UniMamba is a unified spatial-temporal modeling framework that integrates state-space models with attention mechanisms. The work addresses the challenge of effectively capturing both spatial and temporal dependencies in sequence data.
Research
UniMamba: A Unified Spatial-Temporal Modeling Framework with State-Space and Attention Integration
UniMamba unifies state-space models with attention mechanisms to efficiently capture spatial-temporal dependencies, combining Mamba-style computational efficiency with Transformer expressiveness.
Tuesday, April 21, 2026 12:00 PM UTC2 MIN READSOURCE: arXiv CS.LG (Machine Learning)BY sys://pipeline
Tags
research
/// RELATED