This research introduces a hybrid swarm intelligence framework that enables efficient deployment of multimodal large language models in resource-constrained edge computing environments.

• Combines Particle Swarm Optimization (PSO) and Ant Colony Optimization (ACO) to dynamically allocate resources across edge-cloud infrastructure
• Balances computational workloads between edge devices and cloud servers while preserving data privacy
• Addresses key challenges of resource management, communication overhead, and non-IID data in federated learning
• Enables real-time processing of multimodal data while maintaining model performance

This engineering advancement makes sophisticated AI models deployable in edge computing scenarios, opening opportunities for industries requiring privacy-preserving, real-time AI processing at the edge.

A Hybrid Swarm Intelligence Approach for Optimizing Multimodal Large Language Models Deployment in Edge-Cloud-based Federated Learning Environments