3 papers
cs.LG2026
CoASFL: Coupled Consistency Optimization for Asynchronous Split Federated Learning
Junhao Cheng, Yunming Liao, Hongli Xu +2
Split Federated Learning (SFL) has emerged as a promising paradigm for training large-scale deep models on resource-constrained edge devices. Although asynchronous SFL alleviates t…
cs.CL2026
DuDi: Dual-Signal Distillation with Cross-Lingual Verbalizer
Patomporn Payoungkhamdee, Tinnakit Udsa, Jian Gang Ngui +3
Small language models (SLMs) are efficient and scalable, but their multilingual capabilities degrade severely at sub-billion scales, especially for Southeast Asian (SEA) languages.…
cs.LG2025
Exploring Cross-Client Memorization of Training Data in Large Language Models for Federated Learning
Tinnakit Udsa, Can Udomcharoenchaikit, Patomporn Payoungkhamdee +2
Federated learning (FL) enables collaborative training without raw data sharing, but still risks training data memorization. Existing FL memorization detection techniques focus on…