🏢 McMaster University
Sample-Efficient Private Learning of Mixtures of Gaussians
·256 words·2 mins·
loading
·
loading
AI Theory
Privacy
🏢 McMaster University
Researchers achieve a breakthrough in privacy-preserving machine learning by developing sample-efficient algorithms for learning Gaussian Mixture Models, significantly reducing the data needed while m…
ECMamba: Consolidating Selective State Space Model with Retinex Guidance for Efficient Multiple Exposure Correction
·1754 words·9 mins·
loading
·
loading
Computer Vision
Image Generation
🏢 McMaster University
ECMamba: A novel dual-branch framework efficiently corrects multiple exposure images by integrating Retinex theory and an innovative 2D selective state-space layer, achieving state-of-the-art performa…