MV-HNSW is the first native hierarchical graph index for multi-vector data, achieving over 90% recall with up to 14x lower search latency than prior filter-and-refine approaches across seven datasets.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.DB 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Garfield introduces the GMG index and GPU pipeline for multi-attribute RFANNS, achieving 4.4x smaller indexes and 119.8x higher throughput than existing approaches.
citing papers explorer
-
Unified and Efficient Approach for Multi-Vector Similarity Search
MV-HNSW is the first native hierarchical graph index for multi-vector data, achieving over 90% recall with up to 14x lower search latency than prior filter-and-refine approaches across seven datasets.
-
A GPU-Accelerated Framework for Multi-Attribute Range Filtered Approximate Nearest Neighbor Search
Garfield introduces the GMG index and GPU pipeline for multi-attribute RFANNS, achieving 4.4x smaller indexes and 119.8x higher throughput than existing approaches.