State space models (SSM) have recently been shown to be very effective as a deep learning
layer as a promising alternative to sequence models such as RNNs, CNNs, or Transformers …

A central goal of sequence modeling is designing a single principled model that can
address sequence data across a range of modalities and tasks, particularly on long-range …

Linear time-invariant state space models (SSM) are a classical model from engineering and
statistics, that have recently been shown to be very promising in machine learning through …

Foundation models, now powering most of the exciting applications in deep learning, are
almost universally based on the Transformer architecture and its core attention module …

Recent advances in deep learning have mainly relied on Transformers due to their data
dependency and ability to learn at scale. The attention module in these architectures …

Models using structured state space sequence (S4) layers have achieved state-of-the-art
performance on long-range sequence modeling tasks. An S4 layer combines linear state …

The Mamba layer offers an efficient selective state space model (SSM) that is highly effective
in modeling multiple domains including NLP, long-range sequences processing, and …

Transformers have surpassed RNNs in popularity due to their superior abilities in parallel
training and long-term dependency modeling. Recently, there has been a renewed interest …

State space models (SSMs) have shown impressive results on tasks that require modeling
long-range dependencies and efficiently scale to long sequences owing to their …

Deep state-space models (DSSMs) enable temporal predictions by learning the underlying
dynamics of observed sequence data. They are often trained by maximising the evidence …