DU Yihan

Assistant Professor
RESEARCH AREAS
Data Science & Analytics
Machine Learning & AI
Optimisation & Decision Science

Biography

Yihan Du is an Assistant Professor in the Engineering Systems and Design Pillar at the Singapore University of Technology and Design. Her research interests include machine learning, with emphases on reinforcement learning and online learning, and AI safety and alignment. She was a postdoctoral researcher at the University of Illinois at Urbana-Champaign during 2023-2025, working with Prof R Srikant. She obtained her PhD degree in Computer Science from the Institute for Interdisciplinary Information Sciences at Tsinghua University in 2023. She has published multiple first-author papers on the top conferences in machine learning, including ICML, NeurIPS, ICLR and AAAI. She also received several honours, including the China Computer Federation (CCF) Agent and Multi-Agent System Doctoral Dissertation Award, and the Tsinghua Outstanding Doctoral Dissertation Award.

Education
  • PhD in Computer Science, Tsinghua University, China (2018-2023)
  • BE in Computer Science, Xiamen University, China (2014-2018)
Research interests
  • Machine learning, including reinforcement learning (RL) and online learning
  • AI safety and alignment, including reinforcement learning from human feedback (RLHF)
Selected publications
  • Yihan Du, Anna Winnicki, Gal Dalal, Shie Mannor, R. Srikant, “Reinforcement Learning with Segment Feedback,” International Conference on Machine Learning (ICML), 2025.
  • Yihan Du, Anna Winnicki, Gal Dalal, Shie Mannor, R. Srikant, “Exploration-Driven Policy Optimization in RLHF: Theoretical Insights on Efficient Data Utilization,” International Conference on Machine Learning (ICML), 2024.
  • Yihan Du, R. Srikant, Wei Chen, “Cascading Reinforcement Learning,” International Conference on Learning Representations (ICLR), 2024 (Spotlight).
  • Yihan Du, Longbo Huang, Wen Sun, “Multi-task Representation Learning for Pure Exploration in Linear Bandits,” International Conference on Machine Learning (ICML), 2023.
  • Yihan Du, Siwei Wang, Longbo Huang, “Provably Efficient Risk-Sensitive Reinforcement Learning: Iterated CVaR and Worst Path,” International Conference on Learning Representations (ICLR), 2023.
Awards
  • China Computer Federation (CCF) Agent and Multi-Agent System Doctoral Dissertation Award, June 2024
  • Tsinghua Outstanding Doctoral Dissertation Award, June 2023