An integrated system that allows quick, effective and trasparent exploration of researchers' expertise, by making available data on scientific production, research projects, patents and other relevant information. Through the search function, it's possible to discover research areas, people, and results of the research conducted at Politecnico di Torino.
EDGEML - EDGELM: Efficient and Privacy-Preserving Edge Deployment of Multimodal Large Models
Duration:
Principal investigator(s):
Project type:
Funding body:
Project identification number:
PoliTo role:
Abstract
Large models (LMs) powering generative Artificial Intelligence (AI) services are typically hosted in centralized cloud infrastructures. This paradigm introduces significant challenges related to data sovereignty, privacy protection, energy consumption, and transmission latency, severely restricting their suitability for real-time, privacy-sensitive applications. Despite recent advances, current solutions for LM compression and edge deployment remain insufficiently adaptive to heterogeneous hardware distributions, diverse multimodal model requirements, and practical deployment constraints. The EDGELM project directly addresses these gaps by developing a context-aware, AI-driven framework that tailors LM compression strategies to heterogeneous edge-resource distributions, modality-specific compression characteristics, and application-specific accuracy constraints. Complementing this framework, an adaptive reinforcement-learning-assisted orchestration solution will be designed to optimize model cooperation and resource allocation, thereby improving inference latency and energy efficiency.
Furthermore, EDGELM will integrate hybrid quantum-classical fine-tuning methods and federated learning techniques to augment model expressiveness and training efficiency within limited resource budgets. EDGELM’s practical effectiveness will be validated through real-world deployment in a privacy-sensitive healthcare scenario, ensuring compliance with data protection and ethical standards, while evaluating user acceptance and trust with expert psychological insights. Supported by advanced edge-computing and quantum computing facilities at Politecnico di Torino, industrial expertise from Nextworks, and clinical input from healthcare partners, EDGELM will establish a robust methodology and practical roadmap for broader deployment of multimodal LMs at the network edge. This initiative supports Europe's transition toward privacy-compliant, sustainable, and efficient generative AI services.
Structures
Keywords
ERC sectors
Sustainable Development Goals
Budget
| Total cost: | € 193,643.28 |
|---|---|
| Total contribution: | € 193,643.28 |
| PoliTo total cost: | € 193,643.28 |
| PoliTo contribution: | € 193,643.28 |