mlsanityData to 7 Oct 2026

Non-autoregressive Conditional Diffusion Models for Time Series Prediction

arXiv 2306.05043 ↗First posted 8 Jun 2023cs.LGcited by 77

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

Abstract (arXiv)

Recently, denoising diffusion models have led to significant breakthroughs in the generation of images, audio and text. However, it is still an open question on how to adapt their strong modeling ability to model time series. In this paper, we propose TimeDiff, a non-autoregressive diffusion model that achieves high-quality time series prediction with the introduction of two novel conditioning mechanisms: future mixup and autoregressive initialization. Similar to teacher forcing, future mixup allows parts of the ground-truth future predictions for conditioning, while autoregressive initialization helps better initialize the model with basic time series patterns such as short-term trends. Extensive experiments are performed on nine real-world datasets. Results show that TimeDiff consistently outperforms existing time series diffusion models, and also achieves the best overall performance across a variety of the existing strong baselines (including transformers and FiLM).

Key facts. Cited by 77 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 37 of its 50 references that are in the map. First posted on arXiv 8 Jun 2023.

Builds on

37 of 50 references.

Closest ancestors · 2

Same direction, newest first

  1. 2021CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation7 Jul
  2. 2021Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecasting28 Jan

Other references · 35

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  5. 2020Denoising Diffusion Implicit Modelscited by 9,655
  6. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  7. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  8. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,141
  9. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 1,981
  10. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,961
  11. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,654
  12. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,419
23 more
  1. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,400
  2. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,339
  3. 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,200
  4. 2022Diffusion-LM Improves Controllable Text Generationcited by 1,006
  5. 2017Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learningcited by 935
  6. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 869
  7. 2015Scheduled Sampling for Sequence Prediction with Recurrent Neural Networkscited by 779
  8. 2019N-BEATS: Neural basis expansion analysis for interpretable time series forecastingcited by 744
  9. 2021ILVR: Conditioning Method for Denoising Diffusion Probabilistic Modelscited by 634
  10. 2020WaveGrad: Estimating Gradients for Waveform Generationcited by 620
  11. 2019Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecastingcited by 606
  12. 2020A Transformer-based Framework for Multivariate Time Series Representation Learningcited by 449
  13. 2022DiffuSeq: Sequence to Sequence Text Generation with Diffusion Modelscited by 439
  14. 2016Time Series Classification from Scratch with Deep Neural Networks: A Strong Baselinecited by 358
  15. 2022Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Modelscited by 331
  16. 2022Diffusion Probabilistic Modeling for Video Generationcited by 237
  17. 2022Diffusion-based Time Series Imputation and Forecasting with Structured State Space Modelscited by 195
  18. 2022FiLM: Frequency improved Legendre Memory Model for Long-term Time Series Forecastingcited by 147
  19. 2023Generative Time Series Forecasting with Diffusion, Denoise, and Disentanglementcited by 89
  20. 2021Guided-TTS: A Diffusion Model for Text-to-Speech via Classifier Guidancecited by 84
  21. 2023A Theoretical Justification for Image Inpainting using Denoising Diffusion Probabilistic Modelscited by 37
  22. 2022DEPTS: Deep Expansion Learning for Periodic Time Series Forecastingcited by 28
  23. 2022Dynamic Dual-Output Diffusion Modelscited by 25

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 22; 2025: 24; 2026: 29.

77 papers.

Sort:

By area:

