Insight tag

document intelligence

4 related stories.

Stories

Original explanatory diagram

News analysisRelease: September 24, 2025Published: October 24, 20263 min read

IBM released Granite-Docling-258M on September 24, 2025, an Apache-2.0 258M vision-language model for structured document conversion.

Original explanatory diagram

News analysisRelease: May 20, 2025Published: October 24, 20263 min read

PaddlePaddle released PaddleOCR 3.0 on May 20, 2025, adding PP-OCRv5, PP-StructureV3 and PP-ChatOCRv4 with a revised deployment stack.

Original explanatory diagram

News analysisRelease: February 25, 2025Published: October 24, 20263 min read

Ai2 released olmOCR on February 25, 2025, pairing a fine-tuned 7B vision-language model with an open PDF-to-Markdown pipeline.

Original explanatory diagram

News analysisRelease: March 6, 2025Published: October 23, 20263 min read

Mistral introduced its OCR API on March 6, 2025, for extracting ordered text and images from PDFs and images into document-aware workflows.