My current interests lie at the intersection of LLM reasoning, reinforcement learning, and constrained optimization. Broadly, I work on topics including LLM alignment , Constrained Reinforcement Learning, and Bandits. Please refer to my recent publications for further details.
🔥 News
- 2026.04: 🎉🎉 One paper has been accepted by TMLR 2026.
- 2026.04: 🎉🎉 Invited to give a talk at Washington State University on Generative Pre-Training.(See Blogs for more details)
- 2026.01: 🎉🎉 One paper has been accepted by ICLR 2026.
- 2026.01: 🎉🎉 Invited to give a talk at Washington State University on Score Matching.(See Blogs for more details)
- 2025.06: 🎉🎉 Invited to give a talk at SIGMETRICS 2025.
- 2025.05: 🎉🎉 One paper has been accepted by ICML 2025.
📝 Selected Publications
TMLR 2026
Divide and Conquer: Selective Value Learning and Policy Optimization for Offline Safe Reinforcement Learning
Jiahui Zhu, Honghao Wei, Lei Ying
ICLR 2026
Keep the Best, Forget the Rest: Reliable Alignment with Order-Aware Preference Optimization Jiahui Zhu, Yuanjie Shi, Xiyue Peng, Xin Liu, Yan Yan, Honghao Wei
ICML 2025
Online Constrained Markov Decision Processes Jiahui Zhu, Kihyun Yu, Dabeen Lee, Xin Liu, Honghao Wei
📖 Educations
- 2023.08 - now, Washington State University
- 2021.08 - 2023.01, Boston University
💬 Invited Talks
- 2026.04, Generative Pre-Training, Washington State University
- 2026.01, GenAI Seminar, Washington State University
- 2025.06, SIGMETRICS 2025