Reproduce “Generative Modeling via Nonlinear Schrödinger Bridges and Branching Diffusions” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Mathias Grau, Pierre Henry-Labordère

SBNL extends Schrödinger bridges to transport distributions while allowing the evolving population to shape its route. It adds running and terminal costs to endpoint matching, representing their effects through coupled potentials estimated with branching-diffusion Monte Carlo. The method recovers ordinary bridges without interactions and illustrates nonlinear density and environmental costs. Its benchmark tests only the linear, no-interaction setting.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.