PulseAugur
中
实时 03:50:44
English(EN) Query-Aware Token Budgeting for Efficient Late-Interaction Visual Document Retrieval

新方法提高视觉文档检索效率

作者 PulseAugur 编辑部 · [4 个来源] ·

两篇新研究论文提出了提高晚期交互式视觉文档检索系统效率的方法。第一篇论文介绍了生成式晚期交互式嵌入（GLIE），它使用一小组学习到的向量按需重新生成完整的嵌入集，在保持高精度的同时显著降低了存储需求。第二篇论文侧重于查询感知令牌预算，提出根据查询动态分配检索资源可以比静态池化方法恢复更高百分比的完整令牌分数。这两种方法都旨在使大规模视觉文档检索的部署更具成本效益。 AI

影响 这些方法可以显著降低与大规模视觉文档检索系统相关的计算和存储成本。

排序理由 两篇arXiv论文提出了视觉文档检索的新颖方法。

在 arXiv cs.IR (Information Retrieval) 阅读 →

AI 生成摘要 · Google Gemini · 来自 4 个来源。 我们如何撰写摘要 →

新方法提高视觉文档检索效率

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
两篇arXiv论文提出了视觉文档检索的新颖方法。
Source corroboration
4 independent sources
Strong cross-source corroboration — multiple independent publishers covered this within the clustering window.
Topics
paper, infra
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
35 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [4]

  1. arXiv cs.IR (Information Retrieval) TIER_1 English(EN) · Naeemullah Khan ·

    用于视觉文档检索的生成式晚期交互嵌入

    Late-interaction retrieval is the state-of-the-art for visual document search, but it pays for its accuracy in storage. Existing compression methods retain a subset or local average of the N~1,000 vectors per page. Under aggressive storage budgets, however, these methods degrade …

  2. arXiv cs.AI TIER_1 English(EN) · PS Rishi, Rajeev Ranjan Dwivedi, Vinod K Kurmi ·

    面向高效晚期交互视觉文档检索的查询感知令牌预算

    arXiv:2609.07262v1 Announce Type: cross Abstract: Late-interaction visual document retrievers preserve fine-grained page evidence by storing many token embeddings per page, but the resulting storage and query-time interaction costs make large-scale deployment expensive. Pooling d…

  3. Hugging Face Daily Papers TIER_1 English(EN) ·

    用于视觉文档检索的生成式晚期交互嵌入

    Generative Late-Interaction Embeddings compress visual document retrieval vectors by learning a small basis set that regenerates full embeddings on demand, improving accuracy under tight storage limits without retraining the encoder.

  4. arXiv cs.IR (Information Retrieval) TIER_1 English(EN) · Vinod K Kurmi ·

    面向高效晚期交互视觉文档检索的查询感知令牌预算

    Late-interaction visual document retrievers preserve fine-grained page evidence by storing many token embeddings per page, but the resulting storage and query-time interaction costs make large-scale deployment expensive. Pooling document tokens before indexing offers a natural re…

相关实体

相关话题