19 citations · 33 across the 13 of their papers we have counts for
7 papers · 1 filter
Diffusion Transformer Captures Spatial-Temporal Dependencies: A Theory for Gaussian Process Data
Hengyu Fu, Zehao Dou, Jiawei Guo +2
Diffusion Transformer, the backbone of Sora for video generation, successfully scales the capacity of diffusion models, pioneering new avenues for high-fidelity sequential data gen…
Provable Statistical Rates for Consistency Diffusion Models
Zehao Dou, Minshuo Chen, Mengdi Wang +1
Diffusion models have revolutionized various application domains, including computer vision and audio generation. Despite the state-of-the-art performance, diffusion models are kno…
Self-Play with Adversarial Critic: Provable and Scalable Offline Alignment for Language Models
Xiang Ji, Sanjeev Kulkarni, Mengdi Wang +1
This work studies the challenge of aligning large language models (LLMs) with offline preference data. We focus on alignment by Reinforcement Learning from Human Feedback (RLHF) in…
An Overview of Diffusion Models: Applications, Guided Generation, Statistical Rates and Optimization
Minshuo Chen, Song Mei, Jianqing Fan +1
Diffusion models, a powerful and universal generative AI technology, have achieved tremendous success in computer vision, audio, reinforcement learning, and computational biology.…
Gradient Guidance for Diffusion Models: An Optimization Perspective
Yingqing Guo, Hui Yuan, Yukang Yang +2
Diffusion models have demonstrated empirical successes in various applications and can be adapted to task-specific needs via guidance. This paper studies a form of gradient guidanc…
Unveil Conditional Diffusion Models with Classifier-free Guidance: A Sharp Statistical Theory
Hengyu Fu, Zhuoran Yang, Mengdi Wang +1
Conditional diffusion models serve as the foundation of modern image synthesis and find extensive application in fields like computational biology and reinforcement learning. In th…
Theoretical Insights for Diffusion Guidance: A Case Study for Gaussian Mixture Models
Yuchen Wu, Minshuo Chen, Zihao Li +2
Diffusion models benefit from instillation of task-specific information into the score function to steer the sample generation towards desired properties. Such information is coine…