Local-Cloud Inference Offloading for LLMs in Multi-Modal, Multi-Task, Multi-Dialogue Settings
Open Access
- 23 October 2025
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 201-210
Abstract
No abstract availableAll Related Versions
Funding Information
- Office of Naval Research (ONR) (N00014-23-C-1016)
- National Science Foundation (NSF) (CPS-2313109)
- Air Force Office of Scientific Research (AFOSR) (FA9550-24-1-0083)
This publication has 10 references indexed in Scilit:
- Regret Bounds for Online Learning for Hierarchical Inference2024
- Resource Allocation for Stable LLM Training in Mobile Edge Computing2024
- Resource Allocation and Secure Wireless Communication in the Large Model based Mobile Edge Computing System2024
- Resource-aware Deployment of Dynamic DNNs over Multi-tiered Interconnected Systems2024
- Optimization of Offloading Policies for Accuracy-Delay Tradeoffs in Hierarchical Inference2024
- Titanic: Towards Production Federated Learning with Large Language Models2024
- GazePointAR: A Context-Aware Multimodal Voice Assistant for Pronoun Disambiguation in Wearable Augmented Reality2024
- Creating Edge AI from Cloud-based LLMs2024
- Large Language Models Empowered Autonomous Edge AI for Connected IntelligenceIEEE Communications Magazine, 2024
- Human-level control through deep reinforcement learningNature, 2015