Diffusion models have made rapid progress in generating high-quality samples across
various domains. However, a theoretical understanding of the Lipschitz continuity and …

The softmax activation function plays a crucial role in the success of large language models
(LLMs), particularly in the self-attention mechanism of the widely adopted Transformer …

Bayesian flow networks (BFNs) iteratively refine the parameters, instead of the samples in
diffusion models (DMs), of distributions at various noise levels through Bayesian inference …

Deep neural networks (DNNs) are vulnerable to backdoor attacks, where adversaries can
maliciously trigger model misclassifications by implanting a hidden backdoor during model …

Diffusion models (DMs) are a type of potential generative models, which have achieved
better effects in many fields than traditional methods. DMs consist of two main processes …

We propose using a Gaussian Mixture Model (GMM) as reverse transition operator (kernel)
within the Denoising Diffusion Implicit Models (DDIM) framework, which is one of the most …

Denoising diffusion probabilistic models (DDPM) have shown impressive performance in
various domains as a class of deep generative models. In this article, we introduce the …

We investigate the approximation and estimation rates of conditional diffusion transformers
(DiTs) with classifier-free guidance. We present a comprehensive analysis for``in …

We calculate the average differential entropy of aq-component Gaussian mixture in R n. For
simplicity, all components have covariance matrix σ 2 1, while the means {W i} i= 1 q are iid …

Diffusion models have achieved great success in generative tasks\textblue {, with the quality
of generated samples guaranteed by their convergence properties, typically derived within …