1.  [](/)
2.  [Research](/research)
3.  Baidu's Unlimited-OCR: The Model Whose Memory Never Grows

[Back to Research](/research)

Baidu[arXiv:2606.23050](https://mxp.co/e/unlimited-ocr)

# Baidu's Unlimited-OCR: The Model Whose Memory Never Grows

Baidu's Unlimited-OCR replaces decoder attention with Reference Sliding Window Attention, turning the KV cache into a fixed-size queue so 40+ page PDFs parse in one forward pass instead of being chopped at page breaks.

## Where this fits in Mixpeek

Mixpeek's document extractor turns PDFs into searchable text, tables, and layout. Long-document OCR is where naive pipelines break: they split PDFs into single pages and cut tables at page boundaries, losing cross-page structure. A fixed-cache, whole-document OCR approach like Unlimited-OCR is the direction for Mixpeek's document ingestion to preserve tables and reading order across long files, so retrieval and reranking see the whole document rather than fragments.

## About this research

Long-document OCR hits a memory wall: the KV cache grows with every token written, so pipelines chop PDFs into single pages and tables get cut at page breaks. Baidu's Unlimited-OCR (MIT, June 2026) replaces decoder attention with Reference Sliding Window Attention: each token attends to the document's visual tokens plus the last 128 outputs, making the cache a fixed-size queue. 40+ page PDFs parse in one forward pass, scoring 93.23 on OmniDocBench v1.5 vs DeepSeek-OCR's 87.01, about 12% faster, from a 3B MoE with 500M active. Paper: arxiv.org/abs/2606.23050

ocrdocument-intelligenceextractionlong-contextpdf

## Frequently asked questions

What is Reference Sliding Window Attention (R-SWA)?+

Why do OCR pipelines split PDFs into single pages?+

## Go deeper

*   [Diagram: Chunking strategies →](/diagrams/chunking-strategies)
*   [Diagram: Four chunking strategies, same document →](/diagrams/chunking)

Put the research to work

Mixpeek turns video, images, audio, and documents in your object storage into searchable, timestamped results through one API: the retrieval stack these papers describe.

[Search your own data](https://studio.mixpeek.com/namespaces/create?mode=managed&utm_source=homepage&utm_medium=research_detail&utm_campaign=mvs_onramp)

## Related research

[

![Meta's SAM 3: Type a Phrase, Segment Every Instance](https://cdn.mixpeek.com/videos/thumbs/79-sam3.jpg)

Meta

Meta's SAM 3: Type a Phrase, Segment Every Instance



](/research/sam3)[

![Mamba Explained: The LLM Architecture With No Attention (5x Faster, Million-Token Context)](https://cdn.mixpeek.com/videos/thumbs/69-mamba.jpg)

Carnegie Mellon & Princeton

Mamba Explained: The LLM Architecture With No Attention (5x Faster, Million-Token Context)



](/research/mamba)