48 citations · 58 across the 14 of their papers we have counts for
14 papers
Smart Adaptive Computing Across the Continuum: LLMs in IoT-Edge-Cloud Resource Management
Antonino Vaccarella, Lanpei Li, Vincenzo Lomonaco +1
Managing resources across IoT, edge, and cloud layers calls for continuous, context-aware decisions under constraints that rarely stay fixed. Deep reinforcement learning (DRL) hand…
ContinuumBench: Benchmarking Joint Autoscaling and Placement Across Evaluation Regimes in the Cloud-Edge Continuum
Lanpei Li, Antonino Vaccarella, Vincenzo Lomonaco +1
Cloud-edge controllers coordinate service placement, replica scaling, and resource pre-warming to keep end-to-end latency within application deadlines. But evaluations often obscur…
CLOUDADV: Decision-Aligned Instance Sizing with Zero-Shot Foundation Models under Drift
Jack Bell, Giacomo Carfi, Gerlando Gramaglia +3
Cloud virtual machines are often overprovisioned, creating avoidable cost and operational inefficiency. We present CLOUDADV, an interactive engineer-facing advisory system for clou…
Continual Model Routing in Evolving Model Hubs
Jack Bell, Giacomo Carfì, Gerlando Gramaglia +1
AI model hubs provide access to a rapidly growing collection of powerful pre-trained models, enabling off-the-shelf mixture-of-experts systems with different routing strategies. Ho…
Book your room in the Turing Hotel! A symmetric and distributed Turing Test with multiple AIs and humans
Christian Di Maio, Tommaso Guidi, Luigi Quarantiello +4
In this paper, we report our experience with ``TuringHotel'', a novel extension of the Turing Test based on interactions within mixed communities of Large Language Models (LLMs) an…
Reinforcement Learning-Based Dynamic Management of Structured Parallel Farm Skeletons on Serverless Platforms
Lanpei Li, Massimo Coppola, Malio Li +3
We present a framework for dynamic management of structured parallel processing skeletons on serverless platforms. Our goal is to bring HPC-like performance and resilience to serve…
A Compositional Paradigm for Foundation Models: Towards Smarter Robotic Agents
Luigi Quarantiello, Elia Piccoli, Jack Bell +8
The birth of Foundation Models brought unprecedented results in a wide range of tasks, from language to vision, to robotic control. These models are able to process huge quantities…
GLAM: Efficient Continual Learning at Scale via Grouped LoRA Adapter Merging
Irene Testa, Luigi Quarantiello, Eric Nuertey Coleman +3
The ability to learn continuously over time remains a major challenge for modern machine learning systems, even in the era of Foundation Models. While the rich representations lear…
Task-Agnostic Experts Composition for Continual Learning
Luigi Quarantiello, Andrea Cossu, Vincenzo Lomonaco
Compositionality is one of the fundamental abilities of the human reasoning process, that allows to decompose a complex problem into simpler elements. Such property is crucial also…
The Future of Continual Learning in the Era of Foundation Models: Three Key Directions
Jack Bell, Luigi Quarantiello, Eric Nuertey Coleman +5
Continual learning--the ability to acquire, retain, and refine knowledge over time--has always been fundamental to intelligence, both human and artificial. Historically, different…
Parameter-Efficient Continual Fine-Tuning: A Survey
Eric Nuertey Coleman, Luigi Quarantiello, Ziyue Liu +4
The emergence of large pre-trained networks has revolutionized the AI field, unlocking new possibilities and achieving unprecedented performance. However, these models inherit a fu…
Adaptive AI-based Decentralized Resource Management in the Cloud-Edge Continuum
Lanpei Li, Jack Bell, Massimo Coppola +1
In the Cloud-Edge Continuum, dynamic infrastructure change and variable workloads complicate efficient resource management. Centralized methods can struggle to adapt, whilst purely…
LuckyMera: a Modular AI Framework for Building Hybrid NetHack Agents
Luigi Quarantiello, Simone Marzeddu, Antonio Guzzi +1
In the last few decades we have witnessed a significant development in Artificial Intelligence (AI) thanks to the availability of a variety of testbeds, mostly based on simulated e…
Efficient Continual Learning in Neural Networks with Embedding Regularization
Jary Pomponi, Simone Scardapane, Vincenzo Lomonaco +1
Continual learning of deep neural networks is a key requirement for scaling them up to more complex applicative scenarios and for achieving real lifelong learning of these architec…