Lefei Zhang

Engineering · Physical Sciences

1h-index1citations4works0.32yr avg
OpenAlex↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Safety Systems Engineering in Autonomy(3), Software Engineering Research(1), Information and Cyber Security(1)

Publications4 total

Information-Theoretic Reward Modeling for Stable RLHF: Detecting and Mitigating Reward Hacking
arXiv (Cornell University)·2025Open Access
The Energy Loss Phenomenon in RLHF: A New Perspective on Mitigating Reward Hacking
arXiv (Cornell University)·2025Open Access
InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling
arXiv (Cornell University)·2024· 1 citedOpen Access
InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling
2024

Frequent Co-authors

Yuchun Miao(4), Dacheng Tao(4), Sen Zhang(3), Liang Ding(3), Rong Bao(3), Sen Zhang(1), Liang Ding(1), Yu-Qi Zhang(1)