Kunhao Zheng
Scholar

Kunhao Zheng

Google Scholar ID: zDy4jSYAAAAJ
Meta FAIR
Code GenerationReasoningReinforcement LearningLarge Language ModelTheorem Proving
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
1,188
 
H-index
8
 
i10-index
7
 
Publications
16
 
Co-authors
33
list available
Contact
No contact links provided.
Publications
9 items
WybeCoder: Verified Imperative Code Generation
2026
Cited
0
CWM: An Open-Weights LLM for Research on Code Generation with World Models
2025
Cited
0
Improving Diversity in Language Models: When Temperature Fails, Change the Loss
2025
Cited
0
Optimizing Language Models for Inference Time Objectives using Reinforcement Learning
2025
Cited
0
The KoLMogorov Test: Compression by Code Generation
2025
Cited
0
Soft Policy Optimization: Online Off-Policy RL for Sequence Models
2025
Cited
0
PILAF: Optimal Human Preference Sampling for Reward Modeling
2025
Cited
0
What Makes Large Language Models Reason in (Multi-Turn) Code Generation?
arXiv.org · 2024
Cited
8
Resume (English only)
Co-authors
33 total
Ya Zhang
Ya Zhang
Shanghai Jiao Tong University
Chen Ju
Chen Ju
Alibaba Group, Shanghai Jiao Tong University
Co-author 3
Co-author 3
Co-author 4
Co-author 4
Gabriel Synnaeve
Gabriel Synnaeve
Research scientist at Facebook AI Research
Taco Cohen
Taco Cohen
Qualcomm AI Research
Weidi Xie
Weidi Xie
Shanghai Jiao Tong University | VGG, University of Oxford
Jonas Gehring
Jonas Gehring
Facebook AI Research