A survey of resource-efficient llm and multimodal foundation models
Large foundation models, including large language models (LLMs), vision transformers
(ViTs), diffusion, and LLM-based multimodal models, are revolutionizing the entire machine …
(ViTs), diffusion, and LLM-based multimodal models, are revolutionizing the entire machine …
[HTML][HTML] Equilibrium in the Computing Continuum through Active Inference
Computing Continuum (CC) systems are challenged to ensure the intricate requirements of
each computational tier. Given the system's scale, the Service Level Objectives (SLOs) …
each computational tier. Given the system's scale, the Service Level Objectives (SLOs) …
Decentralized Cooperative Caching and Offloading for Virtual Reality Task based on GAN-Powered Multi-Agent Reinforcement Learning
As a critical and prevalent service in future mobile networks, virtual reality (VR) is latency-
sensitive and power-hungry, bringing out the optimization problem of trade-off among power …
sensitive and power-hungry, bringing out the optimization problem of trade-off among power …
Training Machine Learning models at the Edge: A Survey
Edge Computing (EC) has gained significant traction in recent years, promising enhanced
efficiency by integrating Artificial Intelligence (AI) capabilities at the edge. While the focus …
efficiency by integrating Artificial Intelligence (AI) capabilities at the edge. While the focus …
Resource-efficient in-orbit detection of earth objects
With the rapid proliferation of large Low Earth Orbit (LEO) satellite constellations, a huge
amount of in-orbit data is generated and needs to be transmitted to the ground for …
amount of in-orbit data is generated and needs to be transmitted to the ground for …
Energy and Time-Aware Inference Offloading for DNN-based Applications in LEO Satellites
Y Chen, Q Zhang, Y Zhang, X Ma… - 2023 IEEE 31st …, 2023 - ieeexplore.ieee.org
In recent years, Low Earth Orbit (LEO) satellites have witnessed rapid development, with
inference based on Deep Neural Network (DNN) models emerging as the prevailing …
inference based on Deep Neural Network (DNN) models emerging as the prevailing …
Online Request Replication for Obtaining Fresh Information Under Pull Model
HY Wang, Q Sun, Q Li, X Ma… - IEEE Internet of Things …, 2024 - ieeexplore.ieee.org
Age of Information (AoI) has gained widespread usage and emerged as a pivotal metric for
assessing timeliness performance in information-update systems. Such systems often entail …
assessing timeliness performance in information-update systems. Such systems often entail …
FrankenSplit: Efficient Neural Feature Compression with Shallow Variational Bottleneck Injection for Mobile Edge Computing
The rise of mobile AI accelerators allows latency-sensitive applications to execute
lightweight Deep Neural Networks (DNNs) on the client side. However, critical applications …
lightweight Deep Neural Networks (DNNs) on the client side. However, critical applications …
Collaborative Inference in DNN-based Satellite Systems with Dynamic Task Streams
As a driving force in the advancement of intelligent in-orbit applications, DNN models have
been gradually integrated into satellites, producing daily latency-constraint and computation …
been gradually integrated into satellites, producing daily latency-constraint and computation …
Performance and Privacy Aspects of Image Classification in Cross-platform Mobile Applications
A Jeličić, M Ljubojević, M Savić - 2024 23rd International …, 2024 - ieeexplore.ieee.org
Mobile devices and applications that run on them have changed the everyday lives of not
just technology professionals but of the public at large. Another technology that is …
just technology professionals but of the public at large. Another technology that is …