mlsanityData to 7 Oct 2026

The Rise of Diffusion Models in Time-Series Forecasting

arXiv 2401.03006 ↗First posted 5 Jan 2024cs.LG cs.AIcited by 25

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

Abstract (arXiv)

This survey delves into the application of diffusion models in time-series forecasting. Diffusion models are demonstrating state-of-the-art results in various fields of generative AI. The paper includes comprehensive background information on diffusion models, detailing their conditioning methods and reviewing their use in time-series forecasting. The analysis covers 11 specific time-series implementations, the intuition and theory behind them, the effectiveness on different datasets, and a comparison among each other. Key contributions of this work are the thorough exploration of diffusion models' applications in time-series forecasting and a chronologically ordered overview of these models. Additionally, the paper offers an insightful discussion on the current state-of-the-art in this domain and outlines potential future research directions. This serves as a valuable resource for researchers in AI and time-series analysis, offering a clear view of the latest advancements and future potential of diffusion models.

Key facts. Cited by 25 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 60 of its 104 references that are in the map. First posted on arXiv 5 Jan 2024.

Builds on

60 of 104 references.

Closest ancestors · 4

Same direction, newest first

  1. 2023Non-autoregressive Conditional Diffusion Models for Time Series Prediction8 Jun
  2. 2023Diffusion Models for Time Series Applications: A Survey1 May
  3. 2021CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation7 Jul
  4. 2021Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecasting28 Jan

Other references · 56

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  5. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  6. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  7. 2022Classifier-Free Diffusion Guidancecited by 5,717
  8. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  9. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
  10. 2018Neural Ordinary Differential Equationscited by 3,733
  11. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  12. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,424
38 more
  1. 2022Video Diffusion Modelscited by 2,280
  2. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,141
  3. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 1,981
  4. 2022Imagen Video: High Definition Video Generation with Diffusion Modelscited by 1,765
  5. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  6. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,665
  7. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,654
  8. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,339
  9. 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,200
  10. 2021Cascaded Diffusion Models for High Fidelity Image Generationcited by 1,155
  11. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,107
  12. 2022Diffusion Models in Vision: A Surveycited by 1,008
  13. 2022Diffusion-LM Improves Controllable Text Generationcited by 1,006
  14. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 869
  15. 2020NVAE: A Deep Hierarchical Variational Autoencodercited by 635
  16. 2018Disentangling by Factorisingcited by 614
  17. 2020HiPPO: Recurrent Memory with Optimal Polynomial Projectionscited by 600
  18. 2016Recurrent Neural Networks for Multivariate Time Series with Missing Valuescited by 548
  19. 2022DiffuSeq: Sequence to Sequence Text Generation with Diffusion Modelscited by 439
  20. 2019Sliced Score Matching: A Scalable Approach to Density and Score Estimationcited by 381
  21. 2022Understanding Diffusion Models: A Unified Perspectivecited by 337
  22. 2022Flexible Diffusion Modeling of Long Videoscited by 294
  23. 2022Diffsound: Discrete Diffusion Model for Text-to-sound Generationcited by 256
  24. 2021Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Modelscited by 251
  25. 2022Diffusion Probabilistic Modeling for Video Generationcited by 237
  26. 2022Diffusion-based Time Series Imputation and Forecasting with Structured State Space Modelscited by 195
  27. 2022It's Raw! Audio Generation with State-Space Modelscited by 171
  28. 2019High-Dimensional Multivariate Forecasting with Low-Rank Gaussian Copula Processescited by 147
  29. 2022How to Train Your HiPPO: State Space Models with Generalized Orthogonal Basis Projectionscited by 121
  30. 2023Generative Time Series Forecasting with Diffusion, Denoise, and Disentanglementcited by 89
  31. 2022Latent Diffusion Energy-Based Model for Interpretable Text Modelingcited by 67
  32. 2023On the Design Fundamentals of Diffusion Models: A Surveycited by 59
  33. 2020Efficient Learning of Generative Models via Finite-Difference Score Matchingcited by 49
  34. 2019Neural Empirical Bayescited by 46
  35. 2019GluonTS: Probabilistic Time Series Models in Pythoncited by 45
  36. 2021ScoreGrad: Multivariate Probabilistic Time Series Forecasting with Continuous Energy-based Generative Modelscited by 42
  37. 2022Modeling Temporal Data as Continuous Functions with Stochastic Process Diffusioncited by 39
  38. 2021Temporal Latent Auto-Encoder: A Method for Probabilistic Multivariate Time Series Forecastingcited by 32

50 most cited of 56 All 56 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 5; 2025: 14; 2026: 6.

