Scholar
Zikang Shan
Google Scholar ID: qBy4wKcAAAAJ
Peking University
Reinforcement Learning
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
372
H-index
3
i10-index
3
Publications
3
Co-authors
5
list available
Publications
2 items
Bringing Value Models Back: Generative Critics for Value Modeling in LLM Reinforcement Learning
2026
Cited
0
SHAPE: Stage-aware Hierarchical Advantage via Potential Estimation for LLM Reasoning
2026
Cited
0
Co-authors
5 total
Weikang Wan
PhD Student, University of California, San Diego
He Wang
Assistant Professor of Computer Science, Peking University
Han Zhong
Peking University
Liwei Wang
Professor, Peking University
Wei Xiong
University of Illinois Urbana-Champaign
