ReDiTT: Retrieval Augmented Conditional Diffusion Transformers for Asynchronous Time Series
arXiv:2607.12391
The paper proposes ReDiTT, a diffusion‑based conditional transformer that retrieves similar latent sequences from a memory bank to improve prediction of the next event time and type in asynchronous time series, leading to more stable long‑horizon forecasts and greater sample diversity.
Abstract
We present a diffusion based model for asynchronous time series prediction, where the goal is to predict the next inter event time and event type. To address the inherent uncertainty of future events, we introduce ReDiTT, a retrieval augmented conditional diffusion transformer that operates in latent space. ReDiTT retrieves structurally similar latent sequences from a memory bank during both training and inference and incorporates them as reference conditions through cross attention. This retrieval based conditioning allows the model to attend to relevant temporal dynamics and provides global structural guidance for generation. As a result, ReDiTT stabilizes long horizon forecasting and improves sample diversity. Experiments on seven real world datasets demonstrate state of the art performance on next event prediction and long horizon forecasting. Our code is available at https://github.com/BorealisAI/ReDiTT.
Accepted at TMLR 2026