相关论文: On the Expressivity of Selective State-Space Layer…

Time series forecasting has made significant advances, including with Transformer-based models. The attention mechanism in Transformer effectively captures temporal dependencies by attending to all past inputs simultaneously. However, its…

Linear RNN architectures, like Mamba, can be competitive with Transformer models in language modeling while having advantageous deployment characteristics. Given the focus on training large-scale Transformer models, we consider the…

Long-short range time series forecasting is essential for predicting future trends and patterns over extended periods. While deep learning models such as Transformers have made significant strides in advancing time series forecasting, they…

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…

Graph Neural Networks based on the message-passing (MP) mechanism are a dominant approach for handling graph-structured data. However, they are inherently limited to modeling only pairwise interactions, making it difficult to explicitly…

For multivariate time series (MTS) tasks, previous state space models (SSMs) followed the modeling paradigm of Transformer-based methods. However, none of them explicitly model the complex dependencies of MTS: the Channel Dependency…

We introduce VideoMamba, a novel adaptation of the pure Mamba architecture, specifically designed for video recognition. Unlike transformers that rely on self-attention mechanisms leading to high computational costs by quadratic complexity,…

Balancing fine-grained local modeling with long-range dependency capture under computational constraints remains a central challenge in sequence modeling. While Transformers provide strong token mixing, they suffer from quadratic…

Recent years have witnessed significant advancements in light field image super-resolution (LFSR) owing to the progress of modern neural networks. However, these methods often face challenges in capturing long-range dependencies (CNN-based)…

We introduce LocoMamba, a vision-driven cross-modal DRL framework built on selective state-space models, specifically leveraging Mamba, that achieves near-linear-time sequence modeling, effectively captures long-range dependencies, and…

Long-range sequence processing poses a significant challenge for Transformers due to their quadratic complexity in input length. A promising alternative is Mamba, which demonstrates high performance and achieves Transformer-level…

Recurrent neural networks and Transformers have recently dominated most applications in hyperspectral (HS) imaging, owing to their capability to capture long-range dependencies from spectrum sequences. However, despite the success of these…

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…

The problem of Time-series Forecasting is generally addressed by recurrent, Transformer-based and the recently proposed Mamba-based architectures. However, existing architectures generally process their input at a single temporal scale,…

Transformers have become foundational for visual tasks such as object detection, semantic segmentation, and video understanding, but their quadratic complexity in attention mechanisms presents scalability challenges. To address these…

Training deep learning models for semantic occupancy prediction is challenging due to factors such as a large number of occupancy cells, severe occlusion, limited visual cues, complicated driving scenarios, etc. Recent methods often adopt…

Sequence models like Transformers and RNNs often overallocate attention to irrelevant context, leading to noisy intermediate representations. This degrades LLM capabilities by promoting hallucinations, weakening long-range and retrieval…

State Space Models (SSMs) such as Mamba have become a popular alternative to Transformer models, due to their reduced memory consumption and higher throughput at generation compared to their Attention-based counterparts. On the other hand,…

Recent research has shown that combining Mamba with Transformer architecture, which has selective state space and quadratic self-attention mechanism, outperforms using Mamba or Transformer architecture alone in language modeling tasks. The…

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…