新的剪枝方法大幅减小视觉文档检索模型尺寸

作者 PulseAugur 编辑部 · [1 个来源] · 2026-05-22 04:00

研究人员开发了一种新颖的无训练方法——结构锚点剪枝（SAP），用于压缩视觉文档检索模型。SAP通过识别和剪枝冗余的视觉标记来解决这些模型中多向量索引的显著存储开销问题，且无需依赖查询进行训练。该框架利用得分保留诊断和视觉入度中心性评分器，在保持高检索精度的同时有效减小了索引尺寸。 AI

影响引入了一种降低视觉文档检索系统存储成本的技术，可能支持更广泛的部署。

排序理由该集群包含一篇详细介绍新模型压缩方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

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: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍新模型压缩方法的学术论文。[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, 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: 102 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。

arXiv cs.CL TIER_1 English(EN) · Zhuchenyang Liu, Ziyu Hu, Yao Zhang, Yu Xiao · 2026-05-22 04:00

结构锚点剪枝：用于视觉文档检索的无训练多向量压缩

arXiv:2601.20107v2 Announce Type: replace-cross Abstract: Recent Vision-Language Models (e.g., ColPali) enable fine-grained Visual Document Retrieval (VDR) but incur prohibitive multi-vector index storage overhead. Existing training-free pruning methods either rely on heuristic l…