SOURCE-LINKED INTELLIGENCE

AdaptiveEmbed: Sample-Adaptive Multi-Vector Representation for Multimodal Retrieval

arXiv · AI, language, vision and robotics · article · Aug 26, 2026 · UTC

Multi-vector representations have emerged as an effective paradigm for multimodal retrieval, representing each sample with multiple complementary embeddings to capture fine-grained cross-modal information. However, existing approaches typically employ a fixed representation capacity, assigning the same number of vectors to all samples regardless of their individual retrieval demands. Such a fixed-capacity formulation overlooks the fact that different samples may require different amounts of representation capacity for effective retrieval. In this work, we introduce \emph{Sample-Adaptive Multi-

Read original source ↗ Open in workspace

recordType

paper

region

Global