Image de couverture de livre

Bridging On-Device and Cloud LLMs for Collaborative Reasoning: A Unified Methodology for Local Routing and Post-Training

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Fang, Wenzhi, Han, Dong-Jun, Yuan, Liangqi, Chen, Evan, Brinton, Christopher
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

PAAC: Privacy-Aware Agentic Device-Cloud Collaboration
par: Yuan, Liangqi, et autres
Publié: (2026)

Federated Sketching LoRA: A Flexible Framework for Heterogeneous Collaborative Fine-Tuning of LLMs
par: Fang, Wenzhi, et autres
Publié: (2025)

Local-Cloud Inference Offloading for LLMs in Multi-Modal, Multi-Task, Multi-Dialogue Settings
par: Yuan, Liangqi, et autres
Publié: (2025)

Joint Continual Learning of Local Language Models and Cloud Offloading Decisions with Budget Constraints
par: Chen, Evan, et autres
Publié: (2026)

LLMAP: LLM-Assisted Multi-Objective Route Planning with User Preferences
par: Yuan, Liangqi, et autres
Publié: (2025)

Federated Learning over Hierarchical Wireless Networks: Training Latency Minimization via Submodel Partitioning
par: Fang, Wenzhi, et autres
Publié: (2023)

Large Language Models over Networks: Collaborative Intelligence under Resource Constraints
par: Yuan, Liangqi, et autres
Publié: (2026)

Iterative Critique-and-Routing Controller for Multi-Agent Systems with Heterogeneous LLMs
par: Fang, Wenzhi, et autres
Publié: (2026)

Hierarchical Federated Learning with Multi-Timescale Gradient Correction
par: Fang, Wenzhi, et autres
Publié: (2024)

Communication-Efficient Multimodal Federated Learning: Joint Modality and Client Selection
par: Yuan, Liangqi, et autres
Publié: (2024)

Self-Play Enhancement via Advantage-Weighted Refinement in Online Federated LLM Fine-Tuning with Real-Time Feedback
par: Lee, Seohyun, et autres
Publié: (2026)

Rethinking the Starting Point: Collaborative Pre-Training for Federated Downstream Tasks
par: Chu, Yun-Wei, et autres
Publié: (2024)

TAP: Two-Stage Adaptive Personalization of Multi-Task and Multi-Modal Foundation Models in Federated Learning
par: Lee, Seohyun, et autres
Publié: (2025)

Using Diffusion Models as Generative Replay in Continual Federated Learning -- What will Happen?
par: Mei, Yongsheng, et autres
Publié: (2024)

FedMFS: Federated Multimodal Fusion Learning with Selective Modality Communication
par: Yuan, Liangqi, et autres
Publié: (2023)

Robust Collaborative Inference with Vertically Split Data Over Dynamic Device Environments
par: Ganguli, Surojit, et autres
Publié: (2023)

Communication-Efficient Federated Learning under Dynamic Device Arrival and Departure: Convergence Analysis and Algorithm Design
par: Chang, Zhan-Lun, et autres
Publié: (2024)

Differentially-Private Multi-Tier Federated Learning
par: Chen, Evan, et autres
Publié: (2024)

Decentralized Federated Learning: A Survey and Perspective
par: Yuan, Liangqi, et autres
Publié: (2023)

Decentralized Sporadic Federated Learning: A Unified Algorithmic Framework with Convergence Guarantees
par: Zehtabi, Shahryar, et autres
Publié: (2024)

Communication-Efficient and Differentially Private Vertical Federated Learning with Zeroth-Order Optimization
par: Zhang, Jianing, et autres
Publié: (2025)

Gradient Correction in Federated Learning with Adaptive Optimization
par: Chen, Evan, et autres
Publié: (2025)

Unlocking the Potential of Model Calibration in Federated Learning
par: Chu, Yun-Wei, et autres
Publié: (2024)

Sporadic Gradient Tracking over Directed Graphs: A Theoretical Perspective on Decentralized Federated Learning
par: Zehtabi, Shahryar, et autres
Publié: (2026)

Can Post-Training Transform LLMs into Causal Reasoners?
par: Chen, Junqi, et autres
Publié: (2026)

Decentralized Domain Generalization with Style Sharing: Formal Model and Convergence Analysis
par: Zehtabi, Shahryar, et autres
Publié: (2025)

KDRL: Post-Training Reasoning LLMs via Unified Knowledge Distillation and Reinforcement Learning
par: Xu, Hongling, et autres
Publié: (2025)

Cooperative Decentralized Backdoor Attacks on Vertical Federated Learning
par: Lee, Seohyun, et autres
Publié: (2025)

Data-Free Continual Learning of Server Models in Model-Heterogeneous Cloud-Device Collaboration
par: Zhang, Xiao, et autres
Publié: (2025)

Multi-Subspace Matrix Recovery from Permuted Data
par: Xie, Liangqi, et autres
Publié: (2024)

Examining Reasoning LLMs-as-Judges in Non-Verifiable LLM Post-Training
par: Liu, Yixin, et autres
Publié: (2026)

PrivTune: Efficient and Privacy-Preserving Fine-Tuning of Large Language Models via Device-Cloud Collaboration
par: Liu, Yi, et autres
Publié: (2025)

Communication-Efficient Personalized Adaptation via Federated-Local Model Merging
par: Zou, Yinan, et autres
Publié: (2026)

Benchmarking Post-Training Quantization in LLMs: Comprehensive Taxonomy, Unified Evaluation, and Comparative Analysis
par: Zhao, Jiaqi, et autres
Publié: (2025)

Provable Benefit of Curriculum in Transformer Tree-Reasoning Post-Training
par: Bu, Dake, et autres
Publié: (2025)

UnifiedNN: Efficient Neural Network Training on the Cloud
par: Taki, Sifat Ut, et autres
Publié: (2024)

End-to-End On-Device Quantization-Aware Training for LLMs at Inference Cost
par: Tan, Qitao, et autres
Publié: (2025)

BioBridge: Bridging Proteins and Language for Enhanced Biological Reasoning with LLMs
par: Wang, Yujia, et autres
Publié: (2026)

RADAR: Reasoning-Ability and Difficulty-Aware Routing for Reasoning LLMs
par: Fernandez, Nigel, et autres
Publié: (2025)

Metis: Training LLMs with FP4 Quantization
par: Cao, Hengjie, et autres
Publié: (2025)