Generative Vision Atlas

Objective option

Stochastic interpolant framework

A generalized formulation that treats diffusion and flow matching as two points in a continuous family of interpolants between noise and data, exposing objective/coupling/sampler as independent design choices.

Introduced by

Used by (1)

SiT

Alternatives on this axis

Diffusion-loss autoregression, Diffusion (epsilon/v/x0-prediction), Drifting field, Flow matching / rectified flow, Average (mean) velocity, Next-scale autoregression, Normalizing flow, Transition matching

← All Objective options