https://hackerpaper.kaipfister.de/p/2409.10594/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=43052930urn:hackerpapers:mention:2409.10594:43052930Fri, 14 Feb 2025 20:50:50 GMT<p>Related: There was buzz last year about Kolmogorov Arnold Networks, and https://arxiv.org/abs/2409.10594 was claiming KANs perform better than standard MLPs in the transformer architecture. Does anyone know of these being explored in the LLM space? KANs seem to have better properties regarding memory if I&#x27;m not mistaken.</p><p><a href="https://hackerpaper.kaipfister.de/p/2409.10594/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.LGhttps://news.ycombinator.com/item?id=41598563urn:hackerpapers:submission:2409.10594:41598563Fri, 20 Sep 2024 03:36:30 GMT<p>Kolmogorov-Arnold Transformer</p><p></p><p>2 points; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2409.10594/">Paper and source history</a>. A submission is not an endorsement.</p>cs.LG