Instruction-Following Pruning for Large Language Models · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2501.02086/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTInstruction-Following Pruning for Large Language Models — mentioned by Alpha3031https://news.ycombinator.com/item?id=49456764urn:hackerpapers:mention:2501.02086:49456764Wed, 26 Aug 2026 22:25:53 GMT<p>Normal MoE is switch-weights-per-token so you would se substantial slowdowns that way. Apple did a More that switches weights per prompt (instruction-following pruning, https://arxiv.org/abs/2501.02086) but you have to design the model that way which I don&#x27;t think the have.</p><p><a href="https://hackerpaper.kaipfister.de/p/2501.02086/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CLInstruction-Following Pruning for Large Language Models — HN submissionhttps://news.ycombinator.com/item?id=45235119urn:hackerpapers:submission:2501.02086:45235119Sat, 13 Sep 2025 20:37:50 GMT<p>Instruction-Following Pruning for Large Language Models</p><p></p><p>5 points; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2501.02086/">Paper and source history</a>. A submission is not an endorsement.</p>cs.CL