state space models
Mathematical models that represent systems in terms of their states and the transitions between them. They are widely used in control theory and reinforcement learning to model the dynamics of environments.
- Achilles' Heel of Mamba: Essential difficulties of the Mamba architecture demonstrated by synthetic data
- BeyondMix: Leveraging Structural Priors and Long-Range Dependencies for Domain-Invariant LiDAR Segmentation
- Block-Biased Mamba for Long-Range Sequence Processing
- Bridging Expressivity and Scalability with Adaptive Unitary SSMs
- DAMamba: Vision State Space Model with Dynamic Adaptive Scan
- Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation
- DyG-Mamba: Continuous State Space Modeling on Dynamic Graphs
- EDELINE: Enhancing Memory in Diffusion-based World Models via Linear-Time Sequence Modeling
- Efficient Hybrid Language Model Compression through Group-Aware SSM Pruning
- Hankel Singular Value Regularization for Highly Compressible State Space Models
- Linear Attention for Efficient Bidirectional Sequence Modeling
- Metric Automata Theory: A Unifying Theory of RNNs
- PASS: Path-selective State Space Model for Event-based Recognition
- Routing Mamba: Scaling State Space Models with Mixture-of-Experts Projection
- Safe-Sora: Safe Text-to-Video Generation via Graphical Watermarking
- State Space Prompting via Gathering and Spreading Spatio-Temporal Information for Video Understanding
- TRUST: Test-Time Refinement using Uncertainty-Guided SSM Traverses
- Uncovering the Spectral Bias in Diagonal State Space Models
- Zebra-Llama: Towards Extremely Efficient Hybrid Models
- ZigzagPointMamba: Spatial-Semantic Mamba for Point Cloud Understanding