arXiv Machine Learning July 9, 2026 By Niels Cariou-Kotlarek, Vasileios Lampos

From Jumps to Signatures: a Generative Method for Temporal Point Processes

Read the original on arXiv Machine Learning →

arXiv:2607. 06652v1 Announce Type: new Abstract: Rough path signatures are a universal feature map for continuous paths and, via the expected signature, characterise path distributions.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

4d ago

TimeTok: Granularity-Controllable Time-Series Generation via Hierarchical Tokenization

arXiv:2605.01418v2 Announce Type: replace Abstract: Time-series data are inherently multiscale, spanning diverse temporal granularities from coarse trends to fine-scale dynamics. However, existing ti...

By Seokhyun Lee, Jaeho Kim, Changjun Oh, Mihaela van der Schaar, Changhee Lee

nlp benchmarks

arXiv Machine Learning

Sep 10

Online Signature Verification Using Augmented Path Signature and T-Mamba

The paper introduces a new online signature verification framework that combines the augmented path signature (APS) descriptor with a T-Mamba model. APS applies time and basepoint augmentations followed by sliding-window path signatures, capturing geometric structures and nonlinear inter-channel interactions. T-Mamba, a hybrid of two temporal convolutional network blocks and a time-scanning Mamba, learns both local temporal patterns and global long-range dependencies, achieving state‑of‑the‑art equal error rates on three public benchmark datasets.

By Ruiling Li, Danyu Yang

benchmarks

arXiv Machine Learning

Aug 4

Using Lower-Bound Representations for Trajectory Similarity Learning

arXiv:2608. 01039v1 Announce Type: cross Abstract: Trajectory similarity learning is fundamental to efficient trajectory retrieval under complex distance measures.

By Liwei Deng, Haotian Meng, Yupu Zhang, Yan Zhao, Torben Bach Pedersen, Kai Zheng, Christian S. Jensen

rag 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

Jun 4

Generating Financial Time Series by Matching Random Convolutional Features

arXiv:2606. 05138v1 Announce Type: new Abstract: Generating realistic financial time series is challenging as training data is often limited to a single historical path.

By Konrad J. Mueller, Nikita Zozoulenko, Ben Wood, Thomas Cass, Lukas Gonon

diffusion safety

arXiv AI

Aug 14

LOB-ID: Evaluating Synthetic Market Data by Inception Distances

arXiv:2608. 13082v1 Announce Type: cross Abstract: Generative models of limit orderbook (LOB) data have advanced rapidly, but their evaluation often focuses on stylised facts and selected market statistics.

By Andreea Bacalum, Zhuohan Wang, Ollie Olby, Martin Garaj, Namid Stillman

rag

One email a morning, machine-written

Related stories

TimeTok: Granularity-Controllable Time-Series Generation via Hierarchical Tokenization

Online Signature Verification Using Augmented Path Signature and T-Mamba

Using Lower-Bound Representations for Trajectory Similarity Learning

Seahorse: A Unified Benchmarking Framework for Spatiotemporal Event Modeling

Generating Financial Time Series by Matching Random Convolutional Features

LOB-ID: Evaluating Synthetic Market Data by Inception Distances