Pairwise RM: Perform Best-of-N Sampling with Knockout Tournament
Paper
•
2501.13007
•
Published
•
18
Zhao Zhang
zhangzhao219
·
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
11 days ago
Pairwise RM: Perform Best-of-N Sampling with Knockout Tournament
upvoted
a
paper
7 months ago
Aligning Teacher with Student Preferences for Tailored Training Data
Generation
updated
a model
12 months ago
zhangzhao219/WSDM_Cup_2024
Organizations
None yet