mlsanityData to 7 Oct 2026

Diffusion-TS: Interpretable Diffusion for General Time Series Generation

arXiv 2403.01742 ↗First posted 4 Mar 2024cs.LG cs.AIcited by 179

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

Abstract (arXiv)

Denoising diffusion probabilistic models (DDPMs) are becoming the leading paradigm for generative models. It has recently shown breakthroughs in audio synthesis, time series imputation and forecasting. In this paper, we propose Diffusion-TS, a novel diffusion-based framework that generates multivariate time series samples of high quality by using an encoder-decoder transformer with disentangled temporal representations, in which the decomposition technique guides Diffusion-TS to capture the semantic meaning of time series while transformers mine detailed sequential information from the noisy model input. Different from existing diffusion-based approaches, we train the model to directly reconstruct the sample instead of the noise in each diffusion step, combining a Fourier-based loss term. Diffusion-TS is expected to generate time series satisfying both interpretablity and realness. In addition, it is shown that the proposed Diffusion-TS can be easily extended to conditional generation tasks, such as forecasting and imputation, without any model changes. This also motivates us to further explore the performance of Diffusion-TS under irregular settings. Finally, through qualitative and quantitative experiments, results show that Diffusion-TS achieves the state-of-the-art results on various realistic analyses of time series.

Key facts. Cited by 179 papers in the map (data through 7 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. First posted on arXiv 4 Mar 2024.

Builds on

0 of 0 references.

No references here yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 20; 2025: 73; 2026: 86.

179 papers.

Sort:

By area:

