Extended Flow Matching: a Method of Conditional Generation with Generalized Continuity Equation

arXiv:2402.18839v1 Announce Type: new
Abstract: The task of conditional generation is one of the most important applications of generative models, and numerous methods have been developed to date based on the celebrated diffusion models, with the guidance-based classifier-free method taking the lead. However, the theory of the guidance-based method not only requires the user to fine-tune the "guidance strength," but its target vector field does not necessarily correspond to the conditional distribution used in training. In this paper, we develop …

abstract applications arxiv classifier continuity cs.lg diffusion diffusion models equation flow free generalized generative generative models guidance math.ap math.fa math.oc math.pr theory type