English(EN) Baidu has open-sourced Unlimited OCR 2, a document parser that reads documents of any length in one pass. It uses Sparse Reference Sliding Window Attention, kee

百度开源Unlimited OCR 2，实现任意长度文档解析

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-28 03:33

百度发布了Unlimited OCR 2，一个开源的文档解析模型，能够一次性处理任意长度的文档。新版本采用了稀疏参考滑动窗口注意力机制，无论文档大小如何，都能保持一致的内存和延迟。百度通过解析整个《哈利·波特》系列展示了其能力，并在MPDocBench基准测试中取得了84.6分。 AI

影响能够处理极长的文档，可能提高法律、研究和档案应用的效率。

排序理由具有基准测试结果的专业AI模型的开源发布。[lever_c_demoted from research: ic=1 ai=1.0]

在 Mastodon — sigmoid.social 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 3 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 具有基准测试结果的专业AI模型的开源发布。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: model release, product; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

Mastodon — sigmoid.social TIER_1 English(EN) · [email protected] · 2026-10-28 03:33

百度开源Unlimited OCR 2，一款可一次性读取任意长度文档的文档解析器。它使用了稀疏参考滑动窗口注意力机制，保持

Baidu has open-sourced Unlimited OCR 2, a document parser that reads documents of any length in one pass. It uses Sparse Reference Sliding Window Attention, keeping memory and latency nearly constant. Baidu says it parsed all seven Harry Potter books, 3,600 pages, in one run, and…

链接 pandaily.com/baidu-open-sources-unlimited…

本文如何被排名

报道来源 [1]

百度开源Unlimited OCR 2，一款可一次性读取任意长度文档的文档解析器。它使用了稀疏参考滑动窗口注意力机制，保持

相关实体

相关话题