Nanowerk

Stacked memristor arrays compute Euclidean distance in memory to accelerate self-organizing maps

A novel stacked memristor architecture performs Euclidean distance calculations directly within memory, enabling ...
Semiconductor Engineering

Balancing Training, Quantization, And Hardware Integration In NPUs

Evolving challenges and strategies in AI/ML model deployment and hardware optimization have a big impact on NPU architectures ...
InfoWorld

Edge AI: The future of AI inference is smarter local compute

Smaller models, lightweight frameworks, specialized hardware, and other innovations are bringing AI out of the cloud and into ...
IEEE

BRIC: Bottom-Up Residual Vector Quantization for Learned Image Compression

Abstract: This paper presents Bottom-up Residual vector quantization for learned Image Compression (BRIC). This novel deep learning-based image compression method quantizes latent representations ...
GitHub

MELLE: Autoregressive Speech Synthesis without Vector Quantization

An unofficial PyTorch implementation of "Autoregressive Speech Synthesis without Vector Quantization" paper. This repository provides a complete pipeline for training and inference of the MELLE model.
GitHub

Vector Search using Embeddings, FAISS and Product Quantization

This project implements an efficient similarity search system for lecture content using embeddings, FAISS and Product Quantization with custom index & KMeans implementations. It allows you to find ...
IEEE

DCU: A New Dynamic Codebook Update Improvement on the Vector Quantization Model

Abstract: Vector quantization-based image semantic communication systems have successfully boosted transmission efficiency. However, existing models like Vector Quantized Variational Autoencoder 2 ...