AI RESEARCH

Generative Modeling by Value-Driven Transport

arXiv CS.LG

ArXi:2605.22507v1 Announce Type: new We propose a new framework for generative modeling based on a discrete-time stochastic control formulation of measure transport. Adapting classic results from control theory, we formulate our problem as a linear program whose dual variables correspond to the \emph{optimal value function} of the control problem, which directly encodes the optimal control policy.