  1. 2025Sundial: A Family of Highly Capable Time Series Foundation Modelscited by 168
  2. 2024A Survey on Diffusion Models for Time Series and Spatio-Temporal Datacited by 66
  3. 2024Flow Matching with Gaussian Process Priors for Probabilistic Time Series Forecastingcited by 40
  4. 2024Retrieval-Augmented Diffusion Models for Time Series Forecastingcited by 35
  5. 2024MG-TSD: Multi-Granularity Time Series Diffusion Models with Guided Learning Processcited by 31
  6. 2024The Rise of Diffusion Models in Time-Series Forecastingcited by 25
  7. 2025Non-stationary Diffusion For Probabilistic Time Series Forecastingcited by 24
  8. 2024FlowTS: Time Series Generation via Rectified Flowcited by 22
  9. 2025BRIDGE: Bootstrapping Text to Control Time-Series Generation via Multi-Agent Iterative Optimization and Diffusion Modelingcited by 18
  10. 2025Deep Learning and Foundation Models for Weather Prediction: A Surveycited by 15
  11. 2024TimeDART: A Diffusion Autoregressive Transformer for Self-Supervised Time Series Representationcited by 14
  12. 2024ANT: Adaptive Noise Schedule for Time Series Diffusion Modelscited by 11
38 more
  1. 2025Diffusion Models for Time Series Forecasting: A Surveycited by 11
  2. 2025Deep Learning for Time Series Forecasting: A Surveycited by 10
  3. 2025Vision-Enhanced Time Series Forecasting via Latent Diffusion Modelscited by 9
  4. 2023Non-Autoregressive Diffusion-based Temporal Point Processes for Continuous-Time Long-Term Event Predictioncited by 7
  5. 2024Score-CDM: Score-Weighted Convolutional Diffusion Model for Multivariate Time Series Imputationcited by 6
  6. 2024Modeling Temporal Dependencies within the Target for Long-Term Time Series Forecastingcited by 6
  7. 2024Constrained Posterior Sampling: Time Series Generation with Hard Constraintscited by 6
  8. 2024SpecSTG: A Fast Spectral Diffusion Framework for Probabilistic Spatio-Temporal Traffic Forecastingcited by 5
  9. 2024How Deep is your Guess? A Fresh Perspective on Deep Learning for Medical Time-Series Imputationcited by 5
  10. 2025Unveiling the Power of Noise Priors: Enhancing Diffusion Models for Mobile Traffic Predictioncited by 4
  11. 2025Robust Optimization with Diffusion Models for Green Securitycited by 4
  12. 2025RDIT: Residual-based Diffusion Implicit Models for Probabilistic Time Series Forecastingcited by 4
  13. 2023D3A-TS: Denoising-Driven Data Augmentation in Time Seriescited by 3
  14. 2024Model Free Prediction with Uncertainty Assessmentcited by 3
  15. 2024Conditional Denoising Meets Polynomial Modeling: A Flexible Decoupled Framework for Time Series Forecastingcited by 3
  16. 2024Series-to-Series Diffusion Bridge Modelcited by 3
  17. 2025Bridging the Last Mile of Prediction: Enhancing Time Series Forecasting with Conditional Guided Flow Matchingcited by 3
  18. 2025DoFlow: Flow-based Generative Models for Interventional and Counterfactual Forecasting on Time Seriescited by 3
  19. 2024Channel-aware Contrastive Conditional Diffusion for Multivariate Probabilistic Time Series Forecastingcited by 2
  20. 2025EventTSF: Event-Aware Non-Stationary Time Series Forecastingcited by 2
  21. 2025WaveletDiff: Multilevel Wavelet Diffusion For Time Series Generationcited by 2
  22. 2025TimeFlow: Towards Stochastic-Aware and Efficient Time Series Generation via Flow Matching Modelingcited by 2
  23. 2025TARFVAE: Efficient One-Step Generative Time Series Forecasting via TARFLOW based VAEcited by 2
  24. 2024Review of Data-centric Time Series Analysis from Sample, Feature, and Periodcited by 1
  25. 2024Stochastic Diffusion: A Diffusion Probabilistic Model for Stochastic Time Series Forecastingcited by 1
  26. 2024Treating Brain-inspired Memories as Priors for Diffusion Model to Forecast Multivariate Time Seriescited by 1
  27. 2024Domain Fusion Controllable Generalization for Cross-Domain Time Series Forecasting from Multi-Domain Integrated Distributioncited by 1
  28. 2025Cross-Modal Diffusion for Biomechanical Dynamical Systems Through Local Manifold Alignmentcited by 1
  29. 2026Sequence Diffusion Model for Temporal Link Prediction in Continuous-Time Dynamic Graphcited by 1
  30. 2026Drift Estimation for Stochastic Differential Equations with Denoising Diffusion Modelscited by 1
  31. 2026StaTS: Spectral Trajectory Schedule Learning for Adaptive Time Series Forecasting with Frequency Guided Denoisercited by 1
  32. 2024Deep Temporal Deaggregation: Large-Scale Spatio-Temporal Generative Modelscited by 0
  33. 2025Collaborative Deterministic-Probabilistic Forecasting for Diverse Spatiotemporal Systemscited by 0
  34. 2025Alternators With Noise Modelscited by 0
  35. 2025Multimodal Forecasting of Sparse Intraoperative Hypotension Events Powered by Language Modelcited by 0
  36. 2025CHIME: Conditional Hallucination and Integrated Multi-scale Enhancement for Time Series Diffusion Modelcited by 0
  37. 2025Meta-SurDiff: Classification Diffusion Model Optimized by Meta Learning is Reliable for Online Surgical Phase Recognitioncited by 0
  38. 2025From Noise to Precision: A Diffusion-Driven Approach to Zero-Inflated Precipitation Predictioncited by 0

50 most cited of 77 All 77 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Multimodal Conditioned Diffusive Time Series Forecasting
  2. 2023Diffusion Models for Time Series Applications: A Survey
  3. 2025Dynamical Diffusion: Learning Temporal Dynamics with Diffusion Models
  4. 2025TIMED: Adversarial and Autoregressive Refinement of Diffusion-Based Time Series Generation
  5. 2023Add and Thin: Diffusion for Temporal Point Processes
  6. 2024TimeDiT: General-purpose Diffusion Transformers for Time Series Foundation Model
  7. 2026When Denoising Hurts: Rethinking the Terminal Step of Diffusion Time Series Forecasters -- Extended Version
  8. 2024Auto-Regressive Moving Diffusion Models for Time Series Forecasting