The Best of N Worlds: Aligning Reinforcement Learning with Best-of-N Sampling via max@k Optimisation
Paper
•
2510.23393
•
Published
•
16
Farid Bagirov
kraalfar
AI & ML interests
None yet
Recent Activity
authored
a paper
1 day ago
The Best of N Worlds: Aligning Reinforcement Learning with Best-of-N
Sampling via max@k Optimisation
upvoted
a
paper
1 day ago
Diff-XYZ: A Benchmark for Evaluating Diff Understanding
Organizations
authored
a
paper
1 day ago