Efficient acceleration of deep learning inference on resource-constrained edge devices: A review

MMH Shuvo, SK Islam, J Cheng… - Proceedings of the …, 2022 - ieeexplore.ieee.org
Successful integration of deep neural networks (DNNs) or deep learning (DL) has resulted
in breakthroughs in many areas. However, deploying these highly accurate models for data …

Compiler Technologies in Deep Learning Co-Design: A Survey

H Zhang, M **ng, Y Wu, C Zhao - Intelligent Computing, 2023 - spj.science.org
With the rapid development of deep learning applications, general-purpose processors no
longer suffice for deep learning workloads because of the dying of Moore's Law. Thus …

EdgeLLM: Fast On-device LLM Inference with Speculative Decoding

D Xu, W Yin, H Zhang, X **, Y Zhang… - IEEE Transactions …, 2024 - ieeexplore.ieee.org
Generative tasks, such as text generation and question answering, are essential for mobile
applications. Given their inherent privacy sensitivity, executing them on devices is …

Cloud and Edge Computing for Connected and Automated Vehicles

Q Zhu, B Yu, Z Wang, J Tang, QA Chen… - … and Trends® in …, 2023 - nowpublishers.com
The recent development of cloud computing and edge computing shows great promise for
the Connected and Automated Vehicle (CAV), by enabling CAVs to offload their massive on …

Rise of the autonomous machines

S Liu, JL Gaudiot - Computer, 2022 - ieeexplore.ieee.org
We are entering the age of autonomous machines, but many roadblocks exist on the path to
make this a reality. We make a preliminary attempt at recognizing and categorizing the …