Related papers: Parity Requires Unified Input Dependence and Negat…
State-space models (SSMs) have recently emerged as a compelling alternative to Transformers for sequence modeling tasks. This paper presents a theoretical generalization analysis of selective SSMs, the core architectural component behind…
Foundational models have significantly advanced in natural language processing (NLP) and computer vision (CV), with the Transformer architecture becoming a standard backbone. However, the Transformer's quadratic complexity poses challenges…
Mesh saliency enhances the adaptability of 3D vision by identifying and emphasizing regions that naturally attract visual attention. To investigate the interaction between geometric structure and texture in shaping visual attention, we…
Denoising is a crucial preprocessing step for hyperspectral images (HSIs) due to noise arising from intra-imaging mechanisms and environmental factors. Long-range spatial-spectral correlation modeling is beneficial for HSI denoising but…
Recent efficient sequence modeling methods such as Gated DeltaNet, TTT, and RWKV-7 have achieved performance improvements by supervising the recurrent memory management through Delta learning rule. Unlike previous state-space models (e.g.,…
Vision transformers have significantly advanced the field of computer vision, offering robust modeling capabilities and global receptive field. However, their high computational demands limit their applicability in processing long…
An Undirected Weighted Network (UWN) is frequently encountered in a big-data-related application concerning the complex interactions among numerous nodes, e.g., a protein interaction network from a bioinformatics application. A Symmetric…
Modern multivariate time series forecasting primarily relies on two architectures: the Transformer with attention mechanism and Mamba. In natural language processing, an approach has been used that combines local window attention for…
State Space Models (SSMs) have recently enjoyed a rise to prominence in the field of deep learning for sequence modeling, especially as an alternative to Transformers. Their success stems from avoiding two well-known drawbacks of…
Establishing semantic correspondences between images is a fundamental yet challenging task in computer vision. Traditional feature-metric methods enhance visual features but may miss complex inter-correlation relationships, while recent…
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…
The analysis of tabular data has traditionally been dominated by gradient-boosted decision trees (GBDTs), known for their proficiency with mixed categorical and numerical features. However, recent deep learning innovations are challenging…
The Transformer architecture is widely deployed in many popular and impactful Large Language Models. At its core is the attention mechanism for calculating correlations between pairs of tokens. Performing an attention computation takes…
The typical Selective State-Space Model (SSM) used in Mamba addresses several limitations of Transformers, such as the quadratic computational complexity with respect to sequence length and the significant memory requirements during…
Pathological diagnosis is highly reliant on image analysis, where Regions of Interest (ROIs) serve as the primary basis for diagnostic evidence, while whole-slide image (WSI)-level tasks primarily capture aggregated patterns. To extract…
Learning-based stereo matching has recently achieved promising results, yet still suffers difficulties in establishing reliable matches in weakly matchable regions that are textureless, non-Lambertian, or occluded. In this paper, we address…
Medical image segmentation plays an important role in various clinical applications; however, existing deep learning models face trade-offs between efficiency and accuracy. Convolutional Neural Networks (CNNs) capture local details well but…
State Space Models (SSMs) are emerging as a compelling alternative to Transformers because of their consistent memory usage and high performance. Despite this, scaling up SSMs on cloud services or limited-resource devices is challenging due…
Accurate medical image segmentation requires effective modeling of both global anatomical structures and fine-grained boundary details. Recent state space models (e.g., Vision Mamba) offer efficient long-range dependency modeling. However,…
The transfer matrix method is usually employed to study problems described by $N$ equations of matrix Sturm-Liouville (MSL) kind. In some cases a numerical degradation (the so called $\Omega d$ problem) appears thus impairing the…