← Search

Keivan Alizadeh-Vahid

2 accepted papers

2024

ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models

ICLR 2024oral

Large Language Models (LLMs) with billions of parameters have drastically transformed AI applications. However, their demanding computation during inference has raised significant challenges for deployment on resource-constrained devices. Despite recent trends favoring alternative activation functio…

Cited by 85SourcePDFScholar
2022

DKM: Differentiable k-Means Clustering Layer for Neural Network Compression

ICLR 2022poster

Deep neural network (DNN) model compression for efficient on-device inference is becoming increasingly important to reduce memory requirements and keep user data on-device. To this end, we propose a novel differentiable k-means clustering layer (DKM) and its application to train-time weight clusteri…

Cited by 53SourcePDFScholar