HackerTrans
TopNewTrendsCommentsPastAskShowJobs

PixelPanda

no profile record

Submissions

Evaluating OCR-to-Markdown systems is fundamentally broken

nanonets.com
1 points·by PixelPanda·il y a 6 mois·0 comments

Open source 3B param model for documents better than Gemini 2.5

huggingface.co
5 points·by PixelPanda·il y a 9 mois·1 comments

Nanonets-OCR2-3B – OCR model that transforms documents into structured markdown

huggingface.co
13 points·by PixelPanda·il y a 9 mois·4 comments

comments

PixelPanda
·il y a 9 mois·discuss
Results with our benchmarking -> https://nanonets.com/research/nanonets-ocr-2/
PixelPanda
·il y a 9 mois·discuss
Excited to share Nanonets-OCR2, a state-of-the-art suite of models designed for advanced image-to-markdown conversion and Visual Question Answering (VQA).

Live Demo -> https://docstrange.nanonets.com/

Blog -> https://nanonets.com/research/nanonets-ocr-2/