pith. sign in

Glow: Generative flow with invertible 1x1 convolutions

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.CV 1 cs.LG 1

years

2022 1 2021 1

roles

background 1

polarities

unclear 1

representative citing papers

Building Normalizing Flows with Stochastic Interpolants

cs.LG · 2022-09-30 · conditional · novelty 8.0

Normalizing flows are constructed by learning the velocity of a stochastic interpolant via a quadratic loss derived from its probability current, yielding an efficient ODE-based alternative to diffusion models.

Vector-quantized Image Modeling with Improved VQGAN

cs.CV · 2021-10-09 · accept · novelty 6.0

Improved ViT-VQGAN enables autoregressive Transformer pretraining on ImageNet tokens to reach IS 175.1 and FID 4.17 for generation plus 73.2% linear-probe accuracy, beating prior iGPT models.

citing papers explorer

Showing 2 of 2 citing papers.

  • Building Normalizing Flows with Stochastic Interpolants cs.LG · 2022-09-30 · conditional · none · ref 27

    Normalizing flows are constructed by learning the velocity of a stochastic interpolant via a quadratic loss derived from its probability current, yielding an efficient ODE-based alternative to diffusion models.

  • Vector-quantized Image Modeling with Improved VQGAN cs.CV · 2021-10-09 · accept · none · ref 43

    Improved ViT-VQGAN enables autoregressive Transformer pretraining on ImageNet tokens to reach IS 175.1 and FID 4.17 for generation plus 73.2% linear-probe accuracy, beating prior iGPT models.