相关论文: TransMamba: A Sequence-Level Hybrid Transformer-Ma…

Recent Multimodal Large Language Models (MLLMs) have achieved remarkable performance but face deployment challenges due to their quadratic computational complexity, growing Key-Value cache requirements, and reliance on separate vision…

Achieving both high accuracy and topological continuity in road segmentation from satellite imagery is a critical goal for applications ranging from urban planning to disaster response. State-of-the-art methods often rely on Vision…

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…

State-of-the-art transformer-based large multimodal models (LMMs) struggle to handle hour-long video inputs due to the quadratic complexity of the causal self-attention operations, leading to high computational costs during training and…

This work aims to investigate the use of a recently proposed, attention-free, scalable state-space model (SSM), Mamba, for the speech enhancement (SE) task. In particular, we employ Mamba to deploy different regression-based SE models…

Self-supervised video hashing (SSVH) is a practical task in video indexing and retrieval. Although Transformers are predominant in SSVH for their impressive temporal modeling capabilities, they often suffer from computational and memory…

Human-human interaction generation has garnered significant attention in motion synthesis due to its vital role in understanding humans as social beings. However, existing methods typically rely on transformer-based architectures, which…

Transformers have become the backbone of modern Large Language Models (LLMs); however, their inference overhead grows linearly with the sequence length, posing challenges for modeling long sequences. In light of this, Mamba has attracted…

Existing deraining Transformers employ self-attention mechanisms with fixed-range windows or along channel dimensions, limiting the exploitation of non-local receptive fields. In response to this issue, we introduce a novel dual-branch…

In the era of large-scale pre-trained models, effectively adapting general knowledge to specific affective computing tasks remains a challenge, particularly regarding computational efficiency and multimodal heterogeneity. While…

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…

Recent efforts on image restoration have focused on developing "all-in-one" models that can handle different degradation types and levels within single model. However, most of mainstream Transformer-based ones confronted with dilemma…

Recent advances in Vision Transformers (ViTs) and State Space Models (SSMs) have challenged the dominance of Convolutional Neural Networks (CNNs) in computer vision. ViTs excel at capturing global context, and SSMs like Mamba offer linear…

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…

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…

We propose ss-Mamba, a novel foundation model that enhances time series forecasting by integrating semantic-aware embeddings and adaptive spline-based temporal encoding within a selective state-space modeling framework. Building upon the…

Single-cell RNA sequencing (scRNA-seq) enables high-resolution analysis of cellular heterogeneity, but its complexity, which is marked by high dimensionality, sparsity, and batch effects, which poses major computational challenges.…

In recent years, visually-rich document understanding has attracted increasing attention. Transformer-based pre-trained models have become the mainstream approach, yielding significant performance gains in this field. However, the…

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…

In multivariate time series forecasting (MTSF), existing strategies for processing sequences are typically categorized as channel-independent and channel-mixing. The former treats all temporal information of each variable as a token,…