Long, Michael I. Jordan.
    Bridging Theory and Algorithm for Domain Adaptation. International Conference on Machine Learning (ICML), 2019. Spotlight (4.6%). Link

Teaching Fellow

  • STAT 210: Probability Theory (2021 Fall)
  • STAT 111: Introduction to Statistical Inference (2022 Spring)
  • STAT 185: Introduction to Unsupervised Learning (2022 Fall)
  • STAT 170: Quantitative Analysis of Capital Markets (2023 Spring)

Other Skills

  • Languages: Mandarin Chinese (native), English (fluent).
  • Coding: Python (NumPy, SciPy, Pandas, PyTorch), R, JavaScript, OCaml, Wolfram, C/C++; HTML/CSS, Shell, \(\mathrm{\LaTeX}\).
  • Hobbies: Badminton, Bodybuilding, Chinese Calligraphy, Painting & Sketching, Tennis.

Please check out this fun page if you want to learn more about my hobbies.

Selected Awards

Contact Me

tylerliuthu [at] gmail [dot] com