mlsanityData to 14 Oct 2026

How to Unlock Time Series Editing? Diffusion-Driven Approach with Multi-Grained Control

arXiv 2506.05276 ↗First posted 5 Jun 2025cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

Recent advances in time series generation have shown promise, yet controlling properties in generated sequences remains challenging. Time Series Editing (TSE) - making precise modifications while preserving temporal coherence - consider both point-level constraints and segment-level controls that current methods struggle to provide. We introduce the CocktailEdit framework to enable simultaneous, flexible control across different types of constraints. This framework combines two key mechanisms: a confidence-weighted anchor control for point-wise constraints and a classifier-based control for managing statistical properties such as sums and averages over segments. Our methods achieve precise local control during the denoising inference stage while maintaining temporal coherence and integrating seamlessly, with any conditionally trained diffusion-based time series models. Extensive experiments across diverse datasets and models demonstrate its effectiveness. Our work bridges the gap between pure generative modeling and real-world time series editing needs, offering a flexible solution for human-in-the-loop time series generation and editing. The code and demo are provided for validation.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 33 of its 42 references that are in the map. First posted on arXiv 5 Jun 2025.

Builds on

33 of 42 references.

References · 33

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2020Denoising Diffusion Implicit Modelscited by 9,781
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  4. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,354
  5. 2021CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputationcited by 582
  6. 2021Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecastingcited by 337
  7. 2017Real-valued (Medical) Time Series Generation with Recurrent Conditional GANscited by 333
  8. 2016NIPS 2016 Tutorial: Generative Adversarial Networkscited by 285
  9. 2022Diffusion-based Time Series Imputation and Forecasting with Structured State Space Modelscited by 198
  10. 2024Deep Time Series Models: A Comprehensive Survey and Benchmarkcited by 197
  11. 2024Diffusion-TS: Interpretable Diffusion for General Time Series Generationcited by 184
  12. 2023Denoising Diffusion Bridge Modelscited by 178
21 more
  1. 2021TimeVAE: A Variational Auto-Encoder for Multivariate Time Series Generationcited by 142
  2. 2019Quant GANs: Deep Generation of Financial Time Seriescited by 108
  3. 2023Generative Time Series Forecasting with Diffusion, Denoise, and Disentanglementcited by 90
  4. 2023DiffSTG: Probabilistic Spatio-Temporal Graph Forecasting with Denoising Diffusion Modelscited by 81
  5. 2023On the Constrained Time-Series Generation Problemcited by 54
  6. 2020Variational Autoencoders for Learning Nonlinear Dynamics of Physical Systemscited by 50
  7. 2023Vector Quantized Time Series Generation with a Bidirectional Prior Modelcited by 50
  8. 2024Retrieval-Augmented Diffusion Models for Time Series Forecastingcited by 39
  9. 2024Time Weaver: A Conditional Time Series Generation Modelcited by 37
  10. 2024TimeDiT: General-purpose Diffusion Transformers for Time Series Foundation Modelcited by 33
  11. 2021Temporal Latent Auto-Encoder: A Method for Probabilistic Multivariate Time Series Forecastingcited by 32
  12. 2023TSGBench: Time Series Generation Benchmarkcited by 26
  13. 2024The Rise of Diffusion Models in Time-Series Forecastingcited by 25
  14. 2023Reliable Generation of Privacy-preserving Synthetic Electronic Health Record Time Series via Diffusion Modelscited by 24
  15. 2023Synthetic ECG Signal Generation using Probabilistic Diffusion Modelscited by 22
  16. 2023Generative modeling for time series via Schr"odinger bridgecited by 18
  17. 2024Score-CDM: Score-Weighted Convolutional Diffusion Model for Multivariate Time Series Imputationcited by 6
  18. 2024TimeBridge: Better Diffusion Prior Design with Bridge Models for Time Series Generationcited by 6
  19. 2024A Survey of Transformer Enabled Time Series Synthesiscited by 5
  20. 2024Diff-MTS: Temporal-Augmented Conditional Diffusion-based AIGC for Industrial Time Series Towards the Large Model Eracited by 5
  21. 2024Towards Controllable Time Series Generationcited by 4

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Instruction-based Time Series Editingcited by 1