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.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.HC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
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.