ICLR 2026poster0 citations

Branched Schrödinger Bridge Matching

Sophia Tang, Yinuo Zhang, Alexander Tong, Pranam Chatterjee

Abstract

Predicting the intermediate trajectories between an initial and target distribution is a central problem in generative modeling. Existing approaches, such as flow matching and Schrödinger Bridge Matching, effectively learn mappings between two distributions by modeling a single stochastic path. However, these methods are inherently limited to unimodal transitions and cannot capture *branched* or *divergent* evolution from a common origin to multiple distinct outcomes. To address this, we introduce **Branched Schrödinger Bridge Matching (BranchSBM)**, a novel framework that learns branched Schrödinger bridges. BranchSBM parameterizes multiple time-dependent velocity fields and growth processes, enabling the representation of population-level divergence into multiple terminal distributions. We show that BranchSBM is not only more expressive but also essential for tasks involving multi-path surface navigation, modeling cell fate bifurcations from homogeneous progenitor states, and simulating diverging cellular responses to perturbations.

Schrödinger bridgesbranched generative modelingstochastic optimal controlunbalanced optimal transportflow matchingtrajectory inferencestochastic processesprobabilistic transportmultimodal distributionsdynamical systems
BibTeX
@inproceedings{
tang2026branched,
title={Branched Schr\"odinger Bridge Matching},
author={Sophia Tang and Yinuo Zhang and Alexander Tong and Pranam Chatterjee},
booktitle={The Fourteenth International Conference on Learning Representations},
year={2026},
url={https://openreview.net/forum?id=ctq8BfUXWz}
}
Branched Schrödinger Bridge Matching · ICLR 2026