SOURCE-LINKED INTELLIGENCE

Jina-OCR-v1: Efficient Document Parsing with Speculative Decoding and Dense Verifiable Rewards

arXiv · AI, language, vision and robotics · article · Sep 2, 2026 · UTC

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, which activates about 570M parameters per token, with a FastMTP speculative decoding head that shares a single draft block recursively across K=3 prediction steps. Greedy verification makes decoding lossless. Post-training combines instruction alignment, robustness fine-tuning on difficult documents, and GRPO under dense verifiable rewards: deterministic formula, table, and structural checks that award p

Read original source ↗ Open in workspace

recordType

paper

region

Global