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

CONDITIONAL 1

representative citing papers

Do we need equivariant models for molecule generation?

cs.LG · 2025-07-13 · conditional · novelty 6.0

Rotation-augmented CNNs learn equivariance easily for denoising and prediction, but only large models keep generation outputs invariant to seed rotations, and their latent codes do not identify rotated molecules as the same object.

citing papers explorer

Showing 1 of 1 citing paper.

  • Do we need equivariant models for molecule generation? cs.LG · 2025-07-13 · conditional · none · ref 2016

    Rotation-augmented CNNs learn equivariance easily for denoising and prediction, but only large models keep generation outputs invariant to seed rotations, and their latent codes do not identify rotated molecules as the same object.