Abstract: Vision Transformers (ViTs) suffer from high parameter complexity because they rely on Multi-layer Perceptrons (MLPs) for nonlinear representation. This issue is particularly challenging in ...

Paper: https://openaccess.thecvf.com/content/CVPR2023/papers/Kong_Efficient_Frequency_Domain-Based_Transformers_for_High-Quality_Image_Deblurring_CVPR_2023_paper.pdf ...

Our research proves a conjecture from string theory asserting the vanishing of a specific convolution sum arising in the 4-graviton scattering amplitude in 10-dimensional type IIB string theory. The ...

Point Cloud can be considered as non-Euclidean structure data since it is disordered and irregular. When training on point cloud, it is difficult to apply spatial discrete convolution directly. In ...

Predicting the response of cell lines to characteristic drugs based on multi-omics gene information has become the core problem of precision oncology. At present, drug response prediction using ...

In the past few decades, multi-linear algebra also known as tensor algebra has been adapted and employed as a tool for various engineering applications. Recent developments in tensor algebra have ...

Abstract: The Number Theoretic Transform (NTT) is a powerful mathematical tool that has become increasingly important in developing Post Quantum Cryptography (PQC) and Homomorphic Encryption (HE). Its ...

Convolution has a significant impact on many scientific disciplines, ranging from probability theory and harmonic analysis to information theory. Here, we introduce a framework to study quantum ...

Two new approaches allow deep neural networks to solve entire families of partial differential equations, making it easier to model complicated systems and to do so orders of magnitude faster. In high ...

In modern technology, design of devices with the capability of shaping the electromagnetic (EM) waves is rapidly progressing. Understandably, as far as the far field is concerned, metasurface ...