#ocr
Ocr: 6 AI articles covering ocr news, analysis, and research
Articles
Wieszcz-XIX: A 3.1-Billion-Word Corpus of Pre-1918 Polish and⭐9
Wieszcz-XIX offers a 3.1-billion-word corpus of pre-1918 Polish and temporally bounded language models trained from scratch, with quality audits and OCR error a...
Datalab Introduces OmniExtractBench to Fix Bias and Opacity in⭐8
Datalab launches OmniExtractBench, an open benchmark with 620 documents and a deterministic, explainable scorer to fix bias and opacity in document extraction b...
Jina AI Releases jina-ocr-v1: A 3.4B MoE Document Parser With⭐8
Jina AI releases jina-ocr-v1, a 3.4B MoE document parser with built-in speculative decoding, scoring 91.14 on OmniDocBench and built for low-budget GPUs.
LandingAI Launches Agentic Document Extraction Gen2 with DPT-3⭐7
LandingAI's Agentic Document Extraction Gen2 rebuilds document intelligence with DPT-3 Pro and Verity, using hierarchical tree modeling, character-based pricing...
Cohere Releases Parse 5 (v5.0): A 2.3B Vision Language Model for⭐7
Cohere releases Parse v5.0, a 2.3B vision language model converting documents to Markdown efficiently. Priced at $1.50 per 1,000 pages, it's production-ready vi...
Building an End-to-End Document Intelligence Pipeline with⭐9
Build an end-to-end document intelligence pipeline with deepDoctection: layout detection, table parsing, OCR, reading order, and structured export for RAG syste...