mlsanityData to 7 Oct 2026

ReDiTT: Retrieval Augmented Conditional Diffusion Transformers for Asynchronous Time Series

arXiv 2607.12391 ↗First posted 14 Jul 2026cs.LGcited by 0

On the map: Retrieval-augmented generation → Time series and agricultural RAG

also in 1 more
Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Time series and agricultural RAG, one of 15 directions in Retrieval-augmented generation. Builds on 30 of its 48 references that are in the map. First posted on arXiv 14 Jul 2026.

Builds on

30 of 48 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025TS-RAG: Retrieval-Augmented Generation based Time Series Foundation Models are Stronger Zero-Shot Forecaster6 Mar
  2. 2024Retrieval Augmented Time Series Forecasting12 Nov
  3. 2024Retrieval-Augmented Diffusion Models for Time Series Forecasting24 Oct

Other references · 27

  1. 2022Scalable Diffusion Models with Transformerscited by 5,931
  2. 2022Flow Matching for Generative Modelingcited by 5,426
  3. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
  4. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  5. 2019Generalization through Memorization: Nearest Neighbor Language Modelscited by 788
  6. 2021CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputationcited by 577
  7. 2021Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecastingcited by 332
  8. 2019Intensity-Free Learning of Temporal Point Processescited by 138
  9. 2024Improving the Training of Rectified Flowscited by 106
  10. 2021Modeling Irregular Time Series with Continuous Recurrent Unitscited by 101
  11. 2015Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videoscited by 93
  12. 2021Transformer Embeddings of Irregularly Spaced Events and Their Participantscited by 90
15 more
  1. 2023EasyTPP: Towards Open Benchmarking Temporal Point Processescited by 63
  2. 2022HYPRO: A Hybridly Normalized Probabilistic Model for Long-Horizon Prediction of Event Sequencescited by 57
  3. 2023Spatio-temporal Diffusion Point Processescited by 52
  4. 2019Imputing Missing Events in Continuous-Time Event Streamscited by 43
  5. 2020Neural Temporal Point Processes For Modelling Electronic Health Recordscited by 39
  6. 2019A Variational Auto-Encoder Model for Stochastic Point Processescited by 30
  7. 2023Add and Thin: Diffusion for Temporal Point Processescited by 22
  8. 2022Counterfactual Neural Temporal Point Process for Estimating Causal Influence of Misinformation on Social Mediacited by 20
  9. 2022Interval-censored Transformer Hawkes: Detecting Information Operations using the Reaction of Social Systemscited by 16
  10. 2024Decomposable Transformer Point Processescited by 15
  11. 2020Visual Causality Analysis of Event Sequence Datacited by 12
  12. 2023Interacting Diffusion Processes for Event Sequence Forecastingcited by 9
  13. 2018Stochastic Optimal Control of Epidemic Processes in Networkscited by 7
  14. 2023Non-Autoregressive Diffusion-based Temporal Point Processes for Continuous-Time Long-Term Event Predictioncited by 7
  15. 2025ADiff4TPP: Asynchronous Diffusion Models for Temporal Point Processescited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023Predict, Refine, Synthesize: Self-Guiding Diffusion Models for Probabilistic Time Series Forecasting
  2. 2025WaveStitch: Flexible and Fast Conditional Time Series Generation with Diffusion Models
  3. 2024TimeDiT: General-purpose Diffusion Transformers for Time Series Foundation Model
  4. 2026Which Histories Matter for Time Series Forecasting? Learning Predictive Relevance with Future Supervision
  5. 2026Stationarity-Aware Retrieval-Augmented Time Series Forecasting
  6. 2024TimeDART: A Diffusion Autoregressive Transformer for Self-Supervised Time Series Representation
  7. 2026SEER: Self-Evolving Event Reasoning and Retrieval for Time Series Forecasting
  8. 2024Treating Brain-inspired Memories as Priors for Diffusion Model to Forecast Multivariate Time Series