Technologies on Effectiveness and Efficiency: A Survey of State Spaces Models
By: Xingtai Lv , Youbang Sun , Kaiyan Zhang and more
Potential Business Impact:
Helps computers learn faster from long information.
State Space Models (SSMs) have emerged as a promising alternative to the popular transformer-based models and have been increasingly gaining attention. Compared to transformers, SSMs excel at tasks with sequential data or longer contexts, demonstrating comparable performances with significant efficiency gains. In this survey, we provide a coherent and systematic overview for SSMs, including their theoretical motivations, mathematical formulations, comparison with existing model classes, and various applications. We divide the SSM series into three main sections, providing a detailed introduction to the original SSM, the structured SSM represented by S4, and the selective SSM typified by Mamba. We put an emphasis on technicality, and highlight the various key techniques introduced to address the effectiveness and efficiency of SSMs. We hope this manuscript serves as an introduction for researchers to explore the theoretical foundations of SSMs.
Similar Papers
From S4 to Mamba: A Comprehensive Survey on Structured State Space Models
Machine Learning (CS)
Makes computers understand long stories faster.
CodeSSM: Towards State Space Models for Code Understanding
Software Engineering
Helps computers understand code better, faster, cheaper.
Deep Learning-based Approaches for State Space Models: A Selective Review
Machine Learning (Stat)
Helps computers understand changing information better.