LAANN introduces I/O-aware look-ahead techniques for disk-based ANNS and reports 1.41x-4.66x higher throughput with fewer I/O operations at Recall@10=0.9 on large 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
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Onyx inverts ANN-ORAM optimization priorities with a compact pruning representation and locality-aware shallow tree to deliver 1.7-9.9x lower cost and 2.3-12.3x lower latency for disk-oblivious ANN search.
citing papers explorer
-
LAANN: I/O-Aware Look-Ahead Search for Disk-Based Approximate Nearest Neighbor Search
LAANN introduces I/O-aware look-ahead techniques for disk-based ANNS and reports 1.41x-4.66x higher throughput with fewer I/O operations at Recall@10=0.9 on large datasets.
-
Onyx: Cost-Efficient Disk-Oblivious ANN Search
Onyx inverts ANN-ORAM optimization priorities with a compact pruning representation and locality-aware shallow tree to deliver 1.7-9.9x lower cost and 2.3-12.3x lower latency for disk-oblivious ANN search.