@ErickSky: Baidu has just broken one of the biggest limitations of current OCR. Unlimited-OCR processes entire documents in a sing…
Summary
Baidu has released Unlimited-OCR, which processes entire documents in a single pass without chunking, overcoming a major limitation of current OCR technology.
View Cached Full Text
Cached at: 06/23/26, 12:07 PM
Baidu acaba de romper una de las limitaciones más grandes del OCR actual.
Unlimited-OCR procesa documentos enteros de una sola pasada, sin chunking.
Es el siguiente paso después de DeepSeek-OCR.
REPOOO👇 https://t.co/onbAwQeYlw
Similar Articles
Unlimited OCR: One-Shot Long-Horizon Parsing
Baidu releases Unlimited-OCR, an open-source model for one-shot long-horizon document parsing, building upon Deepseek-OCR with support for single images, multi-page documents, and PDFs.
baidu/Unlimited-OCR
Baidu releases Unlimited-OCR, a new model for one-shot long-horizon document parsing, building on Deepseek-OCR. It supports single image and multi-page/PDF parsing via Hugging Face Transformers and SGLang.
@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...
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.
Unlimited OCR Works
Unlimited OCR introduces Reference Sliding Window Attention to eliminate growing memory consumption in long-sequence OCR tasks, enabling efficient transcription of multiple pages in a single forward pass.
@AdinaYakup: Unlimited-OCR New OCR from @PaddlePaddle It can parse hundreds of pages in a single pass while maintaining stable speed…
PaddlePaddle releases Unlimited-OCR, a new OCR model using Reference Sliding Window Attention (R-SWA) to maintain constant KV cache during decoding, achieving 93% on OmniDocBench and a 6% improvement over previous methods.