pith. sign in

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , month =

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.CL 1 cs.LG 1

years

2026 2

verdicts

UNVERDICTED 2

representative citing papers

Is Dimensionality a Barrier for Retrieval Models?

cs.LG · 2026-05-22 · unverdicted · novelty 8.0

Dimension d = O(m^{-2} log n) nearly achieves the optimal margin m^rd(+∞, A) for retrieval embeddings, with matching lower bounds showing d = O(k log(n/k)) suffices and is necessary for m = Θ(k^{-1/2}) on k-sparse query matrices.

DIVE: Embedding Compression via Self-Limiting Gradient Updates

cs.CL · 2026-05-20 · unverdicted · novelty 5.0

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.

citing papers explorer

Showing 2 of 2 citing papers.

  • Is Dimensionality a Barrier for Retrieval Models? cs.LG · 2026-05-22 · unverdicted · none · ref 125

    Dimension d = O(m^{-2} log n) nearly achieves the optimal margin m^rd(+∞, A) for retrieval embeddings, with matching lower bounds showing d = O(k log(n/k)) suffices and is necessary for m = Θ(k^{-1/2}) on k-sparse query matrices.

  • DIVE: Embedding Compression via Self-Limiting Gradient Updates cs.CL · 2026-05-20 · unverdicted · none · ref 17

    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.