α
Research
Alpha Leak
Conferences
Topics
Top Authors
Rankings
Browse All
EN
中
Home
/
Authors
/
Mohammad Saleh
Mohammad Saleh
2
papers
379
total citations
papers (2)
Statistical Rejection Sampling Improves Preference Optimization
ICLR 2024
arXiv
329
citations
RRM: Robust Reward Model Training Mitigates Reward Hacking
ICLR 2025
arXiv
50
citations