The field of speech processing has undergone a transformative shift with the advent of deep
learning. The use of multiple processing layers has enabled the creation of models capable …

Over recent years, there has been a rapid development of deep learning (DL) in both
industry and academia fields. However, finding the optimal hyperparameters of a DL model …

Large Language Models (LLMs) have demonstrated remarkable capabilities in important
tasks such as natural language understanding and language generation, and thus have the …

Transformer models have achieved remarkable results in various natural language tasks,
but they are often prohibitively large, requiring massive memories and computational …

Large language models (LLMs) show inherent brittleness in their safety mechanisms, as
evidenced by their susceptibility to jailbreaking and even non-malicious fine-tuning. This …

In this paper, we introduce a new post-training compression paradigm for Large Language
Models (LLMs) to facilitate their wider adoption. We delve into LLM weight low-rank …

Transformers have become the state-of-the-art architectures for various tasks in Natural
Language Processing (NLP) and Computer Vision (CV); however, their space and …

We propose a simple approach for memory-efficient adaptation of pretrained language
models. Our approach uses an iterative algorithm to decompose each pretrained matrix into …

Abstract Vision Transformers (ViTs) have demonstrated the state-of-the-art performance in
various vision-related tasks. The success of ViTs motivates adversaries to perform backdoor …

Diffusion models have been proven highly effective at generating high-quality images.
However, as these models grow larger, they require significantly more memory and suffer …