mlsanityData to 7 Oct 2026

Flow Matching Neural Processes

arXiv 2512.23853 ↗First posted 29 Dec 2025cs.LGcited by 6

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

Abstract (arXiv)

Neural processes (NPs) are a class of models that learn stochastic processes directly from data and can be used for inference, sampling and conditional sampling. We introduce a new NP model based on flow matching, a generative modeling paradigm that has demonstrated strong performance on various data modalities. Following the NP training framework, the model provides amortized predictions of conditional distributions over any arbitrary points in the data. Compared to previous NP models, our model is simple to implement and can be used to sample from conditional distributions using an ODE solver, without requiring auxiliary conditioning methods. In addition, the model provides a controllable tradeoff between accuracy and running time via the number of steps in the ODE solver. We show that our model outperforms previous state-of-the-art neural process methods on various benchmarks including synthetic 1D Gaussian processes data, 2D images, and real-world weather data.

Key facts. Cited by 6 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 31 of its 38 references that are in the map. First posted on arXiv 29 Dec 2025.

Builds on

31 of 38 references.

Closest ancestors · 3

Same direction, newest first

  1. 2023Functional Flow Matching26 May
  2. 2022Flow Matching for Generative Modeling6 Oct
  3. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow7 Sep

Other references · 28

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  4. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  5. 2022Scalable Diffusion Models with Transformerscited by 5,931
  6. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  7. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,419
  8. 2022Building Normalizing Flows with Stochastic Interpolantscited by 964
  9. 2023Stochastic Interpolants: A Unifying Framework for Flows and Diffusionscited by 897
  10. 2015Importance Weighted Autoencoderscited by 454
  11. 2018Conditional Neural Processescited by 421
  12. 2024One Step Diffusion via Shortcut Modelscited by 373
16 more
  1. 2018Neural Processescited by 307
  2. 2019Attentive Neural Processescited by 280
  3. 2019Convolutional Conditional Neural Processescited by 139
  4. 2022Transformer Neural Processes: Uncertainty-Aware Meta Learning Via Sequence Modelingcited by 126
  5. 2022Neural Diffusion Processescited by 50
  6. 2022Diffusion Generative Models in Infinite Dimensionscited by 49
  7. 2020Bootstrapping Neural Processescited by 40
  8. 2023Infinite-Dimensional Diffusion Modelscited by 38
  9. 2021The Gaussian Neural Processcited by 34
  10. 2023Autoregressive Conditional Neural Processescited by 32
  11. 2020Equivariant Learning of Stochastic Fields: Gaussian Processes and Steerable Conditional Neural Processescited by 29
  12. 2023∞-Diff: Infinite Resolution Diffusion with Subsampled Mollified Statescited by 21
  13. 2024Translation Equivariant Transformer Neural Processescited by 12
  14. 2024Approximately Equivariant Neural Processescited by 8
  15. 2023Deep Stochastic Processes via Functional Markov Transition Operatorscited by 7
  16. 2025Generative Modeling with Bayesian Sample Inferencecited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 6.

6 papers.

  1. 2026On the Conditioning Consistency Gap in Conditional Neural Processescited by 3
  2. 2026LLM Flow Processes for Text-Conditioned Regressioncited by 1
  3. 2026Neural Stochastic Processes for Satellite Precipitation Refinementcited by 1
  4. 2026Support-Conditioned Flow Matching Is Kernel Smoothingcited by 0
  5. 2026Revisiting Neural Processes via Fourier Transform and Volterra Seriescited by 0
  6. 2026Flow Annealing Posterior Sampling for Function-Space Regression and Inverse Problemscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Random Process Flow Matching: Generative Implicit Representations of Multivariate Random Fields
  2. 2025Flow Matching: Markov Kernels, Stochastic Processes and Transport Plans
  3. 2024Flow Matching with Gaussian Process Priors for Probabilistic Time Series Forecasting
  4. 2026Latent Process Generator Matching
  5. 2024Stream-level flow matching with Gaussian processes
  6. 2025Generative Modeling with Continuous Flows: Sample Complexity of Flow Matching
  7. 2026ODE-free Neural Flow Matching for One-Step Generative Modeling
  8. 2024Local Flow Matching Generative Models