Venturing into Uncharted Waters: The Navigation Compass from Transformer to Mamba
This is an incremental survey for researchers in natural language processing and related fields, summarizing existing work without introducing new methods.
This survey paper tackles the challenge of comparing and integrating the Transformer and Mamba architectures in deep learning, providing a comprehensive overview of Mamba's mechanisms, improvements, and potential as a substitute or complement to Transformers.
Transformer, a deep neural network architecture, has long dominated the field of natural language processing and beyond. Nevertheless, the recent introduction of Mamba challenges its supremacy, sparks considerable interest among researchers, and gives rise to a series of Mamba-based models that have exhibited notable potential. This survey paper orchestrates a comprehensive discussion, diving into essential research dimensions, covering: (i) the functioning of the Mamba mechanism and its foundation on the principles of structured state space models; (ii) the proposed improvements and the integration of Mamba with various networks, exploring its potential as a substitute for Transformers; (iii) the combination of Transformers and Mamba to compensate for each other's shortcomings. We have also made efforts to interpret Mamba and Transformer in the framework of kernel functions, allowing for a comparison of their mathematical nature within a unified context. Our paper encompasses the vast majority of improvements related to Mamba to date.