Show HN: Vision-Based, Vectorless RAG for Long Douments
github.comยท3hยท
Discuss: Hacker News
๐Ÿค–Advanced OCR
Flag this post
Getting Started with Text Mining in R and Python: Origins, Applications, and Real-World Case Studies
dev.toยท9hยท
Discuss: DEV
๐Ÿ“„Text Mining
Flag this post
A minimalist web app for extracting text from PDFs
deepocr.ccยท5hยท
Discuss: Hacker News
๐Ÿ“„OCR
Flag this post
Working with Digital Archives: The William S. Burroughs Project
fsuspecialcollections.wordpress.comยท2d
๐Ÿ“œDocument Paleography
Flag this post
DeepSeek-OCR + LLama4 + RAG Just Revolutionized Agent OCR Forever
dev.toยท2dยท
Discuss: DEV
๐Ÿค–Advanced OCR
Flag this post
Wear marks suggest Neanderthals made ocher crayons
arstechnica.comยท5h
๐ŸฆดBinary Paleography
Flag this post
Show HN: Font Finder โ€“ Find and Copy Fonts from Any Webpage
font-finder.orgยท19hยท
Discuss: Hacker News
๐Ÿ”คFont Archaeology
Flag this post
English text readability can be estimated using basic linguistic features, study indicates
phys.orgยท6h
๐Ÿง Intelligence Compression
Flag this post
ProstNFound+: A Prospective Study using Medical Foundation Models for Prostate Cancer Detection
arxiv.orgยท16h
๐Ÿ‘๏ธOCR Enhancement
Flag this post
Researchers Discover Lost 3,000-Year-Old Babylonian Hymn
scitechdaily.comยท1d
๐Ÿ“œPalimpsest Analysis
Flag this post
Word and PowerPoint Alt Text Roundup
webaim.orgยท56m
๐Ÿ“„PostScript
Flag this post
Stochastic computing
scottlocklin.wordpress.comยท3h
๐Ÿด๓ ง๓ ข๓ ณ๓ ฃ๓ ด๓ ฟScottish Computing
Flag this post
Some of the earliest written notes in western musical history discovered in Pennsylvania
theguardian.comยท3d
๐ŸฐManuscript Networks
Flag this post
Show HN: Hot or Slop โ€“ Visual Turing test on how well humans detect AI images
hotorslop.comยท17hยท
Discuss: Hacker News
๐Ÿ“ŠLearned Metrics
Flag this post
Scripts That Donโ€™t Fit: The Hidden Bias of NLP in South Asian Languages
digitalorientalist.comยท3d
๐Ÿ›Digital humanities
Flag this post
DeepSeek-OCR๏ผš10x Compression and 97% Accuracy Beats Tesseract and PaddleOCR
deepocr.ccยท2dยท
Discuss: Hacker News
๐Ÿค–Advanced OCR
Flag this post
REVEAL: A large-scale comprehensive image dataset for steganalysis
sciencedirect.comยท1d
๐Ÿ•ต๏ธSteganographic Archives
Flag this post
Building a Visual Diff System for AI Edits (Like Git Blame for LLM Changes)
news.ycombinator.comยท25mยท
Discuss: Hacker News
๐ŸŽฏGradual Typing
Flag this post
How unstructured data turns your business into a junk drawer - and how to fix it
techradar.comยท4h
๐Ÿ“„Document Digitization
Flag this post
Show HN: I'm building an open source platform for studying Arabic
parallel-arabic.comยท4hยท
Discuss: Hacker News
๐Ÿ“ABNF Extensions
Flag this post