mlsanityData to 7 Oct 2026

The Amazing Stability of Flow Matching

arXiv 2604.16079 ↗First posted 17 Apr 2026cs.CVcited by 2

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

Abstract (arXiv)

The success of deep generative models in generating high-quality and diverse samples is often attributed to particular architectures and large training datasets. In this paper, we investigate the impact of these factors on the quality and diversity of samples generated by flow-matching models. Surprisingly, in our experiments on CelebA-HQ dataset, flow matching remains stable even when pruning 50% of the dataset. That is, the quality and diversity of generated samples are preserved. Moreover, pruning impacts the latent representation only slightly, that is, samples generated by models trained on the full and pruned dataset map to visually similar outputs for a given seed. We observe similar stability when changing the architecture or training configuration, such that the latent representation is maintained under these changes as well. Our results quantify just how strong this stability can be in practice, and help explain the reliability of flow-matching models under various perturbations.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 28 of its 32 references that are in the map. First posted on arXiv 17 Apr 2026.

Builds on

28 of 32 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025On the Closed-Form of Flow Matching: Generalization Does Not Arise from Target Stochasticity4 Jun
  2. 2024How Do Flow Matching Models Memorize and Generalize in Sample Data Subspaces?31 Oct
  3. 2023Improving and generalizing flow-based generative models with minibatch optimal transport1 Feb
  4. 2022Flow Matching for Generative Modeling6 Oct
  5. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow7 Sep

Other references · 23

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  5. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  6. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  7. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  8. 2022Scalable Diffusion Models with Transformerscited by 5,931
  9. 2017Neural Discrete Representation Learningcited by 4,650
  10. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
  11. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  12. 2014Deep Learning Face Attributes in the Wildcited by 3,679
11 more
  1. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  2. 2022Imagen Video: High Definition Video Generation with Diffusion Modelscited by 1,765
  3. 2023Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Modelscited by 1,465
  4. 2024PaliGemma: A versatile 3B VLM for transfercited by 679
  5. 2021Diffusion Schr"odinger Bridge with Applications to Score-Based Generative Modelingcited by 594
  6. 2021Deep Learning on a Data Diet: Finding Important Examples Early in Trainingcited by 529
  7. 2024Lumiere: A Space-Time Diffusion Model for Video Generationcited by 450
  8. 2023Generalization in diffusion models arises from geometry-adaptive harmonic representationscited by 179
  9. 2024Influence Functions for Scalable Data Attribution in Diffusion Modelscited by 31
  10. 2021Stability of Entropic Optimal Transport and Schr"odinger Bridgescited by 25
  11. 2024Data Pruning in Generative Diffusion Modelscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Exploring and Exploiting Stability in Latent Flow Matchingcited by 1
  2. 2026The Signal in the Noise: OOD Detection Through Goodness-of-Fit Testing in Factorised Latent Spacescited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2023Flow Matching in Latent Space
  2. 2025Carr'e du champ flow matching: better quality-generalisation tradeoff in generative models
  3. 2025A Theoretical Analysis of Discrete Flow Matching Generative Models
  4. 2026Training Flow Matching: The Role of Weighting and Parameterization
  5. 2023Multisample Flow Matching: Straightening Flows with Minibatch Couplings
  6. 2025Value Gradient Guidance for Flow Matching Alignment
  7. 2024Self-Corrected Flow Distillation for Consistent One-Step and Few-Step Text-to-Image Generation
  8. 2024Convergence Analysis of Flow Matching in Latent Space with Transformers