2 papers
cs.LG2026
Fine-Tuning Flow Matching via Maximum Likelihood Estimation of Reconstructions
Zhaoyi Li, Jingtao Ding, Yong Li +1
Flow Matching (FM) models achieve remarkable results in generative tasks. Building upon diffusion models, FM's simulation-free training paradigm enables simplicity and efficiency b…
cs.LG2024
ControlSynth Neural ODEs: Modeling Dynamical Systems with Guaranteed Convergence
Wenjie Mei, Dongzhe Zheng, Shihua Li
Neural ODEs (NODEs) are continuous-time neural networks (NNs) that can process data without the limitation of time intervals. They have advantages in learning and understanding the…