@0x0SojalSec: Imagine feeding a whole book to an AI and it just gets it Perfectly, A New OCR model that reads an ENTIRE BOOK in one p…

X AI KOLs Timeline Models

Summary

This tweet announces DeepSeek Unlimited OCR, an AI model that reads entire books in one pass with flat memory usage, achieving a 93% benchmark score and sub-0.11 error rate on 40+ pages.

Imagine feeding a whole book to an AI and it just gets it Perfectly, A New OCR model that reads an ENTIRE BOOK in one pass, DeepSeek Unlimited OCR one key fix to attention, so memory stays flat no matter how long the document. No slowdown on page 40, keeps memory flat, - 93% benchmark score - Sub-0.11 error rate at 40+ pages.
Original Article
View Cached Full Text

Cached at: 07/09/26, 11:53 PM

Imagine feeding a whole book to an AI and it just gets it Perfectly, A New OCR model that reads an ENTIRE BOOK in one pass,

DeepSeek Unlimited OCR one key fix to attention, so memory stays flat no matter how long the document. No slowdown on page 40, keeps memory flat,

  • 93% benchmark score
  • Sub-0.11 error rate at 40+ pages.

Similar Articles

@GoSailGlobal: Current OCR processes multi-page documents page by page. Every time you turn a page, memory is reset. Today, Baidu quietly open-sourced a model on GitHub and HuggingFace called Unlimited OCR, inspired by how humans copy books: - When copying a book, you don't reread hundreds of pages every time you write a word...

X AI KOLs Timeline

Baidu has open-sourced the Unlimited OCR model, which uses a Reference Sliding Window Attention (R-SWA) mechanism to parse documents up to 32K context in a single pass, eliminating the need for page-by-page inference.