InfoQ

Google’s TurboQuant Compression May Support Faster Inference, Same Accuracy on Less Capable Hardware

Google Research unveiled TurboQuant, a novel quantization algorithm that compresses large language models’ Key-Value caches ...
IEEE

MMProtRepPPI: A Multimodal Protein Representation for Predicting Protein-Protein Interactions Using Sequence and Structure

Recently, a range of effective methods have been developed for predicting protein-protein interactions (PPIs). Among them, the methods based on data derived from protein sequences and structures have ...
IEEE

On-Board Hyperspectral Image Compression Using Vector-Quantized Auto Encoders

Abstract: In the CORSA project [1] we demonstrated an AI method for near-lossless image compression for Sentinel-2 data using the concept of vector quantized auto-encoders. As part of the MOVIQ ...