mlsanityData to 14 Oct 2026

Probabilistic Inversion with Flow Matching

arXiv 2606.31288 ↗First posted 30 Jun 2026cs.LG math.PR physics.geo-phcited by 0

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

Abstract (arXiv)

We demonstrate the application of Flow Matching, a technique originating from generative Artificial Intelligence, to probabilistic inversion in geophysical settings, such as seismic Full-Waveform inversion. We adapt the well-established mathematical theory of Flow Matching from generative Artificial Intelligence to the context of probabilistic inversion. We evaluate the approach with two case studies: a simple 2D velocity model to illustrate the general features of the method, and the OpenFWI dataset to show its capabilities for probabilistic inversion of more complex seismic velocity models.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 9 of its 19 references that are in the map. First posted on arXiv 30 Jun 2026.

Builds on

9 of 19 references.

Closest ancestors · 5

Same direction, newest first

  1. 2024Flow Matching Guide and Code9 Dec
  2. 2023Guided Flows for Generative Modeling and Decision Making22 Nov
  3. 2023Flow Matching on General Geometries7 Feb
  4. 2022Efficient Video Prediction via Sparsely Conditioned Flow Matching26 Nov
  5. 2022Flow Matching for Generative Modeling6 Oct

Other references · 4

  1. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  2. 2023Voicebox: Text-Guided Multilingual Universal Speech Generation at Scalecited by 379
  3. 2022Fast Point Cloud Generation with Straight Flowscited by 56
  4. 2023Wuerstchen: An Efficient Architecture for Large-Scale Text-to-Image Diffusion Modelscited by 51

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Controllable seismic velocity synthesis using generative diffusion models
  2. 2024DAWN-FM: Data-Aware and Noise-Informed Flow Matching for Solving Inverse Problems
  3. 2024Generative Geostatistical Modeling from Incomplete Well and Imaged Seismic Observations with Diffusion Models
  4. 2024Propagating the prior from shallow to deep with a pre-trained velocity-model Generative Transformer network
  5. 2026Probabilistic Geodesic Flow Matching on Location-Scale Families
  6. 2026Free Lunch for Stabilizing Rectified Flow Inversion
  7. 2026P-Flow: Proxy-gradient Flows for Linear Inverse Problems
  8. 2026Conditional Rectified Flow-based End-to-End Rapid Seismic Inversion Method