2 citations · 3 across the 4 of their papers we have counts for
5 papers
A level-wise training scheme for learning neural multigrid smoothers with application to integral equations
Lingfeng Li, Yin King Chu, Raymond Chan +1
Convolution-type integral equations commonly occur in signal processing and image processing. Discretizing these equations yields large and ill-conditioned linear systems. While th…
A Mathematical Explanation of Transformers
Xue-Cheng Tai, Hao Liu, Lingfeng Li +1
The Transformer architecture has revolutionized the field of sequence modeling and underpins the recent breakthroughs in large language models (LLMs). However, a comprehensive math…
A Mathematical Explanation of UNet
Xue-Cheng Tai, Hao Liu, Raymond H. Chan +1
The UNet architecture has transformed image segmentation. UNet's versatility and accuracy have driven its widespread adoption, significantly advancing fields reliant on machine lea…
A level set representation method for N-dimensional convex shape and applications
Lingfeng li, Shousheng Luo, Xue-Cheng Tai +1
In this work, we present a new efficient method for convex shape representation, which is regardless of the dimension of the concerned objects, using level-set approaches. Convexit…
Convex hull algorithms based on some variational models
Lingfeng Li, Shousheng Luo, Xue-Cheng Tai +1
Seeking the convex hull of an object is a very fundamental problem arising from various tasks. In this work, we propose two variational convex hull models using level set represent…