3 papers
cs.AI2026
RE-MCDF: Closed-Loop Multi-Expert LLM Reasoning for Knowledge-Grounded Clinical Diagnosis
Shaowei Shen, Xiaohong Yang, Jie Yang +4
Electronic medical records (EMRs), particularly in neurology, are inherently heterogeneous, sparse, and noisy, which poses significant challenges for large language models (LLMs) i…
cs.LG2026
ELSA: Efficient LLM-Centric Split Aggregation for Privacy-Aware Hierarchical Federated Learning over the Network Edge
Xiaohong Yang, Tong Xie, Minghui Liwang +5
Training large language models (LLMs) at the network edge faces fundamental challenges arising from device resource constraints, severe data heterogeneity, and heightened privacy r…
cs.LG2025
Adaptive UAV-Assisted Hierarchical Federated Learning: Optimizing Energy, Latency, and Resilience for Dynamic Smart IoT
Xiaohong Yang, Minghui Liwang, Liqun Fu +4
Hierarchical Federated Learning (HFL) extends conventional Federated Learning (FL) by introducing intermediate aggregation layers, enabling distributed learning in geographically d…