← Back to all news
arXiv Machine Learning By Taylan Soydan, Miguel A. Bessa, Dirk Mohr, Rui Barreira

TIDES: Implicit Time-Awareness in Selective State Space Models

Read the original on arXiv Machine Learning →

TIDES is a new selective state space model that keeps the learned step size equal to the physical time gap, enabling it to handle irregular timestamps while maintaining per‑token expressivity. By moving input dependence from the step size to the diagonal state matrix, TIDES combines the strengths of selective SSMs like Mamba and continuous‑time SSMs like S5. Experiments on a novel Fading Flash benchmark and large‑scale datasets show that TIDES outperforms or matches state‑of‑the‑art models on irregular time‑series tasks.

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.

Related stories

arXiv Statistics ML
Oct 2

Extending SSMs with the Exponentially Weighted Signature

arXiv:2603.19198v3 Announce Type: replace Abstract: We introduce the exponentially weighted signature (EWS), a continuous-time model that computes iterated integrals of a path, where each increment i...

By Alexandre Bloch, Benjamin Walker, Jo\"el Mouterde, Sam Morley, Samuel N. Cohen, Terry Lyons
More like this →
arXiv Machine Learning
Aug 14

A Simple State Space Model Excels at Multivariate Time Series Classification

arXiv:2605. 27406v2 Announce Type: replace Abstract: Structured state space models (SSMs) have recently emerged as a promising foundation for sequence modeling, with Mamba-based architectures demonstrating strong performance through input-dependent state transitions, albeit at considerable complexity.

By Hassan Saadatmand, Geoffrey I. Webb, Hamid Rezatofighi, Mahsa Salehi
benchmarks
More like this →
arXiv AI
Oct 27

EvoBench: An Evolving, Diagnostic Benchmark Framework for Environmental Modeling

EvoBench is a diagnostic benchmark framework designed to reveal where and when machine‑learning models for environmental variables fail, rather than relying on a single average accuracy score. It tracks model performance over time and across spatial extrapolation, highlighting issues such as non‑stationarity, poor performance at unmonitored sites, and under‑prediction of rare events like floods. In a case study on daily streamflow prediction across 9,000 U.S. basins, EvoBench shows that no model dominates all scenarios and that targeted fixes can mitigate identified weaknesses.

By Yiming Sun, Yuan Zhang, Qi Cheng, Yingda Fan, Runlong Yu, Yiqun Xie, Xiaowei Jia
benchmarks
More like this →
arXiv AI
Sep 30

Channel-Dependent State Space Model for Multivariate Time Series Forecasting

The paper introduces Chameleon, a channel‑dependent state space model for multivariate time series forecasting that allows data‑dependent, fine‑grained interactions across variables while maintaining linear scaling with the number of variables. By integrating selective state space models with a Kalman filter and adapting GatedDeltaNet as the backbone, Chameleon improves generalization and achieves lower MSE and MAE on strongly dependent ODE and PEMS datasets compared to both channel‑independent and prior channel‑dependent methods. Across 28 benchmark settings, it outperforms baselines in the majority of cases and demonstrates competitive training‑time and memory efficiency on Traffic and ETT datasets.

By Yu-Cheng Wu, Fan-Keng Sun, Li-Chun Lu, Duane S. Boning
benchmarks
More like this →