pith. sign in

Goal driven discovery of distributional differences via language descriptions

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CV 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

LatentDiff: Scaling Semantic Dataset Comparison to Millions of Images

cs.CV · 2026-04-28 · unverdicted · novelty 6.0

LatentDiff scales semantic dataset comparison to millions of images using latent spaces of vision encoders combined with sparse autoencoders and density ratio estimation, showing better accuracy and robustness than caption-based approaches on a new benchmark for sparse distribution shifts.

citing papers explorer

Showing 1 of 1 citing paper.

  • LatentDiff: Scaling Semantic Dataset Comparison to Millions of Images cs.CV · 2026-04-28 · unverdicted · none · ref 39

    LatentDiff scales semantic dataset comparison to millions of images using latent spaces of vision encoders combined with sparse autoencoders and density ratio estimation, showing better accuracy and robustness than caption-based approaches on a new benchmark for sparse distribution shifts.