FrontierThe story, in brief
Baidu's "Unlimited OCR" processes dozens of document pages in one pass by treating memory like human forgetting
Baidu just 3x'd OCR capacity. A modified attention mechanism processes 30+ pages where competitors max out at 10—and memory stays flat.
The KeyNews take
Why it matters
Baidu's architectural breakthrough in attention mechanisms addresses a hard constraint in document AI, signaling a shift in how models manage context and memory trade-offs. This matters for enterprise document processing workflows and sets a new performance bar for the OCR benchmark.
The key facts
4 to knowBaidu Unlimited OCR processes 30+ document pages in single pass (vs. previous 10-page limit)
Modified attention mechanism maintains flat memory usage regardless of page count
Top score on primary OCR benchmark
Architecture treats memory like 'human forgetting' — selective retention mechanism
Go to the source
The Decoderthe-decoder.com
Publisher excerpt: Baidu's Unlimited OCR reads dozens of document pages in a single pass, where previous systems topped out at about ten. A modified attention mechanism keeps memory use flat no matter how many pages the model processes. It currently holds the top spot on the most important OCR benchmark.