Anbu Huang

Anbu Huang

Research Scientist, Author, AI Enthusiast, THU

Blog posts

2025

• Diffusion Architectures Part I: Stability-Oriented Designs

86 minute read

Published:

This article explores how network architectures shape the stability of diffusion model training. We contrast U-Net and Transformer-based (DiT) backbones, analyzing how skip connections, residual scaling, and normalization influence gradient propagation across noise levels. By surveying stability-oriented innovations such as AdaGN, AdaLN-Zero, and skip pathway regulation, we reveal why architectural choices can determine whether training converges smoothly or collapses. The discussion provides both theoretical insights and practical design rules for building robust diffusion models.

2024

• Analysis of the Stability and Efficiency of Diffusion Model Training

83 minute read

Published:

while diffusion models have revolutionized generative AI, their training challenges stem from a combination of resource intensity, optimization intricacies, and deployment hurdles. A stable training process ensures that the model produces good quality samples and converges efficiently over time without suffering from numerical instabilities.

• Unifying Discrete and Continuous Perspectives in Diffusion Models

20 minute read

Published:

Diffusion models have been shown to be a highly promising approach in the field of image generation. They treat image generation as two independent processes: the forward process, which transforms a complex data distribution into a known prior distribution (typically a standard normal distribution) by gradually injecting noise; and the reverse process, which transforms the prior distribution back into the complex data distribution by gradually removing the noise.