百度开源了Unlimited OCR，3B参数却只有500M激活，表格解析超强，能一次性读完40页文档，比PaddleOCR-VL-1.6强在表格和阅读顺序上。试试看？
Unlimited OCR是百度开源的OCR模型，总参数量3B，仅500M激活。它在表格解析和阅读顺序方面表现优秀，在OmniDocBench v1.5和v1.6上达到SOTA。核心创新是Reference Sliding Window Attention（R-SWA），能保持恒定KV缓存大小，单次前向传递处理40+页文档。与PaddleOCR-VL-1.6对比显示，它在语义格式和图表方面略有不足。
Unlimited OCR is a great model on table parsing and understanding proper reading order. However it ...
Unlimited OCR is a great model on table parsing and understanding proper reading order. However it does struggle a little on semantic formatting, charts (it does decent at bounding boxes). Attaching the results below to compare against PaddleOCR-VL-1.6. Overall it's still a great addition to the open-weight OCR model collection! Check the latest results on ParseBench: parsebench.ai Baidu AI @BaiduAI_News We’re open-sourcing Unlimited OCR — built to read long documents in one pass. With 3B total parameters and only 500M activated, Unlimited OCR sets new end-to-end SOTA results on OmniDocBench v1.5 and v1.6. The key innovation is Reference Sliding Window Attention (R-SWA), inspired by how humans transcribe books: keeping the source, recent context, and next words in focus, while softly forgetting what’s no longer needed. With constant KV Cache size and lower attention cost, Unlimited OCR can transcribe 40+ pages in a single forward pass — without losing context or slowing down. Explore the model👇: --GitHub: github.com/baidu/Unlimite… d --Hugging Face: huggingface.co/baidu/Unlimite… u 🔗 View Quoted Tweet 💬 5 🔄 4 ❤️ 27 👀 3262 📊 11 ⚡