SieveIVF accelerates embedding deduplication by stopping each IVF query after W consecutive threshold-empty partitions, preserving batching with continuous regrouping and a lookahead scheduler.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DB 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SieveIVF: Threshold-Aware IVF Execution for Large-Scale Training Data Deduplication
SieveIVF accelerates embedding deduplication by stopping each IVF query after W consecutive threshold-empty partitions, preserving batching with continuous regrouping and a lookahead scheduler.