Baidu open-sources Wenxin Unlimited OCR 2 for long-document parsing
Understand the event
Baidu released and open-sourced Wenxin Unlimited OCR 2, making its code and model weights available on GitHub and Hugging Face and offering it through Baidu AI Cloud and Baidu’s AI Open Platform. Baidu says the model can parse documents without a page limit. QbitAI reports that the model’s technical report combines sparse reference sliding-window attention with chunked decoding, reducing peak KV cache usage from 47GB to 1.77GB in a hundred-page-scale single-sequence test. Those figures exclude model weights and other memory costs. In a separate 16-way concurrency test, throughput increased from 360 to 1315 tokens per second. QbitAI also reports that the model parsed an 884-page English edition of The Lord of the Rings in approximately 42 minutes and 56 seconds. Leiphone reports scores of 84.6 on MPDocBench and 77.1 on MarathonDocBench, along with seven times faster single-step decoding than Full Attention on hundred-page documents using the model’s SR-SWA attention mechanism.
Generated by AI from reports · Updated 3 days ago
Read next
More changes in today’s briefingMistral releases improved Mistral Large 4 open weights for coding and cybersecurityReport timeline
Follow the reports to explore different sides of the event.
- Baidu Releases Open-Source Unlimited OCR 2 With Lower Long-Document KV Cache Usage
Baidu released and open-sourced Unlimited OCR 2 for continuous long-document parsing. Its technical report pairs sparse reference sliding-window attention with chunked decoding, reducing peak KV cache usage from 47GB to 1.77GB in a hundred-page-scale single-sequence test, excluding model weights and other memory costs. In a separate 16-way concurrency test, throughput rose from 360 to 1315 tokens per second; QbitAI also reports parsing an 884-page English edition of The Lord of the Rings in approximately 42 minutes and 56 seconds.
- Baidu releases and open-sources Wenxin Unlimited OCR 2 for long document parsing
Baidu released and open-sourced Wenxin Unlimited OCR 2 on October 27, claiming document parsing without a page limit. The report cites scores of 84.6 on MPDocBench and 77.1 on MarathonDocBench, and says its SR-SWA attention mechanism delivers 7x faster single-step decoding than Full Attention on hundred-page documents. Code and model weights are available at https://github.com/baidu/Unlimited-OCR and https://huggingface.co/baidu/Unlimited-OCR-2.
Keep up with AI, one email a day
Model releases, price changes and compute developments, with original sources. Free, confirmed by email, and easy to unsubscribe. Read a past issue
Event heat trend
- Current within comparable coverage
- 3
- Peak within comparable coverage
- 1910/27 17:00 (UTC+8)
- 24-hour change
- -75%
Trends compare the same continuously observed participants, which may cover fewer sources than current heat. Point or click to inspect hourly heat, or use left and right arrow keys.