跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-05AI 評分41

TIDES:選擇性狀態空間模型中的隱式時間感知

TIDES: Implicit Time-Awareness in Selective State Space Models

AI 導讀

TIDES 將輸入依賴性由步長移至對角狀態矩陣,使選擇性狀態空間模型原生處理不規則時間戳,同時保留逐 token 表達能力。在 UEA 時間序列分類及 Physiome ODE 回歸基準上,TIDES 取得最佳平均排名,並在 8 個原生不規則資料集中的 6 個匹配或超越參考基線模型。

正文

Published on Oct 5

Authors:

,

,

Abstract

Selective state space models (SSMs), such as Mamba, achieve strong per-token expressivity by making the time discretization step TildeΔ a learned function of the input. However, in doing so, TildeΔ no longer equals the physical time gap Δ between consecutive observations, limiting the ability of these models to handle irregular time series. Continuous time SSMs, such as S5, keep TildeΔequivΔ and therefore handle irregular timestamps natively, but their dynamics remain linear time invariant (LTI), limiting per token expressivity. We propose TIDES, a selective SSM variant that reconciles selective and continuous architectures by moving input dependence off the step size and onto the diagonal state matrix. As a result, TildeΔequivΔ as in S5, allowing the model to handle irregular timestamps natively without sacrificing the per-token expressivity that makes selective SSMs effective. We show this on a novel Fading Flash experimental benchmark, a compact controlled diagnostic for sequence models that jointly tests input dependence and extrapolation to out-of-distribution Δ values, and isolates the distinct failure modes of current state-of-the-art architectures that TIDES avoids by construction. On large-scale benchmarks, TIDES sets the new best average rank on UEA time series classification and the Physiome ODE regression benchmark, and matches or exceeds the reference baseline model on 6 of 8 natively irregular datasets from astronomy, agriculture, neuromorphic sensing, and climate events. Code available at: https://github.com/TaylanSoydan/TIDES.

View arXiv page View PDF GitHub 1 Add to collection

Get this paper in your agent:

hf papers read 2605.09742

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2605.09742 in a model README.md to link it from this page.

Datasets citing this paper 1

Taylantay/fading-flash

Viewer •

Updated about 2 hours ago

•

125k

•

1

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2605.09742 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co