SOURCE-LINKED INTELLIGENCE

RegRet: Enhancing Region-Level Retrieval in Large Multimodal Models

arXiv · AI, language, vision and robotics · article · Sep 15, 2026 · UTC

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 Multimodal Models (LMMs) have made significant strides in multimodal retrieval, they primarily focus on global-level tasks and struggle to capture effective region-level representations. To bridge this gap, we present RegRet, an LMM-based Region-level Retrieval framework that enhances the regional representations without compromising overall global retrieval performance.

Read original source ↗ Open in workspace

recordType

paper

region

Global