DIVE proposes a dimensionality-reduction adapter using self-limiting gradients and implicit view ensembles that outperforms prior adapters on all six BEIR datasets at every tested compression ratio.
DiskANN: Fast Accurate Billion-point Nearest Neighbor Search on a Single Node , url =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
DIVE: Embedding Compression via Self-Limiting Gradient Updates
DIVE proposes a dimensionality-reduction adapter using self-limiting gradients and implicit view ensembles that outperforms prior adapters on all six BEIR datasets at every tested compression ratio.