# Baidu open-sources Unlimited OCR 2 for parsing documents of any length

> Original title: Unlimited OCR 2 is here, and it's open source. 📖 ✨

- Source: Baidu Inc.
- Published: 2026-10-27T02:41:42.000Z
- Bad Influence: https://badinfluence.news/items/e78b6rg9oazsi2aoefrainotq
- Original: https://x.com/Baidu_Inc/status/2114910381311512987

## Summary

Baidu releases Unlimited OCR 2 as an open-source model that parses documents of virtually any length within a finite context window. Its SR-SWA mechanism condenses text-visual attention into a fixed-size set of working references, keeping per-step decoding latency and memory nearly constant as documents grow. Baidu says the model achieves state-of-the-art results on MPDocBench and MarathonDocBench, which cover documents from dozens to hundreds of pages.

## Post

Unlimited OCR 2 is here, and it's open source. 📖 ✨

Longer documents can mean a lot more attention computation. Our new SR-SWA mechanism keeps that in check by condensing text-visual attention interactions into a fixed-size set of working references.

Here's what it delivers:
- Document parsing at virtually any length, within a finite context window
- Nearly constant per-step decoding latency and memory footprint as documents grow longer
- State-of-the-art performance on MPDocBench and MarathonDocBench, covering documents from dozens to hundreds of pages

Check out the model here ↓

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHVmbZoiakAAtEgn.jpg&mode=thumb&exp=1793404800&sig=7c268b9337b43105)

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHVmbZptagAAcnGm.jpg&mode=thumb&exp=1793404800&sig=be60ae67e36f7fe3)