mlsanityData to 14 Oct 2026

Neural Diffusion Processes

arXiv 2206.03992 ↗First posted 8 Jun 2022stat.ML cs.LGcited by 50

Not on the map. Why?

Cited by 24 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Neural network approaches for meta-learning distributions over functions have desirable properties such as increased flexibility and a reduced complexity of inference. Building on the successes of denoising diffusion models for generative modelling, we propose Neural Diffusion Processes (NDPs), a novel approach that learns to sample from a rich distribution over functions through its finite marginals. By introducing a custom attention block we are able to incorporate properties of stochastic processes, such as exchangeability, directly into the NDP's architecture. We empirically show that NDPs can capture functional distributions close to the true Bayesian posterior, demonstrating that they can successfully emulate the behaviour of Gaussian processes and surpass the performance of neural processes. NDPs enable a variety of downstream tasks, including regression, implicit hyperparameter marginalisation, non-Gaussian posterior prediction and global optimisation.

Key facts. Cited by 50 papers in the map (data through 14 Oct 2026). Builds on 24 of its 40 references that are in the map. First posted on arXiv 8 Jun 2022.

Builds on

24 of 40 references.

References · 24

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  4. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  5. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,430
  6. 2017Deep Setscited by 1,421
  7. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,354
  8. 2020Improved Techniques for Training Score-Based Generative Modelscited by 1,043
  9. 2021Diffusion Probabilistic Models for 3D Point Cloud Generationcited by 735
  10. 2022Equivariant Diffusion for Molecule Generation in 3Dcited by 677
  11. 2022GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generationcited by 516
  12. 2015Deep Kernel Learningcited by 445
12 more
  1. 2018Conditional Neural Processescited by 426
  2. 2018Neural Processescited by 311
  3. 2019Attentive Neural Processescited by 283
  4. 2019GP-VAE: Deep Probabilistic Time Series Imputationcited by 172
  5. 2019Convolutional Conditional Neural Processescited by 142
  6. 2021Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learningcited by 113
  7. 2020Meta-Learning Stationary Stochastic Process Prediction with Convolutional Neural Processescited by 76
  8. 2020A Framework for Interdomain and Multioutput Gaussian Processescited by 48
  9. 2021The Gaussian Neural Processcited by 34
  10. 2019Approximate Inference for Fully Bayesian Gaussian Process Regressioncited by 31
  11. 2021Kernel Identification Through Transformerscited by 13
  12. 2020Marginalised Gaussian Processes with Nested Samplingcited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 4; 2023: 16; 2024: 9; 2025: 13; 2026: 8.

50 papers.

Sort:

By area:

