相关论文: MambaTS: Improved Selective State Space Models for…

State Space Models (SSMs), particularly Mamba, have shown potential in long-term time series forecasting. However, existing Mamba-based architectures often struggle with datasets characterized by non-stationary patterns. A key observation…

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…

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…

Multivariate time series forecasting is fundamental to numerous domains such as energy, finance, and environmental monitoring, where complex temporal dependencies and cross-variable interactions pose enduring challenges. Existing…

Recent advances in deep learning have mainly relied on Transformers due to their data dependency and ability to learn at scale. The attention module in these architectures, however, exhibits quadratic time and space in input size, limiting…

Long-term time-series forecasting remains challenging due to the difficulty in capturing long-term dependencies, achieving linear scalability, and maintaining computational efficiency. We introduce TimeMachine, an innovative model that…

Sequential recommendation systems have become a cornerstone of personalized services, adept at modeling the temporal evolution of user preferences by capturing dynamic interaction sequences. Existing approaches predominantly rely on…

Transformers dominate NLP and IR; but their inference inefficiencies and challenges in extrapolating to longer contexts have sparked interest in alternative model architectures. Among these, state space models (SSMs) like Mamba offer…

Speculative decoding has emerged as a promising approach to accelerating large language model (LLM) generation using a fast drafter while maintaining alignment with the target model's distribution. However, existing approaches face a…

Transformers have been the most successful architecture for various speech modeling tasks, including speech separation. However, the self-attention mechanism in transformers with quadratic complexity is inefficient in computation and…

Recently, a novel visual state space (VSS) model, referred to as Mamba, has demonstrated significant progress in modeling long sequences with linear complexity, comparable to Transformer models, thereby enhancing its adaptability for…

Understanding the robustness of deep learning models for multivariate long-term time series forecasting (M-LTSF) remains challenging, as evaluations typically rely on real-world datasets with unknown noise properties. We propose a…

State space models (SSMs) have emerged as an efficient alternative to Transformer models for language modeling, offering linear computational complexity and constant memory usage as context length increases. However, despite their…

Mamba, a special case of the State Space Model, is gaining popularity as an alternative to template-based deep learning approaches in medical image analysis. While transformers are powerful architectures, they have drawbacks, including…

The realm of Mamba for vision has been advanced in recent years to strike for the alternatives of Vision Transformers (ViTs) that suffer from the quadratic complexity. While the recurrent scanning mechanism of Mamba offers computational…

Current automatic speech recognition systems struggle with modeling long speech sequences due to high quadratic complexity of Transformer-based models. Selective state space models such as Mamba has performed well on long-sequence modeling…

Structured state space models (SSMs) have recently emerged as a promising foundation for sequence modeling, with Mamba-based architectures demonstrating strong performance through input-dependent state transitions, albeit at considerable…

Recent advancements in state space models, notably Mamba, have demonstrated significant progress in modeling long sequences for tasks like language understanding. Yet, their application in vision tasks has not markedly surpassed the…

The problem of imputing multivariate time series spans a wide range of fields, from clinical healthcare to multi-sensor systems. Initially, Recurrent Neural Networks (RNNs) were employed for this task; however, their error accumulation…

Recently, deep learning models have achieved excellent performance in hyperspectral image (HSI) classification. Among the many deep models, Transformer has gradually attracted interest for its excellence in modeling the long-range…