Scholar
Huazheng Wang
Google Scholar ID: w3PrbKwAAAAJ
Assistant Professor, Oregon State University
Citations & Impact
Citations
1,518
H-index
18
i10-index
23
Publications
20
Co-authors
4
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Received EECS Fabulous Teacher Recognition in June 2025.
- Two papers accepted by ICML 2025: one spotlight paper on failure attribution of multi-agent LLMs and one on principal-agent bandits.
- Talk at AAAI 2025 New Faculty Highlight: “Efficient and Robust Reinforcement Learning from Human Feedback”.
- One paper on analyzing gradient entanglement of DPO and its variants is accepted by ICLR 2025.
- Talk at CS colloquium series, University of Rochester: “Robust Reinforcement Learning from Biased Human Feedback and Corruption: Theory and Algorithms”.
- One paper on risk-aware preference-based RL is accepted by NeurIPS 2024.
- Received a new NSF award (IIS-2403401) on Neural Bandits in August 2024.
- One paper on conversational dueling bandits is accepted by KDD 2024, and another paper on adversarial attack on combinatorial bandits is accepted by ICML 2024.
- One paper on federated pure exploration is accepted by UAI 2024.
- One paper on policy alignment is accepted by ICLR 2024.
- Two papers accepted by AAAI 2024: one on tree search bandits for protein optimization and one on stealthy attack against MAB.
- One paper on offline RL for learning to rank is accepted by NeurIPS 2023.
- One paper on representation learning in POMDP is accepted by ICML 2023.
- Asynchronous kernel bandits paper is accepted by ICLR 2023.
- Two papers accepted by NeurIPS 2022: one on distributed kernel bandits and the other on Thompson Sampling for Directed Evolution.
- Awarded ICML 2021 Best Reviewers (Top 10%) in August 2021.
- Received SIGIR 2019 Best Paper Award in August 2019.
- Bloomberg Data Science Ph.D. Fellowship from 2018 to 2021.
Background
- Research interests include reinforcement learning, information retrieval, and machine learning in general. Recently focused on developing provably efficient and trustworthy reinforcement learning and multi-armed bandit algorithms with applications to recommendation, ranking, LLM agents, and scientific discovery problems in biology and chemistry.
Miscellany
- Looking for one self-motivated PhD student with solid math and coding backgrounds starting Fall 2026.