25 papers.

Sort:

By area:

  1. 2024TimeDART: A Diffusion Autoregressive Transformer for Self-Supervised Time Series Representationcited by 14
  2. 2024Elucidating the Design Choice of Probability Paths in Flow Matching for Forecastingcited by 12
  3. 2025Diffusion Models for Time Series Forecasting: A Surveycited by 11
  4. 2025VisionTS++: Cross-Modal Time Series Foundation Model with Continual Pre-trained Vision Backbonescited by 11
  5. 2024Auto-Regressive Moving Diffusion Models for Time Series Forecastingcited by 9
  6. 2025Probabilistic Forecasting via Autoregressive Flow Matchingcited by 9
  7. 2024Constrained Posterior Sampling: Time Series Generation with Hard Constraintscited by 6
  8. 2025Byte Pair Encoding for Efficient Time Series Forecastingcited by 5
  9. 2025RDIT: Residual-based Diffusion Implicit Models for Probabilistic Time Series Forecastingcited by 4
  10. 2024Conditional Lagrangian Wasserstein Flow for Time Series Imputationcited by 3
  11. 2025High-Performance Self-Supervised Learning by Joint Training of Flow Matchingcited by 3
  12. 2025How to Unlock Time Series Editing? Diffusion-Driven Approach with Multi-Grained Controlcited by 1
13 more
  1. 2026DeXposure-FM: A Time-series, Graph Foundation Model for Credit Exposures and Stability on Decentralized Financial Networkscited by 1
  2. 2025Hallucination Detection and Mitigation with Diffusion in Multi-Variate Time-Series Foundation Modelscited by 0
  3. 2025STDiff: A State Transition Diffusion Framework for Time Series Imputation in Industrial Systemscited by 0
  4. 2025Conditional Deep Levy Models for Exotic Derivatives: History-Aware Path Generation and P-Q Payoff Diagnosticscited by 0
  5. 2025CSI Prediction Using Diffusion Modelscited by 0
  6. 2025It Takes Two to Tango: Two Parallel Samplers Improve Quality in Diffusion Models for Limited Stepscited by 0
  7. 2025Structured Noise Modeling for Enhanced Time-Series Forecastingcited by 0
  8. 2025EMFusion: Uncertainty-Aware Conditional Diffusion Model for Multivariate Narrow-band Exposure Forecastingcited by 0
  9. 2026Graph2TS: Structure-Controlled Time Series Generation via Quantile-Graph VAEscited by 0
  10. 2026Probabilistic Prediction of Neural Dynamics via Autoregressive Flow Matchingcited by 0
  11. 2026Conditional Diffusion Models for Energy-Efficient Drivingcited by 0
  12. 2026Diffusion models for eye-gaze trajectory generation using position and velocity representationscited by 0
  13. 2026ProtoFlow: Prototype-Guided Flow Matching for Multivariate Time Series Forecastingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Series-to-Series Diffusion Bridge Model
  2. 2024Retrieval-Augmented Diffusion Models for Time Series Forecasting
  3. 2024ANT: Adaptive Noise Schedule for Time Series Diffusion Models
  4. 2024A Survey on Diffusion Models for Time Series and Spatio-Temporal Data
  5. 2026Diffusion-Driven State Space Models
  6. 2023Predict, Refine, Synthesize: Self-Guiding Diffusion Models for Probabilistic Time Series Forecasting
  7. 2026When Denoising Hurts: Rethinking the Terminal Step of Diffusion Time Series Forecasters -- Extended Version
  8. 2023Diffusion Models for Generative Artificial Intelligence: An Introduction for Applied Mathematicians