2 papers
cs.CV2025
Using KL-Divergence to Focus Frequency Information in Low-Light Image Enhancement
Yan Xingyang, Huang Xiaohong, Zhang Zhao +2
In the Fourier domain, luminance information is primarily encoded in the amplitude spectrum, while spatial structures are captured in the phase components. The traditional Fourier…
cs.LG2025
Improving Memory Efficiency for Training KANs via Meta Learning
Zhangchi Zhao, Jun Shu, Deyu Meng +1
Inspired by the Kolmogorov-Arnold representation theorem, KANs offer a novel framework for function approximation by replacing traditional neural network weights with learnable uni…