Related papers: MambaIC: State Space Models for High-Performance L…

Whole-slide images (WSIs) are an important data modality in computational pathology, yet their gigapixel resolution and lack of fine-grained annotations challenge conventional deep learning models. Multiple instance learning (MIL) offers a…

Lightweight and efficient neural network models for deep joint source-channel coding (JSCC) are crucial for semantic communications. In this paper, we propose a novel JSCC architecture, named MambaJSCC, that achieves state-of-the-art…

Large Vision-Language Models (LVLMs) have demonstrated remarkable performance across a wide range of multimodal tasks. However, fine-tuning these models for domain-specific applications remains a computationally intensive challenge. This…

Incorporating semantic information into the codecs during image compression can significantly reduce the repetitive computation of fundamental semantic analysis (such as object recognition) in client-side applications. The same practice…

State Space Models (SSMs)-most notably RNNs-have historically played a central role in sequential modeling. Although attention mechanisms such as Transformers have since dominated due to their ability to model global context, their…

In the field of medical image segmentation, models based on both CNN and Transformer have been thoroughly investigated. However, CNNs have limited modeling capabilities for long-range dependencies, making it challenging to exploit the…

Modern high-energy physics (HEP) experiments are increasingly challenged by the vast size and complexity of their datasets, particularly regarding large-scale point cloud processing and long sequences. In this study, to address these…

Recent event-based image reconstruction methods predominantly rely on Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) to process complementary event information. However, these architectures face fundamental limitations:…

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…

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…

Semantic segmentation is a fundamental task in computer vision with wide-ranging applications, including autonomous driving and robotics. While RGB-based methods have achieved strong performance with CNNs and Transformers, their…

High-resolution remotely sensed images pose a challenge for commonly used semantic segmentation methods such as Convolutional Neural Network (CNN) and Vision Transformer (ViT). CNN-based methods struggle with handling such high-resolution…

With the evolution of storage and communication protocols, ultra-low bitrate image compression has become a highly demanding topic. However, existing compression algorithms must sacrifice either consistency with the ground truth or…

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…

In recent years, Transformers-based models have made significant progress in the field of image restoration by leveraging their inherent ability to capture complex contextual features. Recently, Mamba models have made a splash in the field…

In an era of frequent extreme weather and global warming, obtaining precise, fine-grained near-surface weather forecasts is increasingly essential for human activities. Downscaling (DS), a crucial task in meteorological forecasting, enables…

Structured State Space Models (SSMs) have emerged as a transformative paradigm in sequence modeling, addressing critical limitations of Recurrent Neural Networks (RNNs) and Transformers, namely, vanishing gradients, sequential computation…

Probabilistic State Space Models (SSMs) are essential for Reinforcement Learning (RL) from high-dimensional, partial information as they provide concise representations for control. Yet, they lack the computational efficiency of their…

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…

Reconstructing degraded images is a critical task in image processing. Although CNN and Transformer-based models are prevalent in this field, they exhibit inherent limitations, such as inadequate long-range dependency modeling and high…