  1. 2024Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Surveycited by 52
  2. 2024Utilizing Image Transforms and Diffusion Models for Generative Modeling of Short and Long Time Seriescited by 42
  3. 2024TimeDiT: General-purpose Diffusion Transformers for Time Series Foundation Modelcited by 33
  4. 2025Kronos: A Foundation Model for the Language of Financial Marketscited by 25
  5. 2025Non-stationary Diffusion For Probabilistic Time Series Forecastingcited by 24
  6. 2024FlowTS: Time Series Generation via Rectified Flowcited by 22
  7. 2025TimeDP: Learning to Generate Multi-Domain Time Series with Domain Promptscited by 21
  8. 2024Sports-Traj: A Unified Trajectory Generation Model for Multi-Agent Movement in Sportscited by 19
  9. 2025T2S: High-resolution Time Series Generation with Text-to-Series Diffusion Modelscited by 19
  10. 2025BRIDGE: Bootstrapping Text to Control Time-Series Generation via Multi-Agent Iterative Optimization and Diffusion Modelingcited by 18
  11. 2025Population Aware Diffusion for Time Series Generationcited by 14
  12. 2025Time Series Generation Under Data Scarcity: A Unified Generative Modeling Approachcited by 14
38 more
  1. 2025TAMO: Fine-Grained Root Cause Analysis via Tool-Assisted LLM Agent with Multi-Modality Observation Data in Cloud-Native Systemscited by 13
  2. 2024ANT: Adaptive Noise Schedule for Time Series Diffusion Modelscited by 11
  3. 2025Diffusion Models for Time Series Forecasting: A Surveycited by 11
  4. 2024TimeLDM: Latent Diffusion Model for Unconditional Time Series Generationcited by 10
  5. 2025Deep Learning for Time Series Forecasting: A Surveycited by 10
  6. 2024Auto-Regressive Moving Diffusion Models for Time Series Forecastingcited by 9
  7. 2025Vision-Enhanced Time Series Forecasting via Latent Diffusion Modelscited by 9
  8. 2025TarDiff: Target-Oriented Diffusion Guidance for Synthetic Electronic Health Record Time Series Generationcited by 8
  9. 2025Multimodal Conditioned Diffusive Time Series Forecastingcited by 8
  10. 2025Causal Time Series Generation via Diffusion Modelscited by 7
  11. 2025A Diffusion Model for Regular Time Series Generation from Irregular Data with Completion and Maskingcited by 7
  12. 2025Towards Identifiability of Hierarchical Temporal Causal Representation Learningcited by 7
  13. 2024RespDiff: An End-to-End Multi-scale RNN Diffusion Model for Respiratory Waveform Estimation from PPG Signalscited by 6
  14. 2024Constrained Posterior Sampling: Time Series Generation with Hard Constraintscited by 6
  15. 2024TimeBridge: Better Diffusion Prior Design with Bridge Models for Time Series Generationcited by 5
  16. 2024SynEHRgy: Synthesizing Mixed-Type Structured Electronic Health Records using Decoder-Only Transformerscited by 5
  17. 2025Diffusion Models for Computational Neuroimaging: A Surveycited by 5
  18. 2025TRADES: Generating Realistic Market Simulations with Diffusion Modelscited by 5
  19. 2025Step-Aware Residual-Guided Diffusion for EEG Spatial Super-Resolutioncited by 5
  20. 2024TimeAutoDiff: A Unified Framework for Generation, Imputation, Forecasting, and Time-Varying Metadata Conditioning of Heterogeneous Time Series Tabular Datacited by 4
  21. 2025WaveStitch: Flexible and Fast Conditional Time Series Generation with Diffusion Modelscited by 4
  22. 2025Counterfactual Probabilistic Diffusion with Expert Modelscited by 4
  23. 2026IT-OSE: Exploring Optimal Sample Size for Industrial Data Augmentationcited by 4
  24. 2024Conditional Denoising Meets Polynomial Modeling: A Flexible Decoupled Framework for Time Series Forecastingcited by 3
  25. 2025CENTS: Generating synthetic electricity consumption time series for rare and unseen scenarioscited by 3
  26. 2025MSDformer: Multi-scale Discrete Transformer For Time Series Generationcited by 3
  27. 2025TimeWak: Temporal Chained-Hashing Watermark for Time Series Datacited by 3
  28. 2025Bridging the Last Mile of Prediction: Enhancing Time Series Forecasting with Conditional Guided Flow Matchingcited by 3
  29. 2025CTBench: Cryptocurrency Time Series Generation Benchmarkcited by 3
  30. 2025T2I-Diff: fMRI Signal Generation via Time-Frequency Image Transform and Classifier-Free Denoising Diffusion Modelscited by 3
  31. 2025TSGM: Regular and Irregular Time-series Generation using Score-based Generative Modelscited by 3
  32. 2026SDFlow: Similarity-Driven Flow Matching for Time Series Generationcited by 3
  33. 2024Channel-aware Contrastive Conditional Diffusion for Multivariate Probabilistic Time Series Forecastingcited by 2
  34. 2025Theoretical Foundation of Flow-Based Time Series Generation: Provable Approximation, Generalization, and Efficiencycited by 2
  35. 2025EventTSF: Event-Aware Non-Stationary Time Series Forecastingcited by 2
  36. 2025DS-Diffusion: Data Style-Guided Diffusion Model for Time-Series Generationcited by 2
  37. 2025WaveletDiff: Multilevel Wavelet Diffusion For Time Series Generationcited by 2
  38. 2025Sequence Modeling with Spectral Mean Flowscited by 2

50 most cited of 179 All 179 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023TS-Diffusion: Generating Highly Complex Time Series with Diffusion Models
  2. 2023Generative Time Series Forecasting with Diffusion, Denoise, and Disentanglement
  3. 2023Diffusion Models for Time Series Applications: A Survey
  4. 2026DiTS: Multimodal Diffusion Transformers Are Time Series Forecasters
  5. 2023Predict, Refine, Synthesize: Self-Guiding Diffusion Models for Probabilistic Time Series Forecasting
  6. 2024Self-Supervised Learning of Time Series Representation via Diffusion Process and Imputation-Interpolation-Forecasting Mask
  7. 2025TIMED: Adversarial and Autoregressive Refinement of Diffusion-Based Time Series Generation
  8. 2024TimeDART: A Diffusion Autoregressive Transformer for Self-Supervised Time Series Representation