5 papers
HEART-PFL: Stable Personalized Federated Learning under Heterogeneity with Hierarchical Directional Alignment and Adversarial Knowledge Transfer
Minjun Kim, Minje Kim
Personalized Federated Learning (PFL) aims to deliver effective client-specific models under heterogeneous distributions, yet existing methods suffer from shallow prototype alignme…
MAPLE: Modality-Aware Post-training and Learning Ecosystem
Nikhil Verma, Minjung Kim, JooYoung Yoo +5
Multimodal language models now integrate text, audio, and video for unified reasoning. Yet existing RL post-training pipelines treat all input signals as equally relevant, ignoring…
Activation Boundary Matching: Task-Informed Initialization for Low-Rank Adaptation
Dongha Lee, Jinhee Park, Minjun Kim +1
Low-Rank Adaptation (LoRA) is highly sensitive to initialization, yet existing schemes construct the initial subspace from statistics at the pretrained point, capturing pre-adaptat…
DTA: Dual Temporal-channel-wise Attention for Spiking Neural Networks
Minje Kim, Minjun Kim, Xu Yang
Spiking Neural Networks (SNNs) present a more energy-efficient alternative to Artificial Neural Networks (ANNs) by harnessing spatio-temporal dynamics and event-driven spikes. Effe…
FedCAR: Cross-client Adaptive Re-weighting for Generative Models in Federated Learning
Minjun Kim, Minjee Kim, Jinhoon Jeong
Generative models trained on multi-institutional datasets can provide an enriched understanding through diverse data distributions. However, training the models on medical images i…