https://hackerpaper.kaipfister.de/p/2405.15306/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=43598881urn:hackerpapers:mention:2405.15306:43598881Sun, 06 Apr 2025 04:04:55 GMT<p>I use tesseract which uses a LTSM OCR along with multimodal LLMs to converge to a ground truth. It works remarkably well. However for my purposes I don’t want a LLM explaining charts I want it to produce a vector format of the chart. There are a few models that produce Latex chart formats I’m experimenting with: https://arxiv.org/pdf/2405.15306 Most OCR pipelines like this, along with excellent commercial ones like doctly.ai, are focused on OCR for LLM consumption - while I’d like to be able to recreate the original scientific work that predates digital typesetting in modern typeset - for yes…</p><p><a href="https://hackerpaper.kaipfister.de/p/2405.15306/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CLhttps://news.ycombinator.com/item?id=40571137urn:hackerpapers:mention:2405.15306:40571137Tue, 04 Jun 2024 05:58:59 GMT<p>The application to inverse graphics tasks reminds me of this paper which was released one week earlier: https://arxiv.org/abs/2405.15306</p><p><a href="https://hackerpaper.kaipfister.de/p/2405.15306/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CL