https://hackerpaper.kaipfister.de/p/2311.06242/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=42978179urn:hackerpapers:mention:2311.06242:42978179Fri, 07 Feb 2025 22:20:37 GMT<p>I&#x27;m somewhat surprised neither this article nor the previous one mention anything about the Florence-2 model series. I had thought that Florence-2 was not just surprisingly capable for this kind of work, but also easily fine-tunable for a particular kind of document, when you expect to process a lot of instances of that document and want to further optimize accuracy. It&#x27;s extremely small (0.23B and 0.77B parameters), so it&#x27;s easy to run, easy to fine-tune, and probably unlikely to overthink things. https://arxiv.org/abs/2311.06242 https://huggingface.co/blog/finetune-florence2…</p><p><a href="https://hackerpaper.kaipfister.de/p/2311.06242/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CVhttps://news.ycombinator.com/item?id=38249803urn:hackerpapers:submission:2311.06242:38249803Mon, 13 Nov 2023 13:20:18 GMT<p>Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks</p><p></p><p>1 point; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2311.06242/">Paper and source history</a>. A submission is not an endorsement.</p>cs.CV