Tagged: ocr

12 articles

Latest

Jina AI's new OCR hits 2.57 pages/sec on A100

Reducto's r-1 cuts parsing costs to 1 cent per page with single-pass architecture

LayoutLM hits 95% accuracy on document AI benchmarks, leaving OCR-only approaches behind

Baidu's PaddlePaddle hits 5.35M devs, brings OCR to Hugging Face

deepDoctection 1.2.x Walkthrough: Build a Full Document Intelligence Pipeline

UPDF AI claims GPT-5.6 and 99% OCR accuracy for PDF workflows

PixelRAG ditches HTML parsing, retrieves documents as screenshots with 7-query Recall@k eval

Baidu's Unlimited-OCR model parses entire pages in one shot, skipping the layout analysis stage

PaddleOCR v6 drops: tiny models hit 86.2% detection, run on CPU

PaddleOCR 3.5 now runs on a Transformers backend, cutting a major friction point for RAG devs

Albumentations adds text-aware augmentation that rewrites document images without wrecking OCR

Hugging Face's Idefics2 shrinks to 8B parameters but now beats much larger vision models