Mean Velocity Matching: Rethinking Generative Dynamics in Diffusion Models
This work studies prediction parameterization for stochastic generative dynamics in diffusion models. Existing velocity-based generative models provide the simplicity of learning a single transport field, but their standard formulation is deterministic, whereas stochastic extensions generally require additional score i...
Yun-Hong Zhang, Chang-Jie Cao, Zhi-Hua Zhang et al.
· 0 citations