  1. 2022A Survey on Generative Diffusion Modelcited by 240
  2. 2023Score-based Diffusion Models in Function Spacecited by 82
  3. 2023Diffusion Models for Black-Box Optimizationcited by 76
  4. 2022Diffusion Generative Models in Infinite Dimensionscited by 49
  5. 2024DEFT: Efficient Fine-Tuning of Diffusion Models by Learning the Generalised h-transformcited by 46
  6. 2022Modeling Temporal Data as Continuous Functions with Stochastic Process Diffusioncited by 39
  7. 2023Continuous-Time Functional Diffusion Processescited by 39
  8. 2023Conditional score-based diffusion models for Bayesian inference in infinite dimensionscited by 38
  9. 2022Spectral Diffusion Processescited by 25
  10. 2024Amortized Probabilistic Conditioning for Optimization, Simulation and Inferencecited by 23
  11. 2023A framework for conditional diffusion modelling with applications in motif scaffolding for protein designcited by 22
  12. 2023∞-Diff: Infinite Resolution Diffusion with Subsampled Mollified Statescited by 21
38 more
  1. 2025FunDiff: Diffusion Models over Function Spaces for Physics-Informed Generative Modelingcited by 20
  2. 2024Stochastic Optimal Control for Diffusion Bridges in Function Spacescited by 16
  3. 2025Stochastic Process Learning via Operator Flow Matchingcited by 14
  4. 2023Functional Diffusioncited by 13
  5. 2023Manifold Diffusion Fieldscited by 11
  6. 2024Universal Functional Regression with Neural Operator Flowscited by 9
  7. 2025Source Separation by Flow Matchingcited by 8
  8. 2023Thompson Sampling with Diffusion Generative Priorcited by 7
  9. 2023Deep Stochastic Processes via Functional Markov Transition Operatorscited by 7
  10. 2023Generative Hyperelasticity with Physics-Informed Probabilistic Diffusion Fieldscited by 7
  11. 2023PriorCVAE: scalable MCMC parameter inference with Bayesian deep generative modellingcited by 6
  12. 2025Flow Straight and Fast in Hilbert Space: Functional Rectified Flowcited by 6
  13. 2025In-Context Multi-Objective Optimizationcited by 6
  14. 2025Flow Matching Neural Processescited by 6
  15. 2025The Alpha-Alternator: Dynamic Adaptation To Varying Noise Levels In Sequences Using The Vendi Score For Improved Robustness and Performancecited by 5
  16. 2025Dimension Agnostic Neural Processescited by 5
  17. 2023Learning multi-modal generative models with permutation-invariant encoders and tighter variational objectivescited by 4
  18. 2024Spectral Convolutional Conditional Neural Processescited by 4
  19. 2025Efficient Autoregressive Inference for Transformer Probabilistic Modelscited by 4
  20. 2024Alternators For Sequence Modelingcited by 3
  21. 2024System-Aware Neural ODE Processes for Few-Shot Bayesian Optimizationcited by 3
  22. 2026On the Conditioning Consistency Gap in Conditional Neural Processescited by 3
  23. 2023Diffusion-Augmented Neural Processescited by 2
  24. 2024Noise-Aware Differentially Private Regression via Meta-Learningcited by 2
  25. 2025Hyper-Transforming Latent Diffusion Modelscited by 2
  26. 2026LatentFlow: A General Framework for Conditioning Stochastic Processescited by 2
  27. 2023T1: Scaling Diffusion Probabilistic Fields to High-Resolution on Unified Visual Modalitiescited by 1
  28. 2024R'enyi Neural Processescited by 1
  29. 2025Place Cells as Multi-Scale Position Embeddings: Random Walk Transition Kernels for Path Planningcited by 1
  30. 2026LLM Flow Processes for Text-Conditioned Regressioncited by 1
  31. 2023Latent Dynamical Implicit Diffusion Processescited by 0
  32. 2025Neural Bridge Processescited by 0
  33. 2025Multi-task Neural Diffusion Processescited by 0
  34. 2026Generative Neural Operators through Diffusion Last Layercited by 0
  35. 2026Gaussian Mixture Copula Processes for Irregular Time Seriescited by 0
  36. 2026Revisiting Neural Processes via Fourier Transform and Volterra Seriescited by 0
  37. 2026Flow Annealing Posterior Sampling for Function-Space Regression and Inverse Problemscited by 0
  38. 2026Earth observation embeddings are effective sub-grid descriptors for probabilistic weather downscalingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Diffusion Models: A Mathematical Introduction
  2. 2024Neural Flow Diffusion Models: Learnable Forward Process for Improved Diffusion Modelling
  3. 2023Neural Diffusion Models
  4. 2026Forward-Learned Discrete Diffusion: Learning how to noise to denoise faster
  5. 2022From Points to Functions: Infinite-dimensional Representations in Diffusion Models
  6. 2024GUD: Generation with Unified Diffusion
  7. 2023To smooth a cloud or to pin it down: Guarantees and Insights on Score Matching in Denoising Diffusion Models
  8. 2023Diffusion Models for Generative Artificial Intelligence: An Introduction for Applied Mathematicians