Social Sciences DataLab
PulseAugur coverage of Social Sciences DataLab — every cluster mentioning Social Sciences DataLab across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
Datalab launches OmniParseBench OCR evaluation tool
Datalab has launched OmniParseBench, a new open-source benchmark designed to evaluate OCR parsers. This benchmark includes 16,288 pass/fail tests across 2,937 pages from 2,343 documents in 92 languages, aiming to provid…
-
Social Sciences DataLab releases fast Indra OCR model
Social Sciences DataLab has released Indra OCR, a new 1-million-parameter OCR model designed for high throughput and speed on CPUs. It can process up to 49 pages per second, significantly outperforming Tesseract and Pad…
-
Datalab launches OmniExtractBench to standardize AI document extraction evaluation
Datalab has introduced OmniExtractBench, an open benchmark designed to address bias and opacity in structured document extraction tasks. This new benchmark evaluates how accurately AI systems can populate a JSON schema …
-
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…
-
RAG parsing of scientific papers struggles with tables and equations
Parsing scientific papers for retrieval-augmented generation (RAG) systems remains challenging due to complex layouts, equations, and tables that often result in extraction errors. These errors, such as incorrect number…
-
Marker 2 document converter achieves 5x throughput, beats competitors on benchmark
Datalab has released Marker 2, a significantly rewritten open-source document conversion pipeline. The new version boasts a 5x increase in throughput compared to MinerU, achieving 2.9 pages per second on a single Nvidia…
-
Datalab's Lift 9B model leads in schema-first PDF extraction
Datalab's Lift is a new 9-billion parameter vision-language model designed for schema-first document extraction. Unlike traditional methods that first parse documents into intermediate formats before extracting fields, …
-
Open-source models tackle PDF-to-JSON conversion for enterprise AI
New open-source models are emerging to convert unstructured data within PDFs into usable JSON formats, addressing a critical need for enterprise AI applications. These models fall into two main categories: schema-driven…
-
Open-source OCR models and benchmarks consolidated on Papers with Code
A new resource has been created to track open-source optical character recognition (OCR) models, consolidating information on top-performing models, benchmarks, and links to their papers and code. This initiative highli…
-
Datalab releases lift, a 9B open-weights vision model for structured PDF extraction
Datalab has launched lift, a 9B parameter open-weights vision model designed for structured data extraction from PDFs and images. The model takes a JSON schema as input and generates a JSON object conforming to that sch…