mlsanityData to 7 Oct 2026

TransFusion: Generating Long, High Fidelity Time Series using Diffusion Models with Transformers

arXiv 2307.12667 ↗First posted 24 Jul 2023cs.LGcited by 13

On the map: Diffusion models → Medical imaging and segmentation

Abstract (arXiv)

The generation of high-quality, long-sequenced time-series data is essential due to its wide range of applications. In the past, standalone Recurrent and Convolutional Neural Network-based Generative Adversarial Networks (GAN) were used to synthesize time-series data. However, they are inadequate for generating long sequences of time-series data due to limitations in the architecture. Furthermore, GANs are well known for their training instability and mode collapse problem. To address this, we propose TransFusion, a diffusion, and transformers-based generative model to generate high-quality long-sequence time-series data. We have stretched the sequence length to 384, and generated high-quality synthetic data. Also, we introduce two evaluation metrics to evaluate the quality of the synthetic data as well as its predictive characteristics. We evaluate TransFusion with a wide variety of visual and empirical metrics, and TransFusion outperforms the previous state-of-the-art by a significant margin.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models. Builds on 25 of its 41 references that are in the map. First posted on arXiv 24 Jul 2023.

Builds on

25 of 41 references.

References · 25

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  5. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
  6. 2018Neural Ordinary Differential Equationscited by 3,733
  7. 2022Video Diffusion Modelscited by 2,280
  8. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,339
  9. 2018Deep learning for time series classification: a reviewcited by 575
  10. 2016Temporal Convolutional Networks for Action Segmentation and Detectioncited by 504
  11. 2020Neural Controlled Differential Equations for Irregular Time Seriescited by 501
  12. 2020Reliable Fidelity and Diversity Metrics for Generative Modelscited by 425
13 more
  1. 2021Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecastingcited by 332
  2. 2018Adversarial Audio Synthesiscited by 222
  3. 2021How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative Modelscited by 193
  4. 2019Quant GANs: Deep Generation of Financial Time Seriescited by 107
  5. 2020COT-GAN: Generating Sequential Data via Causal Optimal Transportcited by 70
  6. 2021Sig-Wasserstein GANs for Time Series Generationcited by 60
  7. 2017Adversarial Feature Matching for Text Generationcited by 58
  8. 2022GT-GAN: General Purpose Time Series Synthesis with Generative Adversarial Networkscited by 43
  9. 2017CVAE-GAN: Fine-Grained Image Generation through Asymmetric Trainingcited by 42
  10. 2022TTS-GAN: A Transformer-based Time-Series Generative Adversarial Networkcited by 41
  11. 2020CorGAN: Correlation-Capturing Convolutional Generative Adversarial Networks for Generating Synthetic Healthcare Recordscited by 37
  12. 2020Modeling Continuous Stochastic Processes with Dynamic Normalizing Flowscited by 37
  13. 2022Mandarin Singing Voice Synthesis with Denoising Diffusion Probabilistic Wasserstein GANcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 5; 2025: 6; 2026: 2.

13 papers.

Sort:

By area:

  1. 2024Foundation Models for Time Series Analysis: A Tutorial and Surveycited by 234
  2. 2024A Survey on Diffusion Models for Time Series and Spatio-Temporal Datacited by 66
  3. 2024A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating Large VLMscited by 35
  4. 2025A Diffusion Model for Regular Time Series Generation from Irregular Data with Completion and Maskingcited by 7
  5. 2026Skin Tokens: A Learned Compact Representation for Unified Autoregressive Riggingcited by 5
  6. 2024FairX: A comprehensive benchmarking tool for model analysis using fairness, utility, and explainabilitycited by 2
  7. 2025WaveletDiff: Multilevel Wavelet Diffusion For Time Series Generationcited by 2
  8. 2025Generating Realistic Multi-Beat ECG Signalscited by 1
  9. 2026TransConv-DDPM: Enhanced Diffusion Model for Generating Time-Series Data in Healthcarecited by 1
  10. 2024Synthetic Time Series Data Generation for Healthcare Applications: A PCG Case Studycited by 0
  11. 2025Challenges and Limitations of Generative AI in Synthesizing Wearable Sensor Datacited by 0
  12. 2025Fiaingen: A financial time series generative method matching real-world data qualitycited by 0
1 more
  1. 2025Privacy-Preserving Generative Modeling and Clinical Validation of Longitudinal Health Records for Chronic Diseasecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Utilizing Image Transforms and Diffusion Models for Generative Modeling of Short and Long Time Series
  2. 2025TIMED: Adversarial and Autoregressive Refinement of Diffusion-Based Time Series Generation
  3. 2024A Survey of Transformer Enabled Time Series Synthesis
  4. 2025Time Series Generation Under Data Scarcity: A Unified Generative Modeling Approach
  5. 2025Forecasting-based Biomedical Time-series Data Synthesis for Open Data and Robust AI
  6. 2024Generative AI for Synthetic Data Across Multiple Medical Modalities: A Systematic Review of Recent Developments and Challenges
  7. 2026High-Quality Synthetic Financial Time-Series using a GAN-Diffusion Framework
  8. 2024Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model