6 papers
Diffusion Model's Generalization Can Be Characterized by Inductive Biases toward a Data-Dependent Ridge Manifold
Ye He, Yitong Qiu, Molei Tao
We study a data-dependent notion of diffusion-model generalization: when a model does not memorize the training set, where do its generated samples go relative to the geometry indu…
HAM: A Training-Free Style Transfer Approach via Heterogeneous Attention Modulation for Diffusion Models
Yeqi He, Liang Li, Zhiwen Yang +3
Diffusion models have demonstrated remarkable performance in image generation, particularly within the domain of style transfer. Prevailing style transfer approaches typically leve…
Few-Shot Generative Model Adaption via Identity Injection and Preservation
Yeqi He, Liang Li, Jiehua Zhang +4
Training generative models with limited data presents severe challenges of mode collapse. A common approach is to adapt a large pretrained generative model upon a target domain wit…
Improving Classifier-Free Guidance in Masked Diffusion: Low-Dim Theoretical Insights with High-Dim Impact
Kevin Rojas, Ye He, Chieh-Hsin Lai +3
Classifier-Free Guidance (CFG) is a widely used technique for conditional generation and improving sample quality in continuous diffusion models, and its extensions to discrete dif…
Wavelet Predictive Representations for Non-Stationary Reinforcement Learning
Min Wang, Xin Li, Ye He +4
The real world is inherently non-stationary, with ever-changing factors, such as weather conditions and traffic flows, making it challenging for agents to adapt to varying environm…
What Exactly Does Guidance Do in Masked Discrete Diffusion Models
He Ye, Rojas Kevin, Tao Molei
We study masked discrete diffusion models with classifier-free guidance (CFG). Assuming no score error nor discretization error, we derive an explicit solution to the guided revers…