7 papers
Evaluating the Representation Space of Diffusion Models via Self-Supervised Principles
Xiao Li, Yixuan Jia, Zekai Zhang +6
Diffusion models have demonstrated remarkable generative capabilities and have also emerged as powerful self-supervised representation learners, yet the connection between these tw…
Generalization of Diffusion Models Arises with a Balanced Representation Space
Zekai Zhang, Xiao Li, Xiang Li +4
Diffusion models excel at generating high-quality, diverse samples, yet they risk memorizing training data when overfit to the training objective. We analyze the distinctions betwe…
MCLR: Improving Conditional Modeling via Inter-Class Likelihood-Ratio Maximization and Unifying Classifier-Free Guidance with Alignment Objectives
Xiang Li, Yixuan Jia, Xiao Li +3
Diffusion models achieve strong performance in generative modeling, but their success often relies heavily on classifier-free guidance (CFG), an inference-time heuristic that modif…
Understanding Representation Dynamics of Diffusion Models via Low-Dimensional Modeling
Xiao Li, Zekai Zhang, Xiang Li +4
Diffusion models, though originally designed for generative tasks, have demonstrated impressive self-supervised representation learning capabilities. A particularly intriguing phen…
Towards Understanding the Mechanisms of Classifier-Free Guidance
Xiang Li, Rongrong Wang, Qing Qu
Classifier-free guidance (CFG) is a core technique powering state-of-the-art image generation systems, yet its underlying mechanisms remain poorly understood. In this work, we begi…
Decoupled Data Consistency with Diffusion Purification for Image Restoration
Xiang Li, Soo Min Kwon, Shijun Liang +3
Diffusion models have recently gained traction as a powerful class of deep generative priors, excelling in a wide range of image restoration tasks due to their exceptional ability…