Large language models (LLMs) have revolutionized natural language processing tasks. However, their practical deployment is hindered by their immense memory and computation …
Recent advancements in machine learning achieved by Deep Neural Networks (DNNs) have been significant. While demonstrating high accuracy, DNNs are associated with a …
Large Language Models (LLMs) excel in NLP, but their demands hinder their widespread deployment. While Quantization-Aware Training (QAT) offers a solution, its extensive …
Modern pre-trained transformers have rapidly advanced the state-of-the-art in machine learning, but have also grown in parameters and computational complexity, making them …
The recent detection transformer (DETR) has advanced object detection, but its application on resource-constrained devices requires massive computation and memory resources …
Recent trends in deep learning (DL) imposed hardware accelerators as the most viable solution for several classes of high-performance computing (HPC) applications such as …
How can we compress language models without sacrificing accuracy? The number of compression algorithms for language models is rapidly growing to benefit from remarkable …
SY Liu, Z Liu, KT Cheng - International Conference on …, 2023 - proceedings.mlr.press
Weight oscillation is a by-product of quantization-aware training, in which quantized weights frequently jump between two quantized levels, resulting in training instability and a sub …
Y Zhang, T Zhang, D Chen, Y Wang, Q Chen… - arXiv preprint arXiv …, 2023 - arxiv.org
While generative modeling has been ubiquitous in natural language processing and computer vision, its application to image retrieval remains unexplored. In this paper, we …