Model
UnlimitedOcr
A single OCR large model released by Baidu. It has long-context capability and can transcribe dozens of pages of documents in a single forward pass.
Timeline (last 90 days)
Oct 15
Baidu's UnlimitedOcr is a 3B-parameter OCR model with a context length of 32,768 tokens, built on DeepSeek OCR, replacing all decoder attention layers with Reference Sliding Window Attention (R-SWA), keeping the KV cache constant, and can transcribe dozens of pages in a single forward pass.
Unverified50%