A review on dropout regularization approaches for deep neural networks within the scholarly domain

I Salehin, DK Kang - Electronics, 2023 - mdpi.com
Dropout is one of the most popular regularization methods in the scholarly domain for
preventing a neural network model from overfitting in the training phase. Develo** an …

Resource-efficient algorithms and systems of foundation models: A survey

M Xu, D Cai, W Yin, S Wang, X **, X Liu - ACM Computing Surveys, 2025 - dl.acm.org
Large foundation models, including large language models, vision transformers, diffusion,
and large language model based multimodal models, are revolutionizing the entire machine …

Which tokens to use? investigating token reduction in vision transformers

JB Haurum, S Escalera, GW Taylor… - Proceedings of the …, 2023 - openaccess.thecvf.com
Since the introduction of the Vision Transformer (ViT), researchers have sought to make ViTs
more efficient by removing redundant information in the processed tokens. While different …

Compute-efficient deep learning: Algorithmic trends and opportunities

BR Bartoldson, B Kailkhura, D Blalock - Journal of Machine Learning …, 2023 - jmlr.org
Although deep learning has made great progress in recent years, the exploding economic
and environmental costs of training neural networks are becoming unsustainable. To …

A survey of resource-efficient llm and multimodal foundation models

M Xu, W Yin, D Cai, R Yi, D Xu, Q Wang, B Wu… - arxiv preprint arxiv …, 2024 - arxiv.org
Large foundation models, including large language models (LLMs), vision transformers
(ViTs), diffusion, and LLM-based multimodal models, are revolutionizing the entire machine …

Learning probabilistic symmetrization for architecture agnostic equivariance

J Kim, D Nguyen, A Suleymanzade… - Advances in Neural …, 2023 - proceedings.neurips.cc
We present a novel framework to overcome the limitations of equivariant architectures in
learning functions with group symmetries. In contrary to equivariant architectures, we use an …

Survey of different large language model architectures: Trends, benchmarks, and challenges

M Shao, A Basit, R Karri, M Shafique - IEEE Access, 2024 - ieeexplore.ieee.org
Large Language Models (LLMs) represent a class of deep learning models adept at
understanding natural language and generating coherent responses to various prompts or …

Frozen Feature Augmentation for Few-Shot Image Classification

A Bär, N Houlsby, M Dehghani… - Proceedings of the …, 2024 - openaccess.thecvf.com
Training a linear classifier or lightweight model on top of pretrained vision model outputs so-
called'frozen features' leads to impressive performance on a number of downstream few …

GTP-ViT: Efficient Vision Transformers via Graph-based Token Propagation

X Xu, S Wang, Y Chen, Y Zheng… - Proceedings of the …, 2024 - openaccess.thecvf.com
Abstract Vision Transformers (ViTs) have revolutionized the field of computer vision, yet their
deployments on resource-constrained devices remain challenging due to high …

ViTs as backbones: Leveraging vision transformers for feature extraction

O Elharrouss, Y Himeur, Y Mahmood, S Alrabaee… - Information …, 2025 - Elsevier
Abstract The emergence of Vision Transformers (ViTs) has marked a significant shift in the
field of computer vision, presenting new methodologies that challenge traditional …