百度开源了一个3B参数的OCR模型，能一口气解析几十页文档，KV缓存不膨胀，性能直接碾压DeepSeek。
百度开源Unlimited OCR，一个3B参数的MoE模型，能在单次前向推理中解析数十页文档。其突破性的Reference Sliding Window Attention (R-SWA)机制使KV缓存保持恒定，随着输出增长内存和延迟不变。模型在OmniDocBench v1.5基准上获得93.23分，比DeepSeek OCR基线高出6.22分。该模型采用MIT许可证开源。
Baidu Releases Unlimited OCR, a 3B Model That Keeps the KV Cache Flat for Long-Document Parsing
Baidu open-sourced Unlimited OCR, a 3B-parameter MoE model that parses dozens of document pages in a single forward pass. Its Reference Sliding Window Attention (R-SWA) holds the KV cache constant, so memory and latency stay flat as output grows. It scores 93.23 on OmniDocBench v1.5, beating the DeepSeek OCR baseline by 6.22 points, under an MIT license. The post Baidu Releases Unlimited OCR, a 3B Model That Keeps the KV Cache Flat for Long-Document Parsing appeared first on MarkTechPost .