state-space models
Mathematical models that describe a system using a set of input, output, and state variables, capturing the dynamics of the system. In AI, they are used for modeling temporal processes and in control systems.
- Fixed-Point RNNs: Interpolating from Diagonal to Dense
- Generalization Error Analysis for Selective State-Space Models Through the Lens of Attention
- Improving Bilinear RNN with Closed-loop Control
- Inference of Whole Brain Electrophysiological Networks Through Multimodal Integration of Simultaneous Scalp and Intracranial EEG
- L$^2$M: Mutual Information Scaling Law for Long-Context Language Modeling
- Mamba Modulation: On the Length Generalization of Mamba Models
- Overcoming Long Context Limitations of State Space Models via Context Dependent Sparse Attention
- Physics of Language Models: Part 4.1, Architecture Design and the Magic of Canon Layers
- Polyline Path Masked Attention for Vision Transformer
- STree: Speculative Tree Decoding for Hybrid State Space Models
- Structured Sparse Transition Matrices to Enable State Tracking in State-Space Models
- TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learning
- Trained Mamba Emulates Online Gradient Descent in In-Context Linear Regression
- WaLRUS: Wavelets for Long range Representation Using State Space Methods