Related papers: Mechanistic evaluation of Transformers and state s…

Structured state-space models (SSMs) such as S4, stemming from the seminal work of Gu et al., are gaining popularity as effective approaches for modeling sequential data. Deep SSMs demonstrate outstanding performance across a diverse set of…

Structured State Space Models (SSMs) have emerged as a transformative paradigm in sequence modeling, addressing critical limitations of Recurrent Neural Networks (RNNs) and Transformers, namely, vanishing gradients, sequential computation…

The Mamba layer offers an efficient selective state space model (SSM) that is highly effective in modeling multiple domains, including NLP, long-range sequence processing, and computer vision. Selective SSMs are viewed as dual models, in…

The quadratic complexity of the attention mechanism in Transformer models has motivated the development of alternative architectures with sub-quadratic scaling, such as state-space models. Among these, Mamba has emerged as a leading…

Sequence modeling is a crucial area across various domains, including Natural Language Processing (NLP), speech recognition, time series forecasting, music generation, and bioinformatics. Recurrent Neural Networks (RNNs) and Long Short Term…

The recent empirical success of Mamba and other selective state space models (SSMs) has renewed interest in non-attention architectures for sequence modeling, yet their theoretical foundations remain underexplored. We present a first-step…

We propose Samba ASR,the first state of the art Automatic Speech Recognition(ASR)model leveraging the novel Mamba architecture as both encoder and decoder,built on the foundation of state space models(SSMs).Unlike transformerbased ASR…

Transformers have rapidly become the preferred choice for audio classification, surpassing methods based on CNNs. However, Audio Spectrogram Transformers (ASTs) exhibit quadratic scaling due to self-attention. The removal of this quadratic…

State Space Models (SSMs) have recently enjoyed a rise to prominence in the field of deep learning for sequence modeling, especially as an alternative to Transformers. Their success stems from avoiding two well-known drawbacks of…

State space models (SSMs) with selection mechanisms and hardware-aware architectures, namely Mamba, have recently demonstrated significant promise in long-sequence modeling. Since the self-attention mechanism in transformers has quadratic…

Recent advancements in recurrent architectures, such as Mamba and RWKV, have showcased strong language capabilities. Unlike transformer-based models, these architectures encode all contextual information into a fixed-size state, leading to…

In recent years, Transformers have become the de-facto architecture for sequence modeling on text and a variety of multi-dimensional data, such as images and video. However, the use of self-attention layers in a Transformer incurs…

Selective State-Space Models (SSMs) such as Mamba have emerged as an alternative architecture to self-attention based transformers in sequence modeling tasks. Recent works have demonstrated the use of transformers in some filtering and…

Large language models (LLMs) have advanced significantly due to the attention mechanism, but their quadratic complexity and linear memory demands limit their performance on long-context tasks. Recently, researchers introduced Mamba, an…

In recent years, there has been a growing interest in integrating linear state-space models (SSM) in deep neural network architectures of foundation models. This is exemplified by the recent success of Mamba, showing better performance than…

State Space Model (SSM) is a mathematical model used to describe and analyze the behavior of dynamic systems. This model has witnessed numerous applications in several fields, including control theory, signal processing, economics and…

Transformer structure has achieved great success in multiple applied machine learning communities, such as natural language processing (NLP), computer vision (CV) and information retrieval (IR). Transformer architecture's core mechanism\,…

In the post-deep learning era, the Transformer architecture has demonstrated its powerful performance across pre-trained big models and various downstream tasks. However, the enormous computational demands of this architecture have deterred…

Attention mechanisms have been widely used to capture long-range dependencies among nodes in Graph Transformers. Bottlenecked by the quadratic computational cost, attention mechanisms fail to scale in large graphs. Recent improvements in…

Multilingual automatic speech recognition (ASR) remains a challenging task, especially when balancing performance across high- and low-resource languages. Recent advances in sequence modeling suggest that architectures beyond Transformers…