@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)...

X AI KOLs Timeline Models

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.

Baidu's technical strength is still impressive. Recently, this Unlimited OCR has even caught the attention of Yann LeCun! Unlimited OCR proposes the Reference Sliding Window Attention (R-SWA) mechanism. Instead of the traditional 'page-by-page parsing + result stitching' method, it mimics the way humans read and copy long documents, keeping the KV Cache in the decoding stage at a constant size. With just a 3-billion-parameter model, it achieves continuous parsing of dozens of pages in one go. Open-sourced last month, Unlimited OCR hit #1 on both GitHub Trending and HuggingFace model download trend charts the day after its release. Now the project has over 16,500 GitHub stars and more than 2.24 million downloads on HuggingFace. It has once again made it to Trending, currently ranked second, surpassing GLM-5.2 again. As an infrastructure project for cleaning large model training data, Unlimited OCR has attracted the attention of many developers worldwide. #UnlimitedOCR #Baidu #ERNIE #Wenxin
Original Article
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...

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.

@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…

X AI KOLs Timeline

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…

X AI KOLs Following

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…

X AI KOLs Timeline

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).