DR Pixel enables page-native deep research with vision-language models
DR Pixel is an open-source agent that reasons directly over document page images, outperforming OCR-based methods on scientific papers.
1 stories, newest first · one card per story
DR Pixel is an open-source agent that reasons directly over document page images, outperforming OCR-based methods on scientific papers.
Today 1K readers · 1.4K views · 467 reads · all time 184K views