相关论文: MambaLRP: Explaining Selective State Space Sequenc…

State space models (SSMs), such as Mamba, have emerged as an efficient alternative to transformers for long-context sequence modeling. However, despite their growing adoption, SSMs lack the interpretability tools that have been crucial for…

Human activity recognition (HAR) from inertial sensors is essential for ubiquitous computing, mobile health, and ambient intelligence. Conventional deep models such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs),…

Mamba state-space models (SSMs) have recently outperformed state-of-the-art (SOTA) Transformer large language models (LLMs) in various tasks and been widely adapted. However, a major concern for stable learning in recurrent-based deep…

State-space models (SSMs) have recently emerged as a compelling alternative to Transformers for sequence modeling tasks. This paper presents a theoretical generalization analysis of selective SSMs, the core architectural component behind…

Transformer-based large language models (LLMs) are increasingly being adopted in networking research to address domain-specific challenges. However, their quadratic time complexity and substantial model sizes often result in significant…

Large Language Models (LLMs) have demonstrated strong semantic reasoning across multimodal domains. However, their integration with graph-based models of brain connectivity remains limited. In addition, most existing fMRI analysis methods…

Transformer-based models have become increasingly popular and have impacted speech-processing research owing to their exceptional performance in sequence modeling. Recently, a promising model architecture, Mamba, has emerged as a potential…

The goal of style transfer is, given a content image and a style source, generating a new image preserving the content but with the artistic representation of the style source. Most of the state-of-the-art architectures use transformers or…

This study explores replacing Transformers in Visual Language Models (VLMs) with Mamba, a recent structured state space model (SSM) that demonstrates promising performance in sequence modeling. We test models up to 3B parameters under…

Deep learning models like Convolutional Neural Networks and transformers have shown impressive capabilities in speech verification, gaining considerable attention in the research community. However, CNN-based approaches struggle with…

The accelerated MRI reconstruction poses a challenging ill-posed inverse problem due to the significant undersampling in k-space. Deep neural networks, such as CNNs and ViTs, have shown substantial performance improvements for this task…

Recently, state space models have exhibited strong global modeling capabilities and linear computational complexity in contrast to transformers. This research focuses on applying such architecture to more efficiently and effectively model…

Log parsing is a critical standard operating procedure in software systems, enabling monitoring, anomaly detection, and failure diagnosis. However, automated log parsing remains challenging due to heterogeneous log formats, distribution…

The rapid development of large language and vision models (LLVMs) has been driven by advances in visual instruction tuning. Recently, open-source LLVMs have curated high-quality visual instruction tuning datasets and utilized additional…

Reinforcement learning (RL) has seen significant advancements through the application of various neural network architectures. In this study, we systematically investigate the performance of several neural networks in RL tasks, including…

Efficiently modeling large 2D contexts is essential for various fields including Giga-Pixel Whole Slide Imaging (WSI) and remote sensing. Transformer-based models offer high parallelism but face challenges due to their quadratic complexity…

The recent surge in State Space Models (SSMs), particularly the emergence of Mamba, has established them as strong alternatives or complementary modules to Transformers across diverse domains. In this work, we aim to explore the potential…

Extractive summarization of long documents is bottlenecked by quadratic complexity, often forcing truncation and limiting deployment in resource-constrained settings. We introduce the first Mamba-Transformer hybrid for extractive…

Voice user interfaces (VUIs) have facilitated the efficient interactions between humans and machines through spoken commands. Since real-word acoustic scenes are complex, speech enhancement plays a critical role for robust VUI. Transformer…

In this study, we focus on video captioning by fully open multimodal large language models (MLLMs). The comprehension of visual sequences is challenging because of their intricate temporal dependencies and substantial sequence length. The…