TIDES: Implicit Time-Awareness in Selective State Space Models

arXiv:2605.09742 · cs.LG, cs.AI · Submitted 2026-05-10 · Read on arXiv

cs.LG, cs.AI

Submitted: 2026-05-10

Updated: 2026-10-14

Code: https://github.com/TaylanSoydan/TIDES

Terminology

• Benchmark — 3× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• State Space Models (SSMs) — 1× in this paper · explained in 4 episodes

Sources

• Multi-Time Attention Networks for Irregularly Sampled Time Series
• Simplified State Space Layers for Sequence Modeling
• Mamba: Linear-Time Sequence Modeling with Selective State Spaces
• Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality
• StableSSM: Alleviating the Curse of Memory in State-space Models through Stable Reparameterization
• Rough Transformers for Continuous and Efficient Time-Series Modelling
• Log Neural Controlled Differential Equations: The Lie Brackets Make a Difference
• The UEA multivariate time series classification archive, 2018
• Physiome-ODE: A Benchmark for Irregularly Sampled Multivariate Time Series Forecasting Based on Biological ODEs
• Pixel-wise Agricultural Image Time Series Classification: Comparisons and a Deformable Prototype-based Approach
• Mind the Gap: Bridging Prior Shift in Realistic Few-Shot Crop-Type Classification
• Scalable Event-by-event Processing of Neuromorphic Sensory Signals With Deep State-Space Models
• Rethinking Irregular Time Series Forecasting: A Simple yet Effective Baseline
• Efficiently Modeling Long Sequences with Structured State Spaces
• Gated Linear Attention Transformers with Hardware-Efficient Training
• A Simple State Space Model Excels at Multivariate Time Series Classification

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks