Federated fine-tuning has emerged as a promising approach for adapting foundation models (FMs) to diverse downstream tasks in edge environments. In Internet of Vehicles (IoV) systems, enabling efficient and low-latency multi-task adaptation is particularly challenging due to client mobility, heterogeneous resources, and intermittent connectivity. This paper proposes a hierarchical federated fine-tuning framework that coordinates roadside units (RSUs) and vehicles to support resource-aware and mobility-resilient learning across dynamic IoV scenarios. Leveraging Low-Rank Adaptation (LoRA), we introduce a decentralized, energy-aware rank adaptation mechanism formulated as a constrained multi-armed bandit problem. A novel UCB-DUAL algorithm is developed to enable adaptive exploration under per-task energy budgets, achieving provable sublinear regret. To evaluate our method, we construct a large-scale IoV simulator based on real-world trajectories, capturing dynamic participation, RSU handoffs, and communication variability. Extensive experiments show that our approach achieves the best accuracy-efficiency trade-off among all baselines, reducing latency by over 24\% and improving average accuracy by more than 2.5\%.

翻译：联邦微调已成为一种有前景的方法，用于在边缘环境中将基础模型适应到多样的下游任务。在车联网系统中，由于客户端移动性、异构资源和间歇性连接，实现高效且低延迟的多任务适应尤为具有挑战性。本文提出了一种分层联邦微调框架，该框架协调路侧单元与车辆，以支持动态车联网场景中资源感知和移动鲁棒的学习。利用低秩适应，我们引入了一种去中心化的能量感知秩适应机制，该机制被建模为受约束的多臂老虎机问题。我们开发了一种新颖的UCB-DUAL算法，以在每任务能量预算下实现自适应探索，并达到可证明的亚线性遗憾。为评估我们的方法，我们基于真实轨迹构建了一个大规模车联网模拟器，捕捉动态参与、路侧单元切换和通信可变性。大量实验表明，我们的方法在所有基线中实现了最佳的精度-效率权衡，延迟降低超过24%，平均精度提升超过2.5%。