PulseAugur
EN
LIVE 08:11:03

Baidu releases Unlimited OCR 2 for long document parsing

By PulseAugur Editorial · [1 sources] ·

Baidu has released Unlimited OCR 2, an open-source optical character recognition model designed for parsing lengthy documents. This 3.34B parameter model can process hundreds of pages in a single request, achieving top performance on benchmarks like MarathonDocBench. Its key innovation is SR-SWA, a sparse attention mechanism that maintains consistent decoding costs regardless of document length, enabling near-unlimited context parsing. AI

IMPACT Sets a new standard for long document OCR, potentially accelerating research and application development in fields requiring extensive text analysis.

RANK_REASON Frontier-lab model release with system card and benchmark results. [lever_c_demoted from frontier_release: ic=1 ai=1.0]

Read on MarkTechPost →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Baidu releases Unlimited OCR 2 for long document parsing

How we ranked this

Signal score
41 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Significant
Frontier-lab model release with system card and benchmark results. [lever_c_demoted from frontier_release: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
model release, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. MarkTechPost TIER_1 English(EN) · Asif Razzaq ·

    Baidu Open-Sources Unlimited OCR 2 for Hundred-Page Document Parsing

    <p>Baidu has released Unlimited OCR 2, an MIT-licensed 3B OCR model that parses hundred-page documents in one request. Its SR-SWA attention keeps per-step decoding cost nearly flat, scoring 77.1 on MarathonDocBench</p> <p>The post <a href="https://www.marktechpost.com/2026/10/26/…

RELATED ENTITIES

RELATED TOPICS