This survey provides a taxonomy of preference alignment methods for diffusion models in image generation and editing, covering optimization techniques, applications, and open challenges.
On differentially private 3d medical image synthesis with controllable latent diffusion models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Preference Alignment on Diffusion Model: A Comprehensive Survey for Image Generation and Editing
This survey provides a taxonomy of preference alignment methods for diffusion models in image generation and editing, covering optimization techniques, applications, and open challenges.