Summary

Currently employed at UCLA. A PhD Candidate in Biostatistics.

Education

• Doctor of Philosophy (PhD) in Biostatistics
  University of California, Los Angeles

  Courses: Uncertainty in LLMs, Agent-based AI
• Master of Science in Computer Science

  2024-05-01
  Northeastern University

  GPA: 4.0

  Courses: Algorithm, Distributed Database
• Master of Science in Statistics and Operations Research

  2020-06-01
  University of North Carolina at Chapel Hill

  Courses: Applied Statistics, Machine Learning, Time Series Forecasting

Work Experience

• Software Engineer Intern

  2024-06-01 - 2024-08-01
  Amazon

  • Developed key features for Amazon B2B in AWS platform to automate event-driven applications using EventBridge
  • Implemented enhancements in the Visibility Service using Java, JavaScript and TypeScript, improving real-time tracking and monitoring of important business transactions across the platform
  • Conducted integration tests for all Outbound services and events, ensuring smooth and error-free deployment
  • Designed and tested dashboards using CloudWatch to monitor service performance metrics
• Data Scientist

  2021-02-01 - 2022-08-01
  ByteDance Ltd.

  • Collaborated with cross-function team to deploy dynamic subscription tool to improve customer experience in platform
  • Verified product feasibility and deployed XGBoost model to select the important indicators for customers to help design product features
  • Applied interrupted time series to estimate the potential revenue impact, and evaluate the risk of restricting creator's quotes strategy in advance
  • Conducted attribution analysis to evaluate marketing campaign performance which provided powerful evidence to spur on product marketing
• Data Scientist

  2020-08-01 - 2020-12-01
  Blingby

  • Built data ETL pipelines through Apache Spark to transform raw data into features by combining business sense and statistical knowledge
  • Developed, maintained web-based dashboards with Tableau to update daily data analysis report, which increased 20% daily work efficiency
• Machine Learning Intern

  2020-06-01 - 2020-08-01
  TouchSuite

  • Queried and cleaned terabyte-sized order data from Azure SQL using pyodbc
  • Conducted online analytical processing (OLAP) to display critical sales performance from different dimensions
  • Developed item-based approaches to handle cold-start problems and tuned the model hyper-parameters through SparkML cross-evaluation toolbox which reduced root mean square errors by 10%

Skills

Publications

• Multi-Layer Kernel Machines: Fast and Optimal Nonparametric Regression with Uncertainty Quantification

  2024
  Under R&R at Journal of Machine Learning Research (JMLR)

  Wenlu Xu†, Tong Zhu†, Huiying Zhong, and Xiaowu Dai. [Code]

  View Publication
• Common-Agency Games for Multi-Objective Test-Time Alignment

  2026
  Preprint

  Baiting Chen†, Tong Zhu†, Rui Yu†, and Xiaowu Dai. A game-theoretic framework for multi-objective test-time alignment of language models. [Code]

  View Publication
• Mechanism Design Meets Large Language Models: Foundations and Frontiers

  2026
  Preprint

  A survey paper by Baiting Chen, Tong Zhu, Xuanang Li, Yichi Zhang, and Xiaowu Dai exploring the intersection of mechanism design theory and large language models. [Code]

  View Publication
• Incentivizing Truthful Language Models via Peer Elicitation Games

  2025
  NeurIPS 2025

  This paper introduces Peer Elicitation Games (PEG), a training-free, game-theoretic framework for aligning LLMs.

  View Publication
• Competitive Multi-Agent Delegation For LLM Reasoning
  Submitted to ICML 2025

  This paper introduces COMMAND, a competitive multi-agent delegation framework that treats LLM reasoning as a principal-agent delegation process, using competition and alignment incentives to elicit higher-quality answers.

  View Publication
• LightAgent: Production-level Open-source Agentic Al Framework

  2025
  arXiv preprint

  This paper propose LightAgent, a lightweight, open-source agentic framework that balances flexibility and simplicity by integrating core functionalities like Memory, Tools, and Tree of Thought.

  View Publication

Teaching

• Biostat M257

  2026
  University of California, Los Angeles, Biostatistics Department

  Role: TA

  Statistical Computing — Computational algorithms for research in (bio)statistics, including numerical linear algebra and optimization.
• Biostat 406

  2026
  University of California, Los Angeles, Biostatistics Department

  Role: TA

  Applied Multivariate Biostatistics — Use of multiple regression, principal components, factor analysis, discriminant function analysis, logistic regression, and canonical correlation in biomedical data analysis.
• Biostat 231

  2026
  University of California, Los Angeles, Biostatistics Department

  Role: TA

  Statistical Power and Sample Size Methods for Health Research — Sample size and power analysis methods for common study designs, including comparisons of means and proportions, ANOVA, time-to-event data, group sequential trials, linear regression, cluster randomized trials and multilevel data.
• Biostat 285

  2026
  University of California, Los Angeles, Biostatistics Department

  Role: TA

  Advanced Topics: Recent Developments — Advanced topics and developments in biostatistics not covered in other courses. Possible topics include time-series analysis, classification procedures, correspondence analysis, etc.
• Biostat 203A

  2025
  University of California, Los Angeles, Biostatistics Department

  Role: TA

  Introduction to Data Management and Statistical Computing
• Biostat 201

  2025
  University of California, Los Angeles, Biostatistics Department

  Role: TA

  Topics in Applied Regression

Portfolio

• Portfolio item number 1
  Portfolio

  Short description of portfolio item number 1
  

  View Project

Interests