my_photo.jpg

Muhang Tian

Computer Science PhD Student
Courant Institute of Mathematical Sciences
New York University
60 Fifth Avenue, New York, NY 10011

I am a second-year computer science PhD student at NYU Courant and CILVR group, advised by Sherry Yang. I am currently interested in designing cost-aware agents for tasks where actions spend resources. Examples of such tasks include machine learning engineering and robotics.

Previously, I obtained my BS in Computer Science with a double minor in Mathematics and Economics at Duke University, where I received Graduation with Highest Distinction and Alex Vasilos Memorial Award. At Duke, I was very fortunate to work with Cynthia Rudin, Brandon Fain, and Anru Zhang.

My hobbies include playing Bayan accordion, running, and cooking.

News

Sep 25, 2026 Check out our new preprint on Reward-rate Policy Gradient. 🛠️
Jan 21, 2025 Started my PhD at NYU Courant. Look forward to the journey ahead! 🗽
Apr 28, 2024 I am honored to receive Alex Vasilos Memorial Award and Graduation with Highest Distinction at Duke University. 🔵😈🎉

Publications

* denotes equal contribution

2026

  1. Preprint
    Reward-rate Policy Gradient for Efficient Machine Learning Engineering Agents
    Muhang Tian, and Sherry Yang
    PDF arXiv Code Website

2025

  1. AAMAS
    Multi-objective Reinforcement Learning with Nonlinear Preferences: Provable Approximation for Maximizing Expected Scalarized Return
    Nianli Peng*, Muhang Tian*, and Brandon Fain
    PDF arXiv Code

2024

  1. JAMIA
    Reliable Generation of Privacy-preserving Synthetic Electronic Health Record Time Series via Diffusion Models
    Muhang Tian, Bernie Chen*, Allan Guo*, Shiyi Jiang, and Anru R Zhang
    PDF arXiv Code
  2. JAMIA
    Fast and Interpretable Mortality Risk Scores for Critical Care Patients
    Chloe Qinyu Zhu*, Muhang Tian*, Lesia Semenova, Jiachang Liu, Jack Xu, Joseph Scarpa, and Cynthia Rudin
    PDF arXiv Code

2023

  1. AAMAS
    Welfare and Fairness in Multi-objective Reinforcement Learning
    Zimeng Fan*, Nianli Peng*, Muhang Tian*, and Brandon Fain
    PDF arXiv Code