Chengshuai Shi
Scholar

Chengshuai Shi

Google Scholar ID: twvDiW8AAAAJ
Princeton Language and Intelligence
Reinforcement LearningIntelligent Decision-Making
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
538
 
H-index
11
 
i10-index
12
 
Publications
20
 
Co-authors
13
list available
Contact
No contact links provided.
Publications
5 items
Greedy Sampling Is Provably Efficient for RLHF
2025
Cited
0
From Cross-Task Examples to In-Task Prompts: A Graph-Based Pseudo-Labeling Framework for In-context Learning
2025
Cited
0
Augmenting Online RL with Offline Data is All You Need: A Unified Hybrid RL Algorithm Design and Analysis
2025
Cited
0
Cost-Aware Optimal Pairwise Pure Exploration
2025
Cited
0
Building Math Agents with Multi-Turn Iterative Preference Learning
arXiv.org · 2024
Cited
18
Resume (English only)
Co-authors
13 total
Cong Shen
Cong Shen
Associate Professor, University of Virginia
Jing Yang
Jing Yang
Associate Professor of ECE and CS, University of Virginia
Wei Xiong
Wei Xiong
University of Illinois Urbana-Champaign
Tong Zhang
Tong Zhang
UIUC
Kun Yang
Kun Yang
Google, University of Virginia
Han Zhong
Han Zhong
Peking University
Jundong Li
Jundong Li
Associate Professor, University of Virginia
Chi Jin
Chi Jin
Assistant Professor, Princeton University