Related papers: SAMBA: Toward a Long-Context EEG Foundation Model …

Electroencephalography (EEG) foundation models hold significant promise for universal Brain-Computer Interfaces (BCIs). However, existing approaches often rely on end-to-end fine-tuning and exhibit limited efficacy under frozen-probing…

Selective state-space models excel at long-sequence modeling, but their capacity for language representation -- in complex hierarchical reasoning -- remains underexplored. Most large language models rely on \textit{flat} Euclidean…

Electroencephalography (EEG), with its broad range of applications, necessitates models that can generalize effectively across various tasks and datasets. Large EEG Models (LEMs) address this by pretraining encoder-centric architectures on…

Self-supervised learning has emerged as a highly effective approach in the fields of natural language processing and computer vision. It is also applicable to brain signals such as electroencephalography (EEG) data, given the abundance of…

Transformer-based embedding models suffer from quadratic computational and linear memory complexity, limiting their utility for long sequences. We propose recurrent architectures as an efficient alternative, introducing a vertically chunked…

Spatial-Spectral Mamba (SSM) improves computational efficiency and captures long-range dependencies, addressing Transformer limitations. However, traditional Mamba models overlook rich spectral information in HSIs and struggle with high…

Automated analysis of electroencephalography (EEG) has recently undergone a paradigm shift. The introduction of transformer architectures and self-supervised pretraining (SSL) has led to the development of EEG foundation models. These…

Generating realistic dyadic human motion from text descriptions presents significant challenges, particularly for extended interactions that exceed typical training sequence lengths. While recent transformer-based approaches have shown…

We propose Samba ASR,the first state of the art Automatic Speech Recognition(ASR)model leveraging the novel Mamba architecture as both encoder and decoder,built on the foundation of state space models(SSMs).Unlike transformerbased ASR…

The essence of audio-visual segmentation (AVS) lies in locating and delineating sound-emitting objects within a video stream. While Transformer-based methods have shown promise, their handling of long-range dependencies struggles due to…

Accurate epileptic seizure prediction from electroencephalography (EEG) remains challenging because pre-ictal dynamics may span long time horizons while clinically relevant signatures can be subtle and transient. Many deep learning models…

In recent speech enhancement (SE) research, transformer and its variants have emerged as the predominant methodologies. However, the quadratic complexity of the self-attention mechanism imposes certain limitations on practical deployment.…

Training urban spatio-temporal foundation models that generalize well across diverse regions and cities is critical for deploying urban services in unseen or data-scarce regions. Recent studies have typically focused on fusing cross-domain…

Neuron segmentation is the cornerstone of reconstructing comprehensive neuronal connectomes, which is essential for deciphering the functional organization of the brain. The irregular morphology and densely intertwined structures of neurons…

Brain tumors exhibit high heterogeneity in morphology and multimodal contrast, making manual slice-by-slice de lineation time-consuming and experience-dependent, thus necessitating efficient and stable automated segmentation methods. To…

Transformer-based models have made significant progress in edge detection, but their high computational cost is prohibitive. Recently, vision Mamba have shown excellent ability in efficiently capturing long-range dependencies. Drawing…

Transformers have become dominant in large-scale deep learning tasks across various domains, including text, 2D and 3D vision. However, the quadratic complexity of their attention mechanism limits their efficiency as the sequence length…

Bayesian spatial modeling provides a flexible framework for whole-brain fMRI analysis by explicitly incorporating spatial dependencies, overcoming the limitations of traditional massive univariate approaches that lead to information waste.…

Medical video segmentation gains increasing attention in clinical practice due to the redundant dynamic references in video frames. However, traditional convolutional neural networks have a limited receptive field and transformer-based…

In recent advancements in medical image analysis, Convolutional Neural Networks (CNN) and Vision Transformers (ViT) have set significant benchmarks. While the former excels in capturing local features through its convolution operations, the…