---
type: "post"
id: "unlimited-ocr-2-builds-on-deepseek-ocr-deepseek-8f6931"
slug: "unlimited-ocr-2-builds-on-deepseek-ocr-deepseek-8f6931"
title: "Unlimited OCR 2 builds on DeepSeek-OCR, DeepSeek-OCR-2, PaddleOCR, and Baidu’s first Unlimited OCR release."
description: "A technical report titled “Unlimited OCR Works” proposes Reference Sliding Window Attention (R-SWA) for long-document OCR."
retrieval_nugget: "A technical report titled “Unlimited OCR Works” proposes Reference Sliding Window Attention (R-SWA) for long-document OCR."
published_at: "2026-10-27"
updated_at: "2026-10-27"
record_date: "2026-10-27"
date_kind: "published_at"
topics: ["multimodal","models"]
entities: ["Unlimited OCR","DeepSeek OCR","Youyang Yin"]
related_patterns: []
novelty_label: "same_event"
what_changed: "Same event as Unlimited OCR: OCR без нарезки документа на куски"
prior_refs: ["memory:d5a0da2e-9dab-87db-ab2a-11b5658e776c"]
source_url: "https://arxiv.org/abs/2606.23050"
source_urls: ["https://arxiv.org/abs/2606.23050"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:unlimited-ocr-2-builds-on-deepseek-ocr-deepseek-8f6931"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/unlimited-ocr-2-builds-on-deepseek-ocr-deepseek-8f6931/","markdown":"https://newruntime.com/posts/unlimited-ocr-2-builds-on-deepseek-ocr-deepseek-8f6931.md","json":"https://newruntime.com/posts/unlimited-ocr-2-builds-on-deepseek-ocr-deepseek-8f6931.json"}
related_shifts: ["document-processing-shifts-from-hand-crafted-ocr-pipelines-to-llm"]
---

# Unlimited OCR 2 builds on DeepSeek-OCR, DeepSeek-OCR-2, PaddleOCR, and Baidu’s first Unlimited OCR release.

## Retrieval answer

A technical report titled “Unlimited OCR Works” proposes Reference Sliding Window Attention (R-SWA) for long-document OCR.

A technical report titled “Unlimited OCR Works” proposes Reference Sliding Window Attention (R-SWA) for long-document OCR. The authors use DeepSeek OCR as a baseline and replace all attention layers in its decoder with R-SWA.

The authors say the design keeps the key-value cache constant during decoding, addressing memory use that grows with output length. Combined with DeepSeek OCR’s encoder compression, it can transcribe dozens of document pages in one forward pass under a standard maximum length of 32K.

The report describes R-SWA as a general-purpose parsing attention mechanism that could also be applied to speech recognition and translation. The code and model weights are publicly available, according to the paper. The source does not establish comparative accuracy or performance on independent benchmarks, and it does not report results for those other proposed applications.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Multimodal](https://newruntime.com/topics/multimodal.md): Explore the multimodal topic hub.
- topic hub: [Models](https://newruntime.com/topics/models.md): Explore the models topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)