Scalable Power Sampling: Unlocking Efficient, Training-Free Reasoning for LLMs via Distribution Sharpening · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2601.21590/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTScalable Power Sampling: Unlocking Efficient, Training-Free Reasoning for LLMs via Distribution Sharpening — mentioned by verdvermhttps://news.ycombinator.com/item?id=46843308urn:hackerpapers:mention:2601.21590:46843308Sun, 01 Feb 2026 03:17:14 GMT<p>Submission title matches the paper linked in the blog post: https://www.arxiv.org/abs/2601.21590 Submitted the blog post because it has the more digestible and intuitive explanations</p><p><a href="https://hackerpaper.kaipfister.de/p/2601.21590/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.LG