Granite Docling
PulseAugur coverage of Granite Docling — every cluster mentioning Granite Docling across labs, papers, and developer communities, ranked by signal.
-
Chandra OCR Model Dominates PDF Parsing Benchmark
A recent comparison of PDF parsing capabilities revealed that Chandra, an OCR model from Datalab, outperformed all other tested parsers, successfully handling merged-cell HTML tables, LaTeX, and even difficult cursive t…
-
MinerU, Granite-Docling, PaddleOCR-VL compared for PDF parsing
A user conducted a comparative analysis of three PDF parsing models: MinerU, Granite-Docling, and PaddleOCR-VL, evaluating their performance across 12 distinct capabilities and 6 different document types. The tests incl…
-
IBM releases updated Granite Docling model for improved data handling
IBM has released a new version of its Granite Docling model, named granite-docling-2stage-258m. This updated model aims to improve robustness on out-of-distribution data by dynamically pre-computing layout objects withi…
-
New multi-agent system automates document processing, cuts costs and emissions
Researchers have developed MADP, a multi-agent system designed to automate document processing in enterprise settings. The system combines deep learning for classification and parsing with large language models for extr…