4 papers
Particle Dynamics of Flow Matching and Classifier-Free Guidance from a Stagewise Geometry Perspective
Jian-Feng Cai, Zhengyi Su, Chao Wang
Flow matching, together with classifier-free guidance (CFG), is widely used in generative modeling, yet much of the theoretical understanding remains distribution-wise. Since pract…
Improving Classifier-Free Guidance of Flow Matching via Manifold Projection
Jian-Feng Cai, Haixia Liu, Zhengyi Su +1
Classifier-free guidance (CFG) is a widely used technique for controllable generation in diffusion and flow-based models. Despite its empirical success, CFG relies on a heuristic l…
Online Quantum State Tomography via Stochastic Gradient Descent
Jian-Feng Cai, Yuling Jiao, Yinan Li +3
We initiate the study of online quantum state tomography (QST), where the matrix representation of an unknown quantum state is reconstructed by sequentially performing a batch of m…
Unrolling Plug-and-Play Gradient Graph Laplacian Regularizer for Image Restoration
Jianghe Cai, Gene Cheung, Fei Chen
Generic deep learning (DL) networks for image restoration like denoising and interpolation lack mathematical interpretability, require voluminous training data to tune a large para…