Baidu has released 'Unlimited OCR,' an AI model designed to read long documents in a single step, as open source. Unlimited OCR is an OCR model that reads text contained in images and PDFs, with a particular emphasis on analyzing long documents that span multiple pages. The model has "3B total parameters and only 500M activated," and sets "new end-to-end SOTA results on OmniDocBench v1.5 and v1.6." The key innovation is "Reference Sliding Window Attention (R-SWA)." Unlimited OCR was released to address long-text processing challenges, using "DeepSeek-OCR," released in October 2025, as a baseline. The paper explains that it can transcribe documents of several tens of pages in a single inference process, under the condition of a maximum context length of 32K. R-SWA uses reference information such as document images, treating a certain range of the most recent output text as working memory, instead of storing all output indefinitely.