activity
20122023
most citedSparsely-Connected Neural Networks: Towards Efficient VLSI Implementation of Deep Neural Networks

34 citations · 83 across the 9 of their papers we have counts for

collaborators

13 papers

cs.CL2024

Automatic Pruning of Fine-tuning Datasets for Transformer-based Language Models

Mohammadreza Tayaranian, Seyyed Hasan Mozafari, Brett H. Meyer +2

Transformer-based language models have shown state-of-the-art performance on a variety of natural language understanding tasks. To achieve this performance, these models are first…

cs.CV2024

Faster Inference of Integer SWIN Transformer by Removing the GELU Activation

Mohammadreza Tayaranian, Seyyed Hasan Mozafari, James J. Clark +2

SWIN transformer is a prominent vision transformer model that has state-of-the-art accuracy in image classification tasks. Despite this success, its unique architecture causes slow…

cs.CV2024

AdCorDA: Classifier Refinement via Adversarial Correction and Domain Adaptation

Lulan Shen, Ali Edalati, Brett Meyer +2

This paper describes a simple yet effective technique for refining a pretrained classifier network. The proposed AdCorDA method is based on modification of the training set and mak…

cs.LG2024

Robustness to distribution shifts of compressed networks for edge devices

Lulan Shen, Ali Edalati, Brett Meyer +2

It is necessary to develop efficient DNNs deployed on edge devices with limited computation resources. However, the compressed networks often execute new tasks in the target domain…

eess.SP20231 cited

Step-GRAND: A Low Latency Universal Soft-input Decoder

Syed Mohsin Abbas, Marwan Jalaleddine, Chi-Ying Tsui +1

GRAND features both soft-input and hard-input variants that are well suited to efficient hardware implementations that can be characterized with achievable average and worst-case d…

cs.CV2023

SSS3D: Fast Neural Architecture Search For Efficient Three-Dimensional Semantic Segmentation

Olivier Therrien, Marihan Amein, Zhuoran Xiong +2

We present SSS3D, a fast multi-objective NAS framework designed to find computationally efficient 3D semantic scene segmentation networks. It uses RandLA-Net, an off-the-shelf poin…