A survey on diffusion models for time series and spatio-temporal data
The study of time series data is crucial for understanding trends and anomalies over time,
enabling predictive insights across various sectors. Spatio-temporal data, on the other hand …
enabling predictive insights across various sectors. Spatio-temporal data, on the other hand …
A Survey of Transformer Enabled Time Series Synthesis
Generative AI has received much attention in the image and language domains, with the
transformer neural network continuing to dominate the state of the art. Application of these …
transformer neural network continuing to dominate the state of the art. Application of these …
Utilizing Image Transforms and Diffusion Models for Generative Modeling of Short and Long Time Series
Lately, there has been a surge in interest surrounding generative modeling of time series
data. Most existing approaches are designed either to process short sequences or to handle …
data. Most existing approaches are designed either to process short sequences or to handle …
Entity-based Financial Tabular Data Synthesis with Diffusion Models
In the rapidly evolving financial industry, the adoption of synthetic tabular data is on the rise
to augment scarce data and facilitate data sharing. Existing synthetic tabular data generation …
to augment scarce data and facilitate data sharing. Existing synthetic tabular data generation …
Controllable Sequence Editing for Counterfactual Generation
MM Li, K Li, Y Ektefaie, S Messica, M Zitnik - arXiv preprint arXiv …, 2025 - arxiv.org
Sequence models generate counterfactuals by modifying parts of a sequence based on a
given condition, enabling reasoning about" what if" scenarios. While these models excel at …
given condition, enabling reasoning about" what if" scenarios. While these models excel at …
Towards editing time series
Synthesizing time series data is pivotal in modern society, aiding effective decision making
and ensuring privacy preservation in various scenarios. Time series are associated with …
and ensuring privacy preservation in various scenarios. Time series are associated with …
How Much Can Time-related Features Enhance Time Series Forecasting?
Recent advancements in long-term time series forecasting (LTSF) have primarily focused on
capturing cross-time and cross-variate (channel) dependencies within historical data …
capturing cross-time and cross-variate (channel) dependencies within historical data …
Channel-aware Contrastive Conditional Diffusion for Multivariate Probabilistic Time Series Forecasting
Forecasting faithful trajectories of multivariate time series from practical scopes is essential
for reasonable decision-making. Recent methods majorly tailor generative conditional …
for reasonable decision-making. Recent methods majorly tailor generative conditional …
CENTS: Generating synthetic electricity consumption time series for rare and unseen scenarios
M Fuest, A Cuesta, K Veeramachaneni - arXiv preprint arXiv:2501.14426, 2025 - arxiv.org
Recent breakthroughs in large-scale generative modeling have demonstrated the potential
of foundation models in domains such as natural language, computer vision, and protein …
of foundation models in domains such as natural language, computer vision, and protein …
Constrained Posterior Sampling: Time Series Generation with Hard Constraints
Generating realistic time series samples is crucial for stress-testing models and protecting
user privacy by using synthetic data. In engineering and safety-critical applications, these …
user privacy by using synthetic data. In engineering and safety-critical applications, these …