Itô maps for any-step SDEs
Researchers have introduced the Itô map, a novel method for any-step stochastic differential equation (SDE) integration. This approach allows generative models to predict future states in a single pass by utilizing intermediate states and Brownian paths. The Itô map offers differentiable access to posterior samples, enabling improved inference-time control and demonstrating strong performance in synthetic and image-generation benchmarks. AI
IMPACT Introduces a new primitive for posterior sampling and stochastic control in generative models, potentially improving sampling efficiency and steering capabilities.