activity
20242026
collaborators
Showing cs.LGShow all

5 papers · 1 filter

cs.LG2026

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…

cs.LG2026

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…

cs.LG2025

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…

cs.LG2025

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…

cs.LG2024

Understanding Generalizability of Diffusion Models Requires Rethinking the Hidden Gaussian Structure

Xiang Li, Yixiang Dai, Qing Qu

In this work, we study the generalizability of diffusion models by looking into the hidden properties of the learned score functions, which are essentially a series of deep denoise…