Unlimited OCR 2 模型在解析长文档时实现恒定计算成本

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-02 05:00

研究人员推出 Unlimited OCR 2，这是一种新颖的文档解析模型，旨在处理几乎无限长度的文档，而不会产生高昂的内存开销。该模型将解码器注意力模块升级为稀疏参考滑动窗口注意力 (SR-SWA)，通过将活动参考令牌限制在固定容量内来维持恒定的计算成本。这种方法实现了显著的加速，在百页文档上，每步比全注意力 (Full Attention) 和 R-SWA 分别提高了 7.0 倍和 5.6 倍。Unlimited OCR 2 在专门为解析长文档设计的新基准 MPDocBench 和 MarathonDocBench 上也展示了最先进的性能。 AI

影响能够高效解析极长的文档，可能改变大规模文档分析和转录的处理方式。

排序理由该集群描述了一篇关于新模型架构和文档解析基准的最新研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 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: 1 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群描述了一篇关于新模型架构和文档解析基准的最新研究论文。[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: paper, model release; 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: 1 days old; Coverage has settled into its steady-state source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Shu Wei, Jingjing Wu, Qunyi Xie, Lingshu Zhang, Xiangcheng Du, Yannian Fu, Mengjie Wang, Zuyi Wang, Zhichao Liu, Yangliu Xu, Youyang Yin, Huanhuan Liu, YY, Yi Yang · 2026-11-02 05:00

Unlimited OCR Works 2

arXiv:2610.39308v2 Announce Type: replace Abstract: Unlimited OCR ushers the era of long-horizon parsing, substantially mitigating the growth of working memory as document lengthens. However, as document length scales to hundreds of pages, the visual context grows substantially, …

本文如何被排名

报道来源 [1]

Unlimited OCR Works 2

相关实体

相关话题