2 papers
cs.LG2026
TIDES: Implicit Time-Awareness in Selective State Space Models
Taylan Soydan, Miguel A. Bessa, Dirk Mohr +1
Selective state space models (SSMs), such as Mamba, achieve strong per-token expressivity by making the time discretization step $\TildeÎ$ a learned function of the input. However…
cs.LG2024
S7: Selective and Simplified State Space Layers for Sequence Modeling
Taylan Soydan, Nikola ZubiÄ, Nico Messikommer +2
A central challenge in sequence modeling is efficiently handling tasks with extended contexts. While recent state-space models (SSMs) have made significant progress in this area, t…