Machine Heart
Jun 23, 2026 · Artificial Intelligence
Unlimited OCR Achieves SOTA Long-Document Parsing in a Single Forward Pass
Unlimited OCR, Baidu's open‑source model built on DeepSeek OCR, uses a novel Reference Sliding Window Attention to compress visual tokens and keep KV cache size constant, enabling end‑to‑end parsing of whole books with 93.23% OmniDocBench v1.5 score and stable latency across dozens of pages.
DeepSeekLarge Language ModelLong Document
0 likes · 14 min read
