A training-free adaptive subspace projection method mitigates semantic collapsing in generative personalization by isolating and adjusting drift in a low-dimensional subspace using the stable pre-trained embedding as anchor.
Svdiff: Compact parameter space for diffusion fine-tuning
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.CV 2verdicts
UNVERDICTED 2roles
method 1polarities
use method 1representative citing papers
Proposes Lipschitz regularization during fine-tuning to prevent distributional drift in personalized diffusion models, improving subject fidelity and prompt adherence.
citing papers explorer
-
Adaptive Subspace Projection for Generative Personalization
A training-free adaptive subspace projection method mitigates semantic collapsing in generative personalization by isolating and adjusting drift in a low-dimensional subspace using the stable pre-trained embedding as anchor.