arXiv Machine Learning June 16, 2026 By Yahya Aalaila, Sumantrak Mukherjee, Gerrit Gro{\ss}mann, Sebastian Vollmer

HawkesNest: A Multi-Axis Synthetic Benchmark for Spatiotemporal Pattern Complexity

Read the original on arXiv Machine Learning →

arXiv:2606. 16863v1 Announce Type: new Abstract: Evaluation of spatiotemporal point process (STPP) models relies heavily on opaque real-world datasets, where latent generative structure is unknown and model failures are difficult to attribute.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

benchmarks

arXiv Machine Learning

Jul 2

Seahorse: A Unified Benchmarking Framework for Spatiotemporal Event Modeling

arXiv:2607. 01022v1 Announce Type: new Abstract: Spatiotemporal point processes (STPPs) model event data in continuous time and space, with applications in mobility, epidemiology, and public safety.

By Yahya Aalaila, Gerrit Gro{\ss}mann, Sebastian Vollmer

benchmarks safety

arXiv Machine Learning

Jul 13

Kronecker-Structured Nonparametric Spatiotemporal Point Processes

arXiv:2603. 23746v2 Announce Type: replace Abstract: Events in spatiotemporal domains arise in numerous real-world applications, where uncovering event relationships and enabling accurate prediction are central challenges.

By Zhitong Xu, Qiwei Yuan, Yinghao Chen, Yan Sun, Bin Shen, Shandian Zhe

arXiv Machine Learning

Aug 4

A Semiparametric Discrete Hawkes Model with a Collapsed Gaussian-Process Prior

arXiv:2509. 21996v3 Announce Type: replace-cross Abstract: Hawkes processes are used in settings where past events increase the likelihood of future events occurring, resulting in a natural clustering structure.

By Trinnhallen Brisley, Gordon Ross, Daniel Paulin

arXiv Machine Learning

Jul 17

GAttNHP: Group Attention Neural Hawkes Process for Extrapolation Reasoning in Temporal Knowledge Graphs

arXiv:2607. 14733v1 Announce Type: new Abstract: Temporal Knowledge Graphs (TKGs) record how facts evolve over time, but forecasting future events on a TKG remains difficult for three reasons: (i) long-range temporal dependencies are hard to encode; (ii) events on different chains mutually excite or inhibit one another in ways that snapshot-level models cannot express; and (iii) inter-arrival times are heavy-tailed and statistically sparse, so deterministic time predictors are unreliable.

By Xiangni Tian, Kaixian Yu, Runpeng Dai, Niansheng Tang, Hongtu Zhu

benchmarks

arXiv Machine Learning

Jun 9

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

arXiv:2509. 24762v3 Announce Type: replace Abstract: 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.

By David Berghaus, Patrick Seifner, Kostadin Cvejoski, C\'esar Ojeda, Rams\'es J. S\'anchez

llms benchmarks

arXiv AI

Jul 2

Aionoscope: Debugging Latent-State Accessibility in Time-Series Representations

arXiv:2607. 00956v1 Announce Type: cross Abstract: Time-series models are often evaluated by what they can forecast or classify, but those scores do not show whether their representations preserve the process state a user may want to inspect: event timing, phase, amplitude, frequency, or regime variables.

By Alexander Chemeris, Ming Jin, Randall Balestriero

Related stories

Seahorse: A Unified Benchmarking Framework for Spatiotemporal Event Modeling

Kronecker-Structured Nonparametric Spatiotemporal Point Processes

A Semiparametric Discrete Hawkes Model with a Collapsed Gaussian-Process Prior

GAttNHP: Group Attention Neural Hawkes Process for Extrapolation Reasoning in Temporal Knowledge Graphs

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

Aionoscope: Debugging Latent-State Accessibility in Time-Series Representations