cs.LGMay 27, 2026

Parameter-Efficient Generative Modeling with Controlled Vector Fields

Authors: Peyman Morteza

Abstract

We introduce a continuous-time generative modeling framework, motivated by the Chow-Rashevskii theorem, that builds expressive flows from a small set of fixed vector fields and learned scalar controls. Instead of learning an unconstrained high-dimensional vector field, our framework constructs the velocity by modulating fixed vector fields with learned scalar control functions. When the fixed fields are bracket-generating, their Lie algebra spans the ambient space, providing a mechanism for expressive transport with only a small number of learned control channels and offering a parameter-efficient geometric alternative to standard vector-field parameterizations. This decoupled formulation yields a structured and interpretable generative model in which the number of learned scalar output channels can be chosen independently of the ambient dimension. We formulate an expressivity principle showing that, under suitable controllability and well-posedness assumptions, such controlled flows can transport a source distribution to a target distribution. We train the resulting model using a continuous-normalizing-flow likelihood objective and present proof-of-concept experiments on synthetic distributions.

Explore similar work

CardsList
  1. Expanding Flow Maps

    Jul 23, 2026Sophia Tang, Pranam ChatterjeeGenerative Flow NetworksFlow Map

  2. Conservative Flows: A New Paradigm of Generative Models

    May 7, 2026Eshed Gal, Md Shahriar Rahim Siddiqui, Moshe Eliasof +1Generative Flow NetworksGenerative Models

  3. Generative Modeling by Value-Driven Transport

    May 21, 2026Pablo Moreno-Muñoz, Adrian Müller, Gergely NeuGenerative ModelsStochastic Optimal Control