olmOCR: Unlocking Trillions of Tokens in PDFs with Vision Language Models · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2502.18443/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTolmOCR: Unlocking Trillions of Tokens in PDFs with Vision Language Models — mentioned by fl0underhttps://news.ycombinator.com/item?id=43189445urn:hackerpapers:mention:2502.18443:43189445Wed, 26 Feb 2025 23:22:58 GMT<p>Looks cool! May also be interested in Allen AI&#x27;s OCR tool olmOCR they just released too [1][2]. They say &quot;convert a million PDF pages for only $190 USD&quot;. [1] https://github.com/allenai/olmocr [2] https://arxiv.org/abs/2502.18443</p><p><a href="https://hackerpaper.kaipfister.de/p/2502.18443/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CL