IEEE

Unsupervised Clustering of 3D Hand Scans Using K-Means and Gaussian Mixture Models (GMM)

Abstract: The precise segmentation and classification of anatomical structures from three-dimensional (3D) scan data are critical for advancing personalized rehabilitation protocols, custom prosthetic ...
GitHub

MODE: Mixture of Document Experts for RAG

MODE (Mixture of Document Experts) is an advanced framework that improves Retrieval-Augmented Generation (RAG) by integrating external knowledge retrieval with a mixture of specialized expert models.
IEEE

Enhancing Gaussian Mixture Model Efficiency Through Covariance Matrix Optimization, Singular Value Decomposition, and Block Toeplitz Matrices

Abstract: Gaussian Mixture Models (GMMs) are widely used for clustering, density estimation, and pattern recognition. Despite their versatility, GMMs often face computational challenges, particularly ...
GitHub

Z80-μLM: A Retrocomputing Micro Language Model

Z80-μLM is a 'conversational AI' that generates short character-by-character sequences, with quantization-aware training (QAT) to run on a Z80 processor with 64kb of ram. The root behind this project ...