# Baidu Unlimited-OCR — 3B vision model parses long documents in one pass

> Baidu's open 3B OCR model swaps standard attention for R-SWA so it can transcribe dozens of pages without the usual KV-cache blowup.

- Org: Baidu
- Date: 2026-06-22
- Category: model, paper, algorithm, repo
- Source: https://arxiv.org/abs/2606.23050
- Canonical page: https://ai-tldr.dev/releases/baidu-unlimited-ocr/

## In short

Baidu's Unlimited-OCR is a 3B vision-language model that introduces Reference Sliding Window Attention to keep a constant KV cache, letting one forward pass transcribe dozens of document pages within a 32K context. Code and weights ship under MIT.

## What it is

Unlimited-OCR is a 3B open-weight vision-language model from Baidu, released under MIT with code and weights on Hugging Face. The model parses single images, multi-page documents, and PDFs as one job and supports outputs up to 32,768 tokens.

## How it works

Reference Sliding Window Attention replaces the decoder's standard attention so the KV cache stays a constant size as the output grows. Two inference modes ship out of the box — a 'gundam' setting that crops dense images and a 'base' setting tuned for multi-page documents — both driven from Hugging Face Transformers or SGLang.

## Why it matters

Most OCR stacks force callers to slice a document into pages, run inference per page, then stitch the results back together. Unlimited-OCR turns long-document transcription into a single forward pass, which simplifies pipelines for archives, contracts, invoices, and any workload where chunking loses cross-page context.

## Who it's for

OCR engineers, document-AI teams, researchers building long-output decoders

## Try it

pip install transformers && git clone https://github.com/baidu/Unlimited-OCR

## Quick facts

- Maker: Baidu
- License: MIT
- Parameters: 3B
- Max context: 32,768 tokens
- Innovation: Reference Sliding Window Attention (R-SWA)
- Availability: Hugging Face, GitHub, ModelScope
- Inference: Hugging Face Transformers, SGLang, OpenAI-compatible API

## FAQ

### How is Baidu's Unlimited-OCR different from other OCR models?

Unlimited-OCR replaces the decoder's standard attention with Reference Sliding Window Attention, which keeps the KV cache constant as the output grows. That lets the 3B vision-language model transcribe dozens of document pages in one forward pass, where typical OCR models stall on KV memory after a few pages.

### Is Baidu Unlimited-OCR open source?

Yes. Baidu released Unlimited-OCR under the MIT license, with code on GitHub at baidu/Unlimited-OCR and weights mirrored to Hugging Face and ModelScope. The repo ships inference paths for Hugging Face Transformers, SGLang, and an OpenAI-compatible API, plus a custom no-repeat n-gram sampler.

### Can Unlimited-OCR's attention trick help non-OCR tasks?

The Unlimited-OCR paper argues Reference Sliding Window Attention generalizes to other long-output decoders such as automatic speech recognition and machine translation, anywhere a growing KV cache caps how much a model can emit before memory runs out. The current 3B release is OCR-tuned, but the operator is task-agnostic.

### What does 'one-shot long-horizon parsing' actually mean here?

Unlimited-OCR processes a single image, a multi-page document, or a PDF in one forward pass instead of chunking it into per-page calls. Two modes are exposed: a 'gundam' setting with configurable crop windows for dense single images, and a 'base' setting tuned for multi-page documents up to the 32,768-token output budget.

## Links

- [arXiv Paper](https://arxiv.org/abs/2606.23050)
- [GitHub](https://github.com/baidu/Unlimited-OCR)
- [Hugging Face](https://huggingface.co/baidu/Unlimited-OCR)
- [ModelScope](https://modelscope.cn/models/PaddlePaddle/Unlimited-OCR)