https://hackerpaper.kaipfister.de/p/2503.20215/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=43828074urn:hackerpapers:mention:2503.20215:43828074Tue, 29 Apr 2025 02:06:07 GMT<p>There&#x27;s already a lot of info in there: model architecture and mechanics. Using the model to generate synthetic data also allows to distil its reasoning power into other models that you train, which is very powerful. On top of these, Qwen&#x27;s technical reports follow model releases by some time, they&#x27;re generally very information rich. For instance, check this report for Qwen Omni, it&#x27;s really good: https://huggingface.co/papers/2503.20215</p><p><a href="https://hackerpaper.kaipfister.de/p/2503.20215/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CLhttps://news.ycombinator.com/item?id=43523776urn:hackerpapers:submission:2503.20215:43523776Sun, 30 Mar 2025 12:52:33 GMT<p>Qwen2.5-Omni Technical Report</p><p></p><p>6 points; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2503.20215/">Paper and source history</a>. A submission is not an endorsement.</p>cs.CL