AI RESEARCH
Sampling via Stochastic Interpolants by Langevin-based Velocity and Initialization Estimation in Flow ODEs
arXiv CS.LG
•
ArXi:2601.08527v2 Announce Type: replace-cross We propose a novel method for sampling from unnormalized Boltzmann densities based on a probability flow ordinary differential equation (ODE) derived from linear stochastic interpolants. The key innovation of our approach is the use of a sequence of Langevin samplers to enable efficient simulation of the flow.