Baidu Releases Unlimited OCR, a 3B Model That Keeps the KV Cache Flat for Long-Document Parsing

Read full story on MarkTechPost
Share
Baidu Releases Unlimited OCR, a 3B Model That Keeps the KV Cache Flat for Long-Document Parsing
AI disclosure

Summary

<p>Baidu open-sourced Unlimited OCR, a 3B-parameter MoE model that parses dozens of document pages in a single forward pass. Its Reference Sliding Window Attention (R-SWA) holds the KV cache constant, so memory and latency stay flat as output grows. It scores 93.23 on OmniDocBench v1.5, beating the DeepSeek OCR baseline by 6.22 points, under an MIT license.</p> <p>The post <a href="https://www.marktechpost.com/2026/06/24/baidu-releases-unlimited-ocr-a-3b-model-that-keeps-the-kv-cache-flat-for-long-document-parsing/">Baidu Releases Unlimited OCR, a 3B Model That Keeps the KV Cache Flat for Long-Document Parsing</a> appeared first on <a href="https://www.marktechpost.com">MarkTechPost</a>.</p>

Original reporting

Open original source
Read full article on MarkTechPost

Get the AFBytes Brief

Major stories, AI-assisted analysis, and what to watch next. Free, monthly, unsubscribe anytime.