Researchers have developed a new state-of-the-art (SOTA) Optical Character Recognition (OCR) model called DOTS-OCR, which uses Apple's Core ML framework. The model is designed to recognize text in images and can be used for tasks such as document scanning and image annotation. According to the Hugging Face blog, the DOTS-OCR model outperforms other SOTA OCR models on several benchmarks, including the COCO-text dataset. --- Why it matters: This matters because it provides a high-performance OCR solution that can be easily integrated into Apple devices using Core ML, which could improve text recognition in various applications such as document management and image processing. Source: https://huggingface.co/blog/dots-ocr-ne