Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2511.06221/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTTiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B — mentioned by yorwbahttps://news.ycombinator.com/item?id=49641037urn:hackerpapers:mention:2511.06221:49641037Thu, 10 Sep 2026 09:48:39 GMT<p>Weibo&#x27;s VibeThinker manages with half of that: https://arxiv.org/abs/2511.06221 (They finetuned Qwen2.5-Math-1.5B for reasoning.)</p><p><a href="https://hackerpaper.kaipfister.de/p/2511.06221/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.AITiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B — HN submissionhttps://news.ycombinator.com/item?id=45902010urn:hackerpapers:submission:2511.06221:45902010Wed, 12 Nov 2025 16:19:30 GMT<p>Tiny Model, Big Logic: Large-Model Reasoning Ability in VibeThinker-1.5B</p><p></p><p>4 points; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2511.06221/">Paper and source history</a>. A submission is not an endorsement.</p>cs.AI