16 papers
CT-Merging: Consensus Directions and Task-Level Scaling for LoRA Adapter Merging
Keumseo Ryum, Joonhyuk Kang
LoRA adapters provide an efficient way to specialize a pretrained model for many downstream tasks, but deploying one adapter per task requires adapter storage and task selection at…
Beyond Fixed Rounds: Data-Free Early Stopping for Practical Federated Learning
Youngjoon Lee, Hyukjoon Lee, Seungrok Jung +4
Federated Learning (FL) facilitates decentralized collaborative learning without transmitting raw data. However, reliance on fixed global rounds or validation data for hyperparamet…
MIMO Channel Prediction via Deep Learning-based Conformal Bayes Filter
Dongwon Kim, Jinu Gong, Joonhyuk Kang
Channel prediction has emerged as an effective solution for acquiring accurate channel state information (CSI) in the presense of channel aging. Existing methods have inherent limi…
Forecasting-based Biomedical Time-series Data Synthesis for Open Data and Robust AI
Youngjoon Lee, Seongmin Cho, Yehhyun Jo +3
The limited data availability due to strict privacy regulations and significant resource demands severely constrains biomedical time-series AI development, which creates a critical…
Exploring Potential Prompt Injection Attacks in Federated Military LLMs and Their Mitigation
Youngjoon Lee, Taehyun Park, Yunho Lee +2
Federated Learning (FL) is increasingly being adopted in military collaborations to develop Large Language Models (LLMs) while preserving data sovereignty. However, prompt injectio…
Generative AI-Powered Plugin for Robust Federated Learning in Heterogeneous IoT Networks
Youngjoon Lee, Jinu Gong, Joonhyuk Kang
Federated learning enables edge devices to collaboratively train a global model while maintaining data privacy by keeping data localized. However, the Non-IID nature of data distri…