.png){kind=icon}
.png){kind=icon}
Return
Edge Intelligence in the Generative Artificial Intelligence Era
.png){kind=icon}
PRE
AI
DOI：10.1109/MWC.2025.3599652.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Edge intelligence (EI), by leveraging abundant edge resources and positioning AI algorithms closer to end-users, has long been considered a fundamental catalyst for the AI industry. As the AI realm shifts towards new Generative AI (GAI), EI offers a broader data source, reduced latency, and enhanced privacy protections, making it a more conducive environment for GAI advancements than cloud-based approaches. However, compared to traditional AI models, GAI challenges existing EI with its significantly larger model size, markedly intricate operations, and substantially heightened resource demands. This article delves deeply into the evolution of EI in the upcoming GAI era. Particularly, we first provide a thorough overview of challenges introduced by GAI, including escalated communication costs, greater computational demands, and intensified security and privacy concerns. We then extend the EI scope to encompass the entire lifecycle of GAI within EI, while jointly considering sensing, communication, and computation against these emerging challenges. Additionally, we spotlight key techniques designed to pave the way for the future of EI, elaborating on each of these in detail. To provide concrete insights into how EI adapts for GAI, we present two illustrative case studies: one focusing on diffusion model-based GAI fine-tuning in vehicular networks and the other highlighting large language model-based real-time inference offloading in wireless edge networks. Lastly, we outline three future research directions for EI, guided by the latest advancements in GAI.
Keywords:
Generative AI
edge intelligence
wireless networks
Journal
IF:
11.5
Papers:
2.7K
Citations:
1.3W
View more organizations