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

arXiv: https://arxiv.org/abs/2307.12667 · HTML: https://mlsanity.com/paper/2307.12667/

## Key facts

- Cited by 13 papers in the map (data through 14 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.

## Placed in

- Diffusion models / [Medical imaging and segmentation](https://mlsanity.com/diffusion/medical-imaging-and-segmentation/)

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Neural Ordinary Differential Equations](https://mlsanity.com/paper/1806.07366/) (2018)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [DiffWave: A Versatile Diffusion Model for Audio Synthesis](https://mlsanity.com/paper/2009.09761/) (2020)
- [Deep learning for time series classification: a review](https://mlsanity.com/paper/1809.04356/) (2018)
- [Temporal Convolutional Networks for Action Segmentation and Detection](https://mlsanity.com/paper/1611.05267/) (2016)
- [Neural Controlled Differential Equations for Irregular Time Series](https://mlsanity.com/paper/2005.08926/) (2020)
- [Reliable Fidelity and Diversity Metrics for Generative Models](https://mlsanity.com/paper/2002.09797/) (2020)
- [Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecasting](https://mlsanity.com/paper/2101.12072/) (2021)
- [Adversarial Audio Synthesis](https://mlsanity.com/paper/1802.04208/) (2018)
- [How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative Models](https://mlsanity.com/paper/2102.08921/) (2021)
- [Quant GANs: Deep Generation of Financial Time Series](https://mlsanity.com/paper/1907.06673/) (2019)
- [COT-GAN: Generating Sequential Data via Causal Optimal Transport](https://mlsanity.com/paper/2006.08571/) (2020)
- [Sig-Wasserstein GANs for Time Series Generation](https://mlsanity.com/paper/2111.01207/) (2021)
- [Adversarial Feature Matching for Text Generation](https://mlsanity.com/paper/1706.03850/) (2017)
- [GT-GAN: General Purpose Time Series Synthesis with Generative Adversarial Networks](https://mlsanity.com/paper/2210.02040/) (2022)
- [CVAE-GAN: Fine-Grained Image Generation through Asymmetric Training](https://mlsanity.com/paper/1703.10155/) (2017)
- [TTS-GAN: A Transformer-based Time-Series Generative Adversarial Network](https://mlsanity.com/paper/2202.02691/) (2022)
- [CorGAN: Correlation-Capturing Convolutional Generative Adversarial Networks for Generating Synthetic Healthcare Records](https://mlsanity.com/paper/2001.09346/) (2020)
- [Modeling Continuous Stochastic Processes with Dynamic Normalizing Flows](https://mlsanity.com/paper/2002.10516/) (2020)
- [Mandarin Singing Voice Synthesis with Denoising Diffusion Probabilistic Wasserstein GAN](https://mlsanity.com/paper/2209.10446/) (2022)

## Built on by (most cited first, 13 of 13)

- [Foundation Models for Time Series Analysis: A Tutorial and Survey](https://mlsanity.com/paper/2403.14735/) (2024)
- [A Survey on Diffusion Models for Time Series and Spatio-Temporal Data](https://mlsanity.com/paper/2404.18886/) (2024)
- [A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating Large VLMs](https://mlsanity.com/paper/2412.03324/) (2024)
- [A Diffusion Model for Regular Time Series Generation from Irregular Data with Completion and Masking](https://mlsanity.com/paper/2510.06699/) (2025)
- [Skin Tokens: A Learned Compact Representation for Unified Autoregressive Rigging](https://mlsanity.com/paper/2602.04805/) (2026)
- [WaveletDiff: Multilevel Wavelet Diffusion For Time Series Generation](https://mlsanity.com/paper/2510.11839/) (2025)
- [FairX: A comprehensive benchmarking tool for model analysis using fairness, utility, and explainability](https://mlsanity.com/paper/2406.14281/) (2024)
- [Generating Realistic Multi-Beat ECG Signals](https://mlsanity.com/paper/2505.18189/) (2025)
- [TransConv-DDPM: Enhanced Diffusion Model for Generating Time-Series Data in Healthcare](https://mlsanity.com/paper/2602.07033/) (2026)
- [Synthetic Time Series Data Generation for Healthcare Applications: A PCG Case Study](https://mlsanity.com/paper/2412.16207/) (2024)
- [Challenges and Limitations of Generative AI in Synthesizing Wearable Sensor Data](https://mlsanity.com/paper/2505.14206/) (2025)
- [Fiaingen: A financial time series generative method matching real-world data quality](https://mlsanity.com/paper/2510.01169/) (2025)
- [Privacy-Preserving Generative Modeling and Clinical Validation of Longitudinal Health Records for Chronic Disease](https://mlsanity.com/paper/2512.00434/) (2025)

## 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.