OneFlowSBI: One Model, Many Queries for Simulation-Based Inference
Abstract
We introduce \textit{OneFlowSBI}, a unified framework for simulation-based inference that learns a single flow-matching generative model over the joint distribution of parameters and observations. Leveraging a query-aware masking distribution during training, the same model supports multiple inference tasks, including posterior sampling, likelihood estimation, and arbitrary conditional distributions, without task-specific retraining. We evaluate \textit{OneFlowSBI} on ten benchmark inference problems and two high-dimensional real-world inverse problems across multiple simulation budgets. \textit{OneFlowSBI} is shown to deliver competitive performance against state-of-the-art generalized inference solvers and specialized posterior estimators, while enabling efficient sampling with few ODE integration steps and remaining robust under noisy and partially observed data.
Cite
@article{arxiv.2601.22951,
title = {OneFlowSBI: One Model, Many Queries for Simulation-Based Inference},
author = {Mayank Nautiyal and Li Ju and Melker Ernfors and Klara Hagland and Ville Holma and Maximilian Werkö Söderholm and Andreas Hellander and Prashant Singh},
journal= {arXiv preprint arXiv:2601.22951},
year = {2026}
}