Pith. sign in

Getting vit in shape: Scaling laws for compute-optimal model design

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

1 Pith paper citing it

fields

cs.CV 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

citing papers explorer

Showing 1 of 1 citing paper.

  • Quick ViTs: Speeding up Vision Transformers through Equivariance cs.CV · 2025-05-21 · conditional · none · ref 6

    D8-equivariant linear layers give ViTs a 5.33x FLOP reduction and 8x parameter reduction per layer, and hybrid octic ViTs match or slightly exceed ImageNet-1K accuracy while using about 40% fewer FLOPs.