SOURCE-LINKED INTELLIGENCE
EDGELM: Efficient and Privacy-Preserving Edge Deployment of Multimodal Large Models
EDGELM: Efficient and Privacy-Preserving Edge Deployment of Multimodal Large Models 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
Read original source ↗ Open in workspace
- recordType
- award
- status
- SIGNED
- region
- EU
- value
- 193643.28
- unit
- EUR
Evidence & attribution
European Commission, CORDIS Horizon Europe project dataset. Metadata adapted.
License: CORDIS reuse policy
First collected: 2026-09-20T05:31:32.981Z. This is not the publication date.