mlsanityData to 7 Oct 2026

OneFlowSBI: One Model, Many Queries for Simulation-Based Inference

arXiv 2601.22951 ↗First posted 30 Jan 2026stat.ML cs.LGcited by 0

On the map: Diffusion models → Flow matching, time series and science

Abstract (arXiv)

We introduce textitOneFlowSBI, 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 textitOneFlowSBI on ten benchmark inference problems and two high-dimensional real-world inverse problems across multiple simulation budgets. textitOneFlowSBI 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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 20 of its 31 references that are in the map. First posted on arXiv 30 Jan 2026.

Builds on

20 of 31 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024Improving the Training of Rectified Flows30 May
  2. 2023Flow Matching for Scalable Simulation-Based Inference26 May
  3. 2022Flow Matching for Generative Modeling6 Oct
  4. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow7 Sep

Other references · 16

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  3. 2022Scalable Diffusion Models with Transformerscited by 5,931
  4. 2019Optuna: A Next-generation Hyperparameter Optimization Frameworkcited by 2,455
  5. 2022MaskGIT: Masked Generative Image Transformercited by 1,082
  6. 2019The frontier of simulation-based inferencecited by 490
  7. 2018Sequential Neural Likelihood: Fast Likelihood-free Inference with Autoregressive Flowscited by 217
  8. 2019Automatic Posterior Transformation for Likelihood-Free Inferencecited by 216
  9. 2017Flexible statistical inference for mechanistic models of neural dynamicscited by 162
  10. 2021Benchmarking Simulation-Based Inferencecited by 160
  11. 2024All-in-one simulation-based inferencecited by 71
  12. 2021Simulation Intelligence: Towards a New Generation of Scientific Methodscited by 68
4 more
  1. 2022Compositional Score Modeling for Simulation-based Inferencecited by 46
  2. 2023JANA: Jointly Amortized Neural Approximation of Complex Bayesian Modelscited by 41
  3. 2021Sequential Neural Posterior and Likelihood Approximationcited by 30
  4. 2018Sequential Neural Methods for Likelihood-free Inferencecited by 11

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026GenSBI: Generative Methods for Simulation-Based Inference in JAX
  2. 2026Pawsterior: Variational Flow Matching for Structured Simulation-Based Inference
  3. 2024Flow Matching for Posterior Inference with Simulator Feedback
  4. 2026Tokenised Flow Matching for Hierarchical Simulation Based Inference
  5. 2023Consistency Models for Scalable and Fast Simulation-Based Inference
  6. 2025Diffusion Models in Simulation-Based Inference: A Tutorial Review
  7. 2025Flow Matching Calibration for Simulation-Based Inference under Model Misspecification
  8. 2025Inference-Time Scaling for Flow Models via Stochastic Generation and Rollover Budget Forcing