Sample, Don't Search: Rethinking Test-Time Alignment for Language Models
Paper
•
2504.03790
•
Published
•
3
Gonçalo Faria
graf
AI & ML interests
NLP
Recent Activity
updated
a model
7 days ago
graf/qwen2.5-1.5b-instruct-sft-test-bon
published
a model
7 days ago
graf/qwen2.5-1.5b-instruct-sft-test-bon
updated
a dataset
7 days ago
graf/DeepScaleR-Preview-Dataset.20000.ancestral.128.Qwen2.5-1.5B-Instruct.bon
Organizations
upvoted
a
paper
3 months ago