Related papers: MambaScope: Coarse-to-Fine Scoping for Efficient V…

Vision Transformers have demonstrated exceptional performance across various computer vision tasks, yet their quadratic computational complexity concerning token length remains a significant challenge. To address this, token reduction…

Medical image segmentation plays an important role in computer-aided diagnosis. Traditional convolution-based U-shape segmentation architectures are usually limited by the local receptive field. Existing vision transformers have been widely…

Spiking Transformers have shown strong potential for long-range visual modeling through spike-driven self-attention. However, their quadratic token interactions remain fundamentally misaligned with the sparse and event-driven nature of…

We present MambaCSR, a simple but effective framework based on Mamba for the challenging compressed image super-resolution (CSR) task. Particularly, the scanning strategies of Mamba are crucial for effective contextual knowledge modeling in…

While Multimodal Large Language Models (MLLMs) offer strong perception and reasoning capabilities for image-text input, Visual Question Answering (VQA) focusing on small image details still remains a challenge. Although visual cropping…

A fundamental objective in robot manipulation is to enable models to comprehend visual scenes and execute actions. Although existing Vision-Language-Action (VLA) models for robots can handle a range of basic tasks, they still face…

Low-light image enhancement remains a persistent challenge in computer vision, where state-of-the-art models are often hampered by hardware constraints and computational inefficiency, particularly at high resolutions. While foundational…

Vision encoders typically generate a large number of visual tokens, providing information-rich representations but significantly increasing computational demands. This raises the question of whether all generated tokens are equally valuable…

Sufficient cross-task interaction is crucial for success in multi-task dense prediction. However, sufficient interaction often results in high computational complexity, forcing existing methods to face the trade-off between interaction…

Token-free language models learn directly from raw bytes and remove the inductive bias of subword tokenization. Operating on bytes, however, results in significantly longer sequences. In this setting, standard autoregressive Transformers…

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…

Cloud detection in remote sensing imagery is a fundamental, critical, and highly challenging problem. Existing deep learning-based cloud detection methods generally formulate it as a single-stage pixel-wise binary segmentation task with one…

Pan-sharpening involves integrating information from low-resolution multi-spectral and high-resolution panchromatic images to generate high-resolution multi-spectral counterparts. While recent advancements in the state space model,…

Network traffic classification is a crucial research area aiming to enhance service quality, streamline network management, and bolster cybersecurity. To address the growing complexity of transmission encryption techniques, various machine…

State Space Models (SSMs), particularly the Mamba architecture, have recently emerged as powerful alternatives to Transformers for sequence modeling, offering linear computational complexity while achieving competitive performance. Yet,…

CNN- and Transformer-based architectures have achieved strong performance in medical image segmentation, but CNNs are limited in modeling long-range dependencies, while Transformers often suffer from quadratic computational and memory…

Medical image segmentation has traditionally relied on convolutional neural networks (CNNs) and Transformer-based models. CNNs, however, are constrained by limited receptive fields, while Transformers face scalability challenges due to…

Sequential recommendation systems aim to predict users' next preferences based on their interaction histories, but existing approaches face critical limitations in efficiency and multi-scale pattern recognition. While Transformer-based…

Table images present unique challenges for effective and efficient understanding due to the need for question-specific focus and the presence of redundant background regions. Existing Multimodal Large Language Model (MLLM) approaches often…

Point cloud segmentation is an important topic in 3D understanding that has traditionally has been tackled using either the CNN or Transformer. Recently, Mamba has emerged as a promising alternative, offering efficient long-range contextual…