mlsanityData to 13 Oct 2026

EventFlow: Forecasting Temporal Point Processes with Flow Matching

arXiv 2410.07430 ↗First posted 9 Oct 2024cs.LG stat.MLcited by 8

On the map: Diffusion models → Flow matching, time series and science

Abstract (arXiv)

Continuous-time event sequences, in which events occur at irregular intervals, are ubiquitous across a wide range of industrial and scientific domains. The contemporary modeling paradigm is to treat such data as realizations of a temporal point process, and in machine learning it is common to model temporal point processes in an autoregressive fashion using a neural network. While autoregressive models are successful in predicting the time of a single subsequent event, their performance can degrade when forecasting longer horizons due to cascading errors and myopic predictions. We propose EventFlow, a non-autoregressive generative model for temporal point processes. The model builds on the flow matching framework in order to directly learn joint distributions over event times, side-stepping the autoregressive process. EventFlow is simple to implement and achieves a 20%-53% lower forecast error than the nearest baseline on standard TPP benchmarks while simultaneously using fewer model calls at sampling time.

Key facts. Cited by 8 papers in the map (data through 13 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 32 of its 53 references that are in the map. First posted on arXiv 9 Oct 2024.

Builds on

32 of 53 references.

Closest ancestors · 7

Same direction, newest first

  1. 2024Dirichlet Flow Matching with Applications to DNA Sequence Design8 Feb
  2. 2024Generative Flows on Discrete State-Spaces: Enabling Multimodal Flows with Applications to Protein Co-Design7 Feb
  3. 2023EPiC-ly Fast Particle Cloud Generation with Flow-Matching and Diffusion29 Sep
  4. 2023Flow Matching in Latent Space17 Jul
  5. 2023Improving and generalizing flow-based generative models with minibatch optimal transport1 Feb
  6. 2022Flow Matching for Generative Modeling6 Oct
  7. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow7 Sep

Other references · 25

  1. 2017Attention Is All You Needcited by 60,106
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,952
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,028
  4. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,021
  5. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,751
  6. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,317
  7. 2022Building Normalizing Flows with Stochastic Interpolantscited by 979
  8. 2024SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformerscited by 715
  9. 2020Transformer Hawkes Processcited by 230
  10. 2019Intensity-Free Learning of Temporal Point Processescited by 138
  11. 2019Fully Neural Network based Model for General Temporal Point Processescited by 119
  12. 2021Neural Temporal Point Processes: A Reviewcited by 113
13 more
  1. 2017Modeling The Intensity Function Of Point Process Via Recurrent Neural Networkscited by 93
  2. 2021Transformer Embeddings of Irregularly Spaced Events and Their Participantscited by 90
  3. 2023EasyTPP: Towards Open Benchmarking Temporal Point Processescited by 64
  4. 2022HYPRO: A Hybridly Normalized Probabilistic Model for Long-Horizon Prediction of Event Sequencescited by 57
  5. 2022Fast Point Cloud Generation with Straight Flowscited by 56
  6. 2017Wasserstein Learning of Deep Generative Point Process Modelscited by 46
  7. 2019Imputing Missing Events in Continuous-Time Event Streamscited by 43
  8. 2022Exploring Generative Neural Temporal Point Processcited by 30
  9. 2020Fast and Flexible Temporal Point Processes with Triangular Mapscited by 28
  10. 2023Add and Thin: Diffusion for Temporal Point Processescited by 22
  11. 2023On the Predictive Accuracy of Neural Temporal Point Process Models for Continuous-time Event Datacited by 13
  12. 2021An Empirical Study: Extensive Deep Temporal Point Processcited by 10
  13. 2022Probabilistic Querying of Continuous-Time Event Sequencescited by 5

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2025: 4; 2026: 4.

8 papers.

  1. 2025In-Context Learning of Temporal Point Processes with Foundation Inference Modelscited by 7
  2. 2025Edit-Based Flow Matching for Temporal Point Processescited by 7
  3. 2025Advances in Temporal Point Processes: Bayesian, Neural, and LLM Approachescited by 2
  4. 2025Unified Flow Matching for Long Horizon Event Forecastingcited by 0
  5. 2026Arbitrarily Conditioned Hierarchical Flows for Spatiotemporal Eventscited by 0
  6. 2026Structured Neural Marked Point Processes for Interpretable Event Interaction Modelingcited by 0
  7. 2026From Jumps to Signatures: a Generative Method for Temporal Point Processescited by 0
  8. 2026Universal Multi-Modal Traceformer: Integrating Heterogeneous Context for Process Event Predictioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Interacting Diffusion Processes for Event Sequence Forecasting
  2. 2024Flow Matching with Gaussian Process Priors for Probabilistic Time Series Forecasting
  3. 2025TimeFlow: Towards Stochastic-Aware and Efficient Time Series Generation via Flow Matching Modeling
  4. 2025ADiff4TPP: Asynchronous Diffusion Models for Temporal Point Processes
  5. 2025Probabilistic Forecasting via Autoregressive Flow Matching
  6. 2023Non-Autoregressive Diffusion-based Temporal Point Processes for Continuous-Time Long-Term Event Prediction
  7. 2025Speculative Sampling for Parametric Temporal Point Processes
  8. 2026MercerFlow: Flow Matching in a Kernel-Induced Latent Space for Probabilistic Forecasting