# MarathonDocBench

Baidu released Unlimited OCR 2, aiming to move document parsing from long documents to unlimited-horizon parsing. Earlier OCR models let text and visual tokens interact across ultra-long sequences, so computation grew with length; the new version uses Sparse Reference Sliding Window Attention (SR-SWA) to compress those interactions onto a fixed-size set of working references, for example 512 tokens, bounding computational complexity. The release also introduces MarathonDocBench, a benchmark for ultra-long document parsing, and the model is served through Transformers, vLLM and SGLang.

Baidu released Unlimited OCR 2, aiming to move document parsing from long documents to unlimited-horizon parsing. Earlier OCR models let text and visual tokens interact across ultra-long sequences, so computation grew with length; the new version uses Sparse Reference Sliding Window Attention (SR-SWA) to compress those interactions onto a fixed-size set of working references, for example 512 tokens, bounding computational complexity. The release also introduces MarathonDocBench, a benchmark for ultra-long document parsing, and the model is served through Transformers, vLLM and SGLang.