EGA adapter induces gradient sparsity so that 96.5% of triplets become inactive at convergence, preserving unseen-class geometry while refining seen classes and improving worst-case Label Precision on OOD benchmarks.
Diskann: fast accurate billion-point nearest neighbor search on a single node
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
MCGI adapts graph-based vector search to data manifolds via local intrinsic dimensionality to improve approximation quality and stability at billion scale.
citing papers explorer
-
EGA: Adapting Frozen Encoders for Vector Search with Bounded Out-of-Distribution Degradation
EGA adapter induces gradient sparsity so that 96.5% of triplets become inactive at convergence, preserving unseen-class geometry while refining seen classes and improving worst-case Label Precision on OOD benchmarks.
-
MCGI: Manifold-Consistent Graph Indexing for Billion-Scale Disk-Resident Vector Search
MCGI adapts graph-based vector search to data manifolds via local intrinsic dimensionality to improve approximation quality and stability at billion scale.