Scholar
Yihan Du
Google Scholar ID: _RSr3vUAAAAJ
Assistant Professor, SUTD ESD
Citations & Impact
Citations
204
H-index
8
i10-index
7
Publications
17
Co-authors
10
list available
Publications
Resume (English only)
Academic Achievements
- - Published multiple papers in top conferences like ICML, ICLR, and NeurIPS
- - Example publications:
- - "Reinforcement Learning with Segment Feedback" (ICML 2025)
- - "Exploration-Driven Policy Optimization in RLHF: Theoretical Insights on Efficient Data Utilization" (ICML 2024)
- - "Cascading Reinforcement Learning" (ICLR 2024, spotlight, top 5%)
- - "Provably Efficient Iterated CVaR Reinforcement Learning with Function Approximation and Human Feedback" (ICLR 2024)
- - "Provably Safe Reinforcement Learning with Step-wise Violation Constraints" (NeurIPS 2023)
- - "Multi-task Representation Learning for Pure Exploration in Linear Bandits" (ICML 2023)
- - "Provably Efficient Risk-Sensitive Reinforcement Learning: Iterated CVaR and Worst Path" (ICLR 2023)
- - "Collaborative Pure Exploration in Kernel Bandit" (ICLR 2023)
- - "Branching Reinforcement Learning" (ICML)
Research Experience
- - Postdoc at UIUC from 2023 to 2025, advised by Prof. R. Srikant
- - Visited Cornell University in Fall 2022, working with Prof. Wen Sun
- - Research intern at MSR Asia from January to May 2020, mentored by Dr. Wei Chen
- - Collaborated with industry partners such as Nvidia and Microsoft
Education
- - Ph.D. in Computer Science, September 2018 - June 2023, Institute for Interdisciplinary Information Sciences (IIIS), Tsinghua University, Advisor: Prof. Longbo Huang
- - B.E. in Computer Science, September 2014 - June 2018, Xiamen University
Background
- - Research interests: machine learning, including reinforcement learning, online learning (particularly bandits), and multi-task learning
- - Recent research interests: application of RL and bandits in LLMs (e.g., RLHF and DPO), and diffusion models for decision making
- - Tenure-track assistant professor at the ESD pillar of the Singapore University of Technology and Design (SUTD)
Miscellany
- - Actively looking for Ph.D. students with full scholarship (Spring or Fall 2026), research interns, and visiting scholars
- - Co-mentored two undergraduate students with his Ph.D. advisor, both projects published in top conferences NeurIPS and ICLR (the student is the first author)
