pith. sign in

Efficient generative model training via embedded representation warmup.arXiv preprint arXiv:2504.10188

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

2026 2

roles

background 1

polarities

background 1

representative citing papers

Self-Adversarial One Step Generation via Condition Shifting

cs.CV · 2026-04-14 · unverdicted · novelty 6.0

APEX derives self-adversarial gradients from condition-shifted velocity fields in flow models to achieve high-fidelity one-step generation, outperforming much larger models and multi-step teachers.

citing papers explorer

Showing 2 of 2 citing papers.

  • Self-Adversarial One Step Generation via Condition Shifting cs.CV · 2026-04-14 · unverdicted · none · ref 13

    APEX derives self-adversarial gradients from condition-shifted velocity fields in flow models to achieve high-fidelity one-step generation, outperforming much larger models and multi-step teachers.

  • Data Warmup: Complexity-Aware Curricula for Efficient Diffusion Training cs.LG · 2026-04-08 · conditional · none · ref 17

    Data Warmup accelerates diffusion training on ImageNet by scheduling images from low to high complexity via a foreground-based metric and temperature-controlled sampler, improving FID and IS scores faster than uniform sampling.