Scalable Power Sampling: Unlocking Efficient, Training-Free Reasoning for LLMs via Distribution Sharpening
Paper
•
2601.21590
•
Published
•
10
Arnaud Lallouet
Aaaarno
·
AI & ML interests
Neurosymbolic
Recent Activity
upvoted
a
paper
about 13 hours ago
Scalable Power Sampling: Unlocking Efficient, Training-Free Reasoning for LLMs via Distribution Sharpening
Organizations
upvoted
a
paper
about 13 hours ago