Yang Sui

I am a Postdoctoral Scholar in the Department of Statistics and Data Science at UCLA, working with Professors Jin Zhou, Hua Zhou, and Xiaowu Dai.

Email: yangsui@ucla.edu

Google Scholar  |  LinkedIn

Current Focus

• AI-Powered Uncertainty Quantification: Reliable inference with AI predictions and limited labels for LLM evaluation and biomedical studies.
• Synthetic Data Generation: Generating tabular data from limited observations and summary statistics for model post-training and biomedical analysis.
• Heterogeneous Data Integration: Integrating diverse populations, data sources, and missingness patterns for efficient biomedical learning.

Selected Manuscripts

Prediction-Powered Conditional Inference
Yang Sui, Jin Zhou, Hua Zhou, Xiaowu Dai
Under major revision at Journal of the Royal Statistical Society: Series B (JRSSB)
[arXiv] [Code]

Partially-shared Imaging Regression on Integrating Heterogeneous Brain-Cognition Associations across Alzheimer's Diagnoses
Yang Sui, Qi Xu, Ting Li, Yang Bai, Annie Qu
Under major revision at Journal of the American Statistical Association (JASA)
[arXiv]

Multi-Task Learning with Covariate-Overlap Regularization
Yang Sui, Qi Xu, Yang Bai, Annie Qu
Under reject and resubmit at Journal of Machine Learning Research (JMLR)
[arXiv] [Code]

Tensor-Based Individualized Treatment Rules for Neuroimaging Applications
Yang Sui, Ting Li, Yuanying Chen, Yang Bai, Hongtu Zhu
Accepted at Annals of Applied Statistics (AOAS)
[Article] [Code]

Multi-Task Learning for Heterogeneous Multi-Source Block-Wise Missing Data
Yang Sui, Qi Xu, Yang Bai, Annie Qu
Journal of Computational and Graphical Statistics (JCGS), 35(3):1131–1139, 2026
[DOI] [Code]

Statistical Inference for LLM Evaluations: From Multiple Auxiliary Predictors to Valid Uncertainty Quantification
Yang Sui, Jin Zhou, Hua Zhou, Xiaowu Dai
Draft available upon request
[Code]

Imperfect AI predictions across data sources reduce uncertainty in individualized treatment decisions
Yang Sui, Bowen Zang, Judong Shen, Devan Mehrotra, Michael Johnson, Xiaowu Dai, Hua Zhou, Jin Zhou
Draft available upon request

For a full list, please refer to my Google Scholar page.

Experience & Education

• Department of Statistics and Data Science, University of California, Los Angeles (UCLA), 2025 – Present
  Postdoctoral Scholar, Advisors: Prof. Jin Zhou, Prof. Hua Zhou, and Prof. Xiaowu Dai
• Department of Statistics, University of California, Irvine (UCI), 2023 – 2025
  Visiting Scholar, Advisor: Prof. Annie Qu
• Shanghai University of Finance and Economics (SUFE), 2020 – 2025
  Ph.D. in Statistics, Advisor: Prof. Yang Bai
• Central South University, 2016 – 2020
  B.S. in Statistics

Selected Honors

• IDRE Postdoctoral Fellowship, UCLA, 2026
• CSFAI Travel Award, 2026
• CAST Young Elite Scientist Sponsorship Program (Doctoral Track), 2025
• National Scholarship, 2024
• Academic Star Award (Nominee), Shanghai University of Finance and Economics, 2023

Reviewer Service

Journals: JASA, AOAS, TMLR, Stat
Conferences: NeurIPS (Top Reviewer, 2026), ICML (Silver Reviewer, 2026), ICLR, AAAI