https://hackerpaper.kaipfister.de/p/2602.17687/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:27:26 GMThttps://news.ycombinator.com/item?id=47125210urn:hackerpapers:submission:2602.17687:47125210Mon, 23 Feb 2026 17:10:50 GMT<p>Show HN: Irpapers – Visual embeddings vs. OCR trade-offs in scientific PDFs</p><p>Hey HN, we are releasing IRPAPERS to answer a highly pragmatic question: when building a RAG pipeline over PDFs, should you OCR the text or just embed the raw page images? Processing PDFs in production usually involves stringing together brittle OCR heuristics. While recent multimodal embeddings (like ColModernVBERT or ColPali) allow you to skip OCR entirely and retrieve directly from visual layouts, we wanted to measure if the computational overhead is actually worth the utility. The short answer: Transformer-based image pipelines won&#x27;t be perfect for every use-case, but they fix exactly…</p><p>5 points; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2602.17687/">Paper and source history</a>. A submission is not an endorsement.</p>cs.IRhttps://news.ycombinator.com/item?id=47124377urn:hackerpapers:submission:2602.17687:47124377Mon, 23 Feb 2026 16:17:46 GMT<p>A Visual Document Benchmark for Scientific Retrieval and Question Answering</p><p></p><p>2 points; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2602.17687/">Paper and source history</a>. A submission is not an endorsement.</p>cs.IR