Artificial intelligence / news brief
Baidu opens Unlimited OCR 2 for very long document parsing
- Event
- Published
Baidu released the 3.34B-parameter Unlimited OCR 2 model, weights and code under the MIT license. Its SR-SWA mechanism keeps per-step decoding memory and latency nearly flat as documents grow, according to Baidu, while its leading long-document benchmark scores remain self-reported and MarathonDocBench is not publicly available.
Why it matters
The release makes long-document OCR runnable outside a closed API, but the claimed scaling and accuracy still need independent reproduction.
Sources
- Unlimited OCR 2 model card (external site)Baidu · primary source ·
- Baidu Open-Sources Unlimited OCR 2 for Hundred-Page Document Parsing (external site)MarkTechPost · coverage ·
- Baidu's Unlimited-OCR-2 reads whole books with a fixed memory budget (external site)AIholics · coverage ·