Siyuan Xu

PhD student, EECS, Pennsylvania State University

Joined

May 2023

Names

Siyuan Xu (Preferred)

Emails

****@psu.edu (Confirmed)

****@outlook.com (Confirmed)

Personal Links

Google Scholar

Career & Education History

PhD student

EECS, Pennsylvania State University (psu.edu)

2020 – Present

Undergrad student

Xi'an Jiaotong University (xjtu.edu.cn)

2015 – 2019

Advisors, Relations & Conflicts

PhD Advisor

Minghui Zhu

2020 – Present

Expertise

No areas of expertise listed

Publications

A Constrained Bi-level Optimization Framework for Constrained Reinforcement Learning from Human Feedback
Yue Mao, Siyuan Xu, Shicheng Liu, Minghui Zhu
- Submitted to ICLR 2026
- Readers: Everyone
Inverse Reinforcement Learning of Interactive Scenarios
Yue Mao, Shicheng Liu, Siyuan Xu, Minghui Zhu
- Submitted to ICLR 2026
- Readers: Everyone
Adaptive Code Watermarking Through Reinforcement Learning
Zhimeng Guo, Huaisheng Zhu, Siyuan Xu, Hangfan Zhang, Teng Xiao, Minhao Cheng
- Submitted to ICLR 2026
- Readers: Everyone
Self-Aware Reinforcement Learning for Improving LLMs with Minimal Data
Hangfan Zhang, Siyuan Xu, Zhimeng Guo, Huaisheng Zhu, Shicheng Liu, Xinrun Wang, Qiaosheng Zhang, Yang Chen, Peng Ye, LEI BAI, Shuyue Hu
- Submitted to ICLR 2026
- Readers: Everyone
Simple Distillation for One-Step Diffusion Models
Huaisheng Zhu, Teng Xiao, Shijie Zhou, Zhimeng Guo, Hangfan Zhang, Siyuan Xu, Vasant G Honavar
- NeurIPS 2025 poster
- Readers: Everyone
Explainable Reinforcement Learning from Human Feedback to Improve Alignment
Shicheng Liu, Siyuan Xu, Wenjie Qiu, Hangfan Zhang, Minghui Zhu
- NeurIPS 2025 poster
- Readers: Everyone
Efficient Safe Meta-Reinforcement Learning: Provable Near-Optimality and Anytime Safety
Siyuan Xu, Minghui Zhu
- NeurIPS 2025 poster
- Readers: Everyone
Meta-Reinforcement Learning with Adaptation from Human Feedback via Preference-Order-Preserving Task Embedding
Siyuan Xu, Minghui Zhu
- ICML 2025 poster
- Readers: Everyone
Safe Meta-Reinforcement Learning via Dual-Method-Based Policy Adaptation: Near-Optimality and Anytime Safety Guarantee
Siyuan Xu, Minghui Zhu
- Submitted to ICLR 2025
- Readers: Everyone
Meta-Reinforcement Learning with Universal Policy Adaptation: Provable Near-Optimality under All-task Optimum Comparator
Siyuan Xu, Minghui Zhu
- NeurIPS 2024 poster
- Readers: Everyone

View all 13 publications