On statistical rates of conditional diffusion transformers: Approximation, estimation and minimax optimality
We investigate the approximation and estimation rates of conditional diffusion transformers
(DiTs) with classifier-free guidance. We present a comprehensive analysis for``in …
(DiTs) with classifier-free guidance. We present a comprehensive analysis for``in …
Gradient-Free Classifier Guidance for Diffusion Model Sampling
Image generation using diffusion models have demonstrated outstanding learning
capabilities, effectively capturing the full distribution of the training dataset. They are known …
capabilities, effectively capturing the full distribution of the training dataset. They are known …
Training-Free Constrained Generation With Stable Diffusion Models
Stable diffusion models represent the state-of-the-art in data synthesis across diverse
domains and hold transformative potential for applications in science and engineering, eg …
domains and hold transformative potential for applications in science and engineering, eg …
Decoupling Training-Free Guided Diffusion by ADMM
In this paper, we consider the conditional generation problem by guiding off-the-shelf
unconditional diffusion models with differentiable loss functions in a plug-and-play fashion …
unconditional diffusion models with differentiable loss functions in a plug-and-play fashion …
On the Guidance of Flow Matching
Flow matching has shown state-of-the-art performance in various generative tasks, ranging
from image generation to decision-making, where guided generation is pivotal. However …
from image generation to decision-making, where guided generation is pivotal. However …