3 papers
cs.LG2026
A Kinetic Energy Perspective of Flow Matching
Ziyun Li, Huancheng Hu, Soon Hoe Lim +6
Flow-based generative models can be viewed through a physics lens: sampling transports a particle from noise to data by integrating a learned velocity field, and each sample corres…
cs.LG2025
EnfoPath: Energy-Informed Analysis of Generative Trajectories in Flow Matching
Ziyun Li, Ben Dai, Huancheng Hu +2
Flow-based generative models synthesize data by integrating a learned velocity field from a reference distribution to the target data distribution. Prior work has focused on endpoi…
cs.LG2025
FlowTS: Time Series Generation via Rectified Flow
Yang Hu, Xiao Wang, Zezhen Ding +7
Diffusion-based models have significant achievements in time series generation but suffer from inefficient computation: solving high-dimensional ODEs/SDEs via iterative numerical s…