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.
Proceedings of the 36th International Conference on Neural Information Processing Systems , articleno =
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.