Yinbin Miao

2 accepted papers

2026

DP-FedAdamW: An Efficient Optimizer for Differentially Private Federated Large Models

Jin Liu, Ning Xi, Yinbin Miao, Junkang Liu

CVPR 2026

Balancing convergence efficiency and robustness under Differential Privacy (DP) is a central challenge in Federated Learning (FL). Although AdamW accelerates training and fine-tuning in large-scale models, we find that directly applying it to Differentially Private FL (DPFL) suffers from three major

Cited by 0 Source ↗code ↗Scholar ↗

2026

Rethinking LoRA for Privacy-Preserving Federated Learning in Large Models

Jin Liu, Ning Xi, Yinbin Miao, Junkang Liu

ICLR 2026poster

Fine-tuning large vision models (LVMs) and large language models (LLMs) under differentially private federated learning (DPFL) is hindered by a fundamental privacy-utility trade-off. Low-Rank Adaptation (LoRA), a promising parameter-efficient fine-tuning (PEFT) method, reduces computational and comm…

Cited by 0 Source ↗code ↗Scholar ↗