Pith. sign in

Title resolution pending

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

1 Pith paper citing it

fields

cs.LG 1

years

2025 1

verdicts

REJECT 1

representative citing papers

Self-similarity Analysis in Deep Neural Networks

cs.LG · 2025-07-23 · reject · novelty 5.0

A new regularizer that constrains a distance-based self-similarity score of hidden features improves accuracy on MLP and transformer models by up to 6 points, but the metric itself is not validated.

citing papers explorer

Showing 1 of 1 citing paper.

  • Self-similarity Analysis in Deep Neural Networks cs.LG · 2025-07-23 · reject · none · ref 3

    A new regularizer that constrains a distance-based self-similarity score of hidden features improves accuracy on MLP and transformer models by up to 6 points, but the metric itself is not validated.