Seonglae ChoJina-OCR-v1: Efficient Document Parsing with Speculative Decoding...
We present Jina-OCR-v1, an end-to-end document parsing model built to serve on low-budget GPUs. It combines the compressed-vision encoder and the 3B mixture-of-experts decoder of DeepSeek-OCR,...
https://arxiv.org/abs/2609.03181
