Unlimited OCR Works

Published
Source
arXiv
Paper number
468
Field
Computer Vision
arXiv ID
2606.23050

Key points

  • Reference Sliding Window Attention (R-SWA) keeps the KV cache constant by giving reference tokens full attention and output tokens a sliding window of 128.
  • On OmniDocBench v1.5, it improves by 6% over DeepSeek OCR, reaching 93%, with an MoE structure that uses only 0.5B active parameters.
  • It can process more than 40 pages at once and is 35% faster when generating 6,000 tokens.
  • Replacing full standard attention with R-SWA does not reduce single-page OCR accuracy.
  • It was developed by Baidu, and the code and weights are released on GitHub.

Paper links

External research summaries. These are not HDATF publications or measured product results.

Read original (opens in a new tab)