STRIDE boosts diversity in one-step diffusion models by injecting PCA-aligned pink noise into transformer features while preserving text alignment and quality.
Sliderspace: Decomposing the visual capabilities of diffusion models
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3roles
background 1polarities
background 1representative citing papers
A new task and architecture for inferring an unlabeled visual concept from a small image set and re-instantiating it in a query image, with experiments showing gains over VLMs.
LatentGandr computes local principal components from neighborhood embeddings in generative model latent spaces and visualizes them as interactive grids to improve exploration over global slider methods.
citing papers explorer
-
STRIDE: Training-Free Diversity Guidance via PCA-Directed Feature Perturbation in Single-Step Diffusion Models
STRIDE boosts diversity in one-step diffusion models by injecting PCA-aligned pink noise into transformer features while preserving text alignment and quality.
-
Show Me Examples: Inferring Visual Concepts from Image Sets
A new task and architecture for inferring an unlabeled visual concept from a small image set and re-instantiating it in a query image, with experiments showing gains over VLMs.
-
LatentGandr: Visual Exploration of Generative AI Latent Space via Local Embeddings
LatentGandr computes local principal components from neighborhood embeddings in generative model latent spaces and visualizes them as interactive grids to improve exploration over global slider methods.