Unverified50% confidenceFactExact time
Unlimited OCR 2 can parse hundreds of pages or even longer documents in a single uninterrupted pass while keeping computational cost constant.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/30/2026
First Seen
Valid until: 1/28/2027
Sources
Related Entities
Related Claims
UnverifiedBaidu has open-sourced the Unlimited OCR 2 model.75% similarUnverifiedAt the hundred-page document scale, Unlimited OCR 2 achieves a 5.6x per-step speedup over R-SWA.65% similarUnverifiedBaidu'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.64% similarUnverifiedThe cost of multi-vector approaches is that each document requires storing multiple vectors, making index sizes typically several to tens of times larger than single-vector approaches and placing higher demands on vector database storage and ANN search performance.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1113978API
curl https://kongchang.com/api/v1/knowledge/claims/1113978MCP
get_claim(id=1113978)