Deep Seek OCR Condenses Charts and Code and Reduces Tokens Per Image by 20X
by Brian Wang from NextBigFuture.com on (#7106C)
DeepSeek's announced OCR (Optical Character Recognition) model compresses text-heavy data into images and reduces vision tokens per image by up to 20x while retaining 97% accuracy (10x compression) or ~60% at 20x. This outperforms competitors on efficiency-performance charts. arxiv - DeepSeek-OCR: Contexts Optical Compression We present DeepSeek-OCR as an initial investigation into the feasibility of ...