Penghui Qi
Scholar

Penghui Qi

Google Scholar ID: CLRsGEMAAAAJ
Sea AI Lab & PhD student of NUS
Machine LearningReinforcement LearningMLSys
Google Scholar↗
Citations & Impact
All-time
Citations
526
 
H-index
6
 
i10-index
4
 
Publications
9
 
Co-authors
8
list available
Contact
No contact links provided.
Publications
11 items
Predictive Divergence Masks for LLM RL
2026
Cited
0
Flow-DPPO: Divergence Proximal Policy Optimization for Flow Matching Models
2026
Cited
0
Rethinking the Divergence Regularization in LLM RL
2026
Cited
0
Rethinking the Trust Region in LLM Reinforcement Learning
2026
Cited
1
Revisiting Parameter Server in LLM Post-Training
2026
Cited
1
Defeating the Training-Inference Mismatch via FP16
2025
Cited
0
SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning
2025
Cited
0
Optimizing Anytime Reasoning via Budget Relative Policy Optimization
2025
Cited
0
Resume (English only)
Co-authors
8 total
Min Lin
Min Lin
Principal Research Scientist, Sea AI Lab
Zichen Liu
Zichen Liu
Sea AI Lab; National University of Singapore
Tianyu Pang
Tianyu Pang
Senior Research Scientist, Sea AI Lab
Chao Du
Chao Du
Senior Research Scientist, Sea AI Lab
Wee Sun Lee
Wee Sun Lee
Professor, Department of Computer Science, National University of Singapore
Xinyi Wan
Xinyi Wan
Sea AI Lab
Junxiao Song
Junxiao Song
DeepSeek AI
Co-author 8
Co-author 8