@vista8: Baidu's technical strength is still impressive. Recently, this Unlimited OCR has even caught the attention of Yann LeCun! Unlimited OCR proposes Reference Sliding Window Attention (R-SWA)...
Summary
Baidu's open-source Unlimited OCR model proposes the Reference Sliding Window Attention (R-SWA) mechanism, achieving continuous parsing of dozens of pages with 3 billion parameters, gaining high attention on GitHub and HuggingFace.
View Cached Full Text
Cached at: 07/22/26, 06:35 PM
It feels like Baidu’s technical foundation is still very solid.
Recently, this Unlimited OCR has even caught the attention of Yann LeCun!
Unlimited OCR introduces the Reference Sliding Window Attention (R-SWA) mechanism. Instead of the traditional “page-by-page parsing + result stitching” approach, it mimics how humans read and copy long documents, keeping the KV cache in the decoding stage at a constant scale. With only a 3-billion-parameter model, it can continuously parse documents spanning dozens of pages in one go.
Open-sourced last month, Unlimited OCR hit #1 on both GitHub Trending and HuggingFace model download trends the very next day.
Now, the project has surpassed 16.5k GitHub Stars, over 2.24 million downloads on HuggingFace, and has once again climbed the Trending list, currently ranking #2, surpassing GLM-5.2 again.
As a foundational project for cleaning large model training data, Unlimited OCR has attracted attention from developers worldwide.
#无限OCR #UnlimitedOCR #Baidu #ERNIE #文心
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...
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.
@BaiduAI_News: We’re open-sourcing Unlimited OCR — built to read long documents in one pass. With 3B total parameters and only 500M ac…
Baidu open-sources Unlimited OCR, a 3B parameter model (500M activated) that reads long documents in a single pass using Reference Sliding Window Attention (R-SWA), achieving state-of-the-art results on OmniDocBench.
@berryxia: Wow, this move directly poached DeepSeek's talent! Last night I saw this interesting OCR open-source model on HuggingFace and the fascinating story behind it. This OCR model is completely different from traditional ones! Its speed and accuracy are absolutely unbeatable~~ Let me start with some background, for those who are familiar…
Baidu has open-sourced the Unlimited OCR model, which uses the R-SWA attention mechanism to process hundreds of pages in a single pass without page splitting, with a constant KV Cache. The model innovatively mimics the attention pattern of humans copying books by hand and shares technical lineage with DeepSeek OCR, sparking discussions about talent mobility.
@Fenng: HuggingFace and GitHub charts hit top four, stars surpass 10k in just 5 days — Baidu Unlimited OCR becomes one of the fastest growing open source projects. I've seen many people mentioning Baidu's Unlimited-OCR in my timeline lately. Actually, OCR has always been a traditional strength of Baidu…
Baidu's open source project Unlimited-OCR tops four charts on HuggingFace and GitHub, with stars exceeding 10k in five days. The model uses a MoE architecture (3B total parameters, 570M activated parameters) and excels at continuous recognition of long documents. Inspired by how humans copy books, it also offers new ideas for long-term memory management in large models.
@geekbb: Baidu's open-source visual language model OCR project, upgraded from DeepSeek-OCR, focuses on one-shot parsing of extremely long documents. The model has two inference modes: 'gundam' mode for dense text in a single image, and 'base' mode for multi-page or PDF processing. https://github…
Baidu has open-sourced the visual language model Unlimited-OCR, upgraded from DeepSeek-OCR, supporting one-shot parsing of extremely long documents, offering two inference modes: gundam (dense text in a single image) and base (multi-page/PDF).