Guest talk: Roberto Morabito "From the Edge to the Cloud: Exploring AI Inference (yes, including Generative AI) Across the Computing Continuum"

From the Edge to the Cloud: Exploring AI Inference (yes, including Generative AI) Across the Computing Continuum

Roberto Morabito
Communication Systems Department at EURECOM, France

Abstract: This talk explores recent research on AI inference across the computing
continuum, from the edge to the cloud, with a focus on the challenges and opportunities
brought by hardware and software heterogeneity, as well as automation requirements.
Roberto will present insights into collaborative, edge-centric generative AI inference,
including efforts to benchmark language models on constrained devices and to
route queries efficiently across distributed nodes. He will also discuss recent work
on automating the lifecycle of extreme edge devices using LLMs, demonstrating
how these models can support code generation, adaptation, and deployment under
tight resource constraints.

Bio: Roberto Morabito is an Assistant Professor in the Communication Systems Department
at EURECOM, France. His research focuses on networked systems, edge computing, and
distributed AI, with recent work exploring the role of generative AI in constrained
environments. He holds a PhD from Aalto University and has held positions at
Ericsson Research, the University of Helsinki, and Princeton University. He has also
been a visiting researcher at INRIA, TUM, and Yale University.

This guest talk is hosted by Associate Professor Alex Jung, Department of Computer Science.