Realtime AI News
Baidu Unveils OCR Model Processing 40 Pages at Once
Baidu has released a new OCR model capable of processing up to 40 pages in a single pass.
Baidu today unveiled a new OCR model that can process 40 pages of documents at once, as reported by Chosun Ilbo (조선일보). This marks a significant leap in efficiency for document digitization.
Traditional OCR models often require page-by-page processing, but the new model leverages an optimized architecture to handle multiple pages in parallel. This reduces the time needed for bulk document recognition.
The release comes as AI continues to transform office automation. Baidu has a strong track record in OCR technology, and this update strengthens its position in the enterprise market.
While detailed benchmarks are not yet public, the claimed 40-page capability sets a new bar for the industry. Practical performance will be closely watched.
Why it matters
This model will accelerate document digitization and boost office automation efficiency.
Nearby Updates
All06/29, 04:46
The 14th Internet Security Conference opens in Beijing: Moving from consensus to action in the age of agents
The 14th Internet Security Conference opens in Beijing, focusing on moving from consensus to action in security governance in the age of agents.
06/29, 04:42
xAI unveils Grok 4.5, a significant upgrade powered by 1.5 trillion parameter V9 model
xAI unveils Grok 4.5, a significant upgrade powered by a 1.5 trillion parameter V9 model.
06/29, 05:42
China's Z.ai Claims It Can Match Mythos on Cybersecurity
Chinese AI company Z.ai publicly claims its cybersecurity capabilities are on par with Mythos, according to a report by The Verge.
06/29, 03:05
Ford Rehires 'Gray Beard' Engineers After AI Falls Short
Ford admits it mistakenly thought that just introducing AI would produce high quality products, and is now rehiring experienced engineers to bridge the gap.