tarasovcode
Models1 min readMarkTechPost

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

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

Save
Share:VKTelegramWhatsApp
Baidu Open-Sources Unlimited OCR 2 for Hundred-Page Document Parsing
Illustration: Tarasov Code

In brief

  • What: Baidu Open-Sources Unlimited OCR 2 for Hundred-Page Document Parsing
  • When: October 27, 2026 at 08:26
  • Source: MarkTechPost (media)
  • Topic: Models

#Open source#Models

Prepared by Ilya Tarasov’s Tarasov Code newsroom based on a report by MarkTechPost.

Read next

MarkTechPost · October 26, 2026Tsinghua AI Open-Sources AKV, a Cache Engineering Server for LLM Agents on SGLangMarkTechPost · October 25, 2026Cognition Open-Sources an Agent Plugin that Helps Secure Systems against Recent Cybersecurity ThreatsLatent Space · October 24, 2026[AINews] Kimi 3.1 Pro 104BA-2.8T: Fable-5.1-Class Open Weights narrows Closed-AI lead to 1 month... and Pro Highspeed API with 2-3× speedInfoQ AI/ML · October 23, 2026Anthropic Adds Opt-In Security Scanning for Critical Open-Source Projects