Related papers: SpecMamba: Accelerating Mamba Inference on FPGA wi…

Vision Mamba (ViM) models offer a compelling efficiency advantage over Transformers by leveraging the linear complexity of State Space Models (SSMs), yet efficiently deploying them on FPGAs remains challenging. Linear layers struggle with…

State-Space Models (SSMs) have emerged as efficient alternatives to transformers for sequential data tasks, offering linear or near-linear scalability with sequence length, making them ideal for long-sequence applications in NLP, vision,…

With the evolution of large language models, traditional Transformer models become computationally demanding for lengthy sequences due to the quadratic growth in computation with respect to the sequence length. Mamba, emerging as a…

Denoising is a crucial preprocessing step for hyperspectral images (HSIs) due to noise arising from intra-imaging mechanisms and environmental factors. Long-range spatial-spectral correlation modeling is beneficial for HSI denoising but…

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…

Mamba-based State Space Models (SSM) have emerged as a promising alternative to the ubiquitous transformers. Despite the expressive power of transformers, the quadratic complexity of computing attention is a major impediment to scaling…

Recent State Space Models (SSM), especially Mamba, have demonstrated impressive performance in visual modeling and possess superior model efficiency. However, the application of Mamba to visual tasks suffers inferior performance due to…

Speculative decoding is a standard method for accelerating the inference speed of large language models. However, scaling it for production environments poses several engineering challenges, including efficiently implementing different…

Large Language Models (LLMs) have achieved remarkable performance across tasks but remain energy-intensive due to dense matrix operations. Spiking neural networks (SNNs) improve energy efficiency by replacing dense matrix multiplications…

In recent years, Transformers have become the de-facto architecture for long-term sequence forecasting (LTSF), but faces challenges such as quadratic complexity and permutation invariant bias. A recent model, Mamba, based on selective state…

State-space models (SSMs) have recently shown promise in capturing long-range dependencies with subquadratic computational complexity, making them attractive for various applications. However, purely SSM-based models face critical…

Speculative decoding and quantization effectively accelerate memory-bound inference of large language models. Speculative decoding mitigates the memory bandwidth bottleneck by verifying multiple tokens within a single forward pass, which…

Prior efforts in light-weight model development mainly centered on CNN and Transformer-based designs yet faced persistent challenges. CNNs adept at local feature extraction compromise resolution while Transformers offer global reach but…

Speculative decoding accelerates LLM inference by using a draft model to look ahead, but gains are capped by the cost of autoregressive draft generation: increasing draft size elevates acceptance rates but introduces additional latency…

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…

Although Mamba models significantly improve hyperspectral image (HSI) classification, one critical challenge is the difficulty in building the sequence of Mamba tokens efficiently. This paper presents a Sparse Deformable Mamba (SDMamba)…

In various domains, Sequential Recommender Systems (SRS) have become essential due to their superior capability to discern intricate user preferences. Typically, SRS utilize transformer-based architectures to forecast the subsequent item…

Spatial-Spectral Mamba (SSM) improves computational efficiency and captures long-range dependencies, addressing Transformer limitations. However, traditional Mamba models overlook rich spectral information in HSIs and struggle with high…

Image restoration requires simultaneously preserving fine-grained local structures and maintaining long-range spatial coherence. While convolutional networks struggle with limited receptive fields, and Transformers incur quadratic…

The field of neuromorphic computing has gained significant attention in recent years, aiming to bridge the gap between the efficiency of biological neural networks and the performance of artificial intelligence systems. This paper…