Italiano(IT) RegRet: Enhancing Region-Level Retrieval in Large Multimodal Models

新的RegRet框架增强了大型多模态模型中的区域级检索能力

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-16 04:00

研究人员开发了RegRet，一个旨在提高大型多模态模型（LMMs）区域级检索能力的新框架。该框架集成了区域感知编码器，以更好地捕捉详细的图像区域特征，同时保持全局检索性能。RegRet还采用了多阶段训练流程，包括本地化字幕生成和区域对比学习，以增强细粒度理解。为解决区域级对比数据和多样化评估任务的缺乏问题，引入了REGMB基准，该基准包含在四个多模态检索任务中的225,000个对比对。 AI

影响这项研究可能显著提高图像区域检索的准确性，对电子商务和RAG系统等应用产生影响。

排序理由该集群描述了一篇详细介绍多模态模型新框架和基准的新研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 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: 14 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群描述了一篇详细介绍多模态模型新框架和基准的新研究论文。[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: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 Italiano(IT) · Xun Liang, Honghui Yang, Weihang Pan, Ruisi Zhao, Boyuan Pan, Yao Hu, Wenxiao Wang, Binbin Lin, Deng Cai · 2026-09-16 04:00

RegRet：增强大型多模态模型中的区域级检索

arXiv:2609.16847v1 Announce Type: cross Abstract: Region-level retrieval aims to align user-specified image regions with relevant regions or textual descriptions, playing a crucial role in realworld applications such as e-commerce product search and RAG. Although recent Large Mul…

本文如何被排名

报道来源 [1]

RegRet：增强大型多模态模型中的区域级检索

相关实体

相关话题