pith. sign in

Bootstrap your own latent-a new approach to self-supervised learning

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

2 Pith papers citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.LG 2

years

2025 1 2023 1

roles

background 1

polarities

background 1

representative citing papers

Consistency Models

cs.LG · 2023-03-02 · conditional · novelty 8.0

Consistency models achieve fast one-step generation with SOTA FID of 3.55 on CIFAR-10 and 6.20 on ImageNet 64x64 by directly mapping noise to data, outperforming prior distillation techniques.

Self-Supervised Learning by Curvature Alignment

cs.LG · 2025-11-21 · unverdicted · novelty 6.0

CurvSSL augments Barlow Twins-style SSL with a curvature alignment loss computed from k-nearest-neighbor cosine scores on the unit hypersphere, yielding competitive linear evaluation accuracy on MNIST and CIFAR-10.

citing papers explorer

Showing 2 of 2 citing papers.

  • Consistency Models cs.LG · 2023-03-02 · conditional · none · ref 16

    Consistency models achieve fast one-step generation with SOTA FID of 3.55 on CIFAR-10 and 6.20 on ImageNet 64x64 by directly mapping noise to data, outperforming prior distillation techniques.

  • Self-Supervised Learning by Curvature Alignment cs.LG · 2025-11-21 · unverdicted · none · ref 10

    CurvSSL augments Barlow Twins-style SSL with a curvature alignment loss computed from k-nearest-neighbor cosine scores on the unit hypersphere, yielding competitive linear evaluation accuracy on MNIST and CIFAR-10.