mlsanityData to 14 Oct 2026

In-Context Learning of Temporal Point Processes with Foundation Inference Models

arXiv 2509.24762 ↗First posted 29 Sep 2025cs.LGcited by 10

Not on the map. Why?

Abstract (arXiv)

Modeling event sequences of multiple event types with marked temporal point processes (MTPPs) provides a principled way to uncover governing dynamical rules and predict future events. Current neural network approaches to MTPP inference rely on training separate, specialized models for each target system. We pursue a radically different approach: drawing on amortized inference and in-context learning, we pretrain a deep neural network to infer, in-context, the conditional intensity functions of event histories from a context defined by sets of event sequences. Pretraining is performed on a large synthetic dataset of MTPPs sampled from a broad distribution of Hawkes processes. Once pretrained, our Foundation Inference Model for Point Processes (FIM-PP) can estimate MTPPs from real-world data without any additional training, or be rapidly finetuned to target systems. Experiments show that this amortized approach matches the performance of specialized models on next-event prediction across common benchmark datasets.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 34 of its 60 references that are in the map. First posted on arXiv 29 Sep 2025.

Builds on

34 of 60 references.

References · 34

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018Neural Ordinary Differential Equationscited by 3,779
  3. 2022TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Secondcited by 674
  4. 2020Neural Controlled Differential Equations for Irregular Time Seriescited by 506
  5. 2021Transformers Can Do Bayesian Inferencecited by 360
  6. 2021Multi-Time Attention Networks for Irregularly Sampled Time Seriescited by 238
  7. 2019Intensity-Free Learning of Temporal Point Processescited by 140
  8. 2018Learning Tree-based Deep Model for Recommender Systemscited by 99
  9. 2021Transformer Embeddings of Irregularly Spaced Events and Their Participantscited by 93
  10. 2015SEISMIC: A Self-Exciting Point Process Model for Predicting Tweet Popularitycited by 76
  11. 2016Learning Granger Causality for Hawkes Processescited by 69
  12. 2023EasyTPP: Towards Open Benchmarking Temporal Point Processescited by 68
22 more
  1. 2023ODEFormer: Symbolic Regression of Dynamical Systems with Transformerscited by 62
  2. 2022HYPRO: A Hybridly Normalized Probabilistic Model for Long-Horizon Prediction of Event Sequencescited by 57
  3. 2017Wasserstein Learning of Deep Generative Point Process Modelscited by 46
  4. 2019Imputing Missing Events in Continuous-Time Event Streamscited by 44
  5. 2018Lecture Notes: Temporal Point Processes and the Conditional Intensity Functioncited by 40
  6. 2022Exploring Generative Neural Temporal Point Processcited by 30
  7. 2014Discovering Latent Network Structure in Point Process Datacited by 28
  8. 2023Add and Thin: Diffusion for Temporal Point Processescited by 23
  9. 2021Long Horizon Forecasting With Temporal Point Processescited by 20
  10. 2025Position: The Future of Bayesian Prediction Is Prior-Fittedcited by 20
  11. 2024Decomposable Transformer Point Processescited by 16
  12. 2024Zero-shot Imputation with Foundation Inference Models for Dynamical Systemscited by 13
  13. 2024Foundation Inference Models for Markov Jump Processescited by 13
  14. 2023Interacting Diffusion Processes for Event Sequence Forecastingcited by 10
  15. 2024TPP-LLM: Modeling Temporal Point Processes by Efficiently Fine-Tuning Large Language Modelscited by 9
  16. 2024EventFlow: Forecasting Temporal Point Processes with Flow Matchingcited by 8
  17. 2024Learning Granger Causality from Instance-wise Self-attentive Hawkes Processescited by 7
  18. 2025In-Context Learning of Stochastic Differential Equations with Foundation Inference Modelscited by 7
  19. 2024Decoupled Marked Temporal Point Process using Neural Ordinary Differential Equationscited by 6
  20. 2020Recurrent Point Review Modelscited by 4
  21. 2025Amortized In-Context Mixed Effect Transformer Models: A Zero-Shot Approach for Pharmacokineticscited by 4
  22. 2021Dynamic Review-based Recommenderscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 8.

10 papers.

  1. 2026Foundation Inference Models for Ordinary Differential Equationscited by 3
  2. 2026SurvivalPFN: Amortizing Survival Prediction via In-Context Bayesian Inferencecited by 3
  3. 2026Domain-Adaptation through Synthetic Data: Fine-Tuning Large Language Models for German Lawcited by 2
  4. 2026Beyond Reinforcement Learning: Fast and Scalable Quantum Circuit Synthesiscited by 2
  5. 2025Towards Fast Coarse-graining and Equation Discovery with Foundation Inference Modelscited by 1
  6. 2025On Foundation Models for Temporal Point Processes to Accelerate Scientific Discoverycited by 0
  7. 2026EVIL: Evolving Interpretable Algorithms for Zero-Shot Inference on Event Sequences and Time Series with LLMscited by 0
  8. 2026Prior-Fitted Functional Flow: In-Context Generative Models for Pharmacokineticscited by 0
  9. 2026Amortized Variational Inference of Latent Intensities from Replicated Point Patternscited by 0
  10. 2026Foundation Models for Event Prediction Across Heterogeneous Event Logscited by 0