Wenhao Zhan
Scholar

Wenhao Zhan

Google Scholar ID: o42MH0MAAAAJ
Graduate Student, Princeton University
reinforcement learninglarge language modelsstatistics
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
660
 
H-index
11
 
i10-index
11
 
Publications
17
 
Co-authors
35
list available
Contact
No contact links provided.
Publications
4 items
Accelerating RL for LLM Reasoning with Optimal Advantage Regression
2025
Cited
0
Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHF
arXiv.org · 2024
Cited
2
Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization
arXiv.org · 2024
Cited
8
Optimal Multi-Distribution Learning
Annual Conference Computational Learning Theory · 2023
Cited
15
Resume (English only)
Co-authors
35 total
Jason D. Lee
Jason D. Lee
Associate Professor of EECS & Statistics at UC Berkeley
Wen Sun
Wen Sun
Assistant Professor, Cornell University
Masatoshi Uehara
Masatoshi Uehara
EvolutionaryScale
Baihe Huang
Baihe Huang
University of California, Berkeley
Yuxin Chen
Yuxin Chen
University of Pennsylvania
Co-author 6
Co-author 6
Kianté Brantley
Kianté Brantley
Assistant Professor, Harvard University
Yuejie Chi
Yuejie Chi
Yale University