🏢 Queen Mary University of London
Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization
·4050 words·20 mins·
loading
·
loading
AI Theory
Interpretability
🏢 Queen Mary University of London
Multilinear Mixture of Experts (μMoE) achieves scalable expert specialization in deep neural networks through tensor factorization, enabling efficient fine-tuning and interpretable model editing.
CemiFace: Center-based Semi-hard Synthetic Face Generation for Face Recognition
·3037 words·15 mins·
loading
·
loading
Computer Vision
Face Recognition
🏢 Queen Mary University of London
CemiFace: Generating high-quality synthetic facial data for robust face recognition, while addressing privacy concerns.