2 papers
cs.LG2026
CT-Merging: Consensus Directions and Task-Specific Scaling for LoRA Adapter Merging
Keumseo Ryum, Joonhyuk Kang
LoRA merging methods increasingly operate on the low-rank structure of task updates, yet how the common subspace is estimated and how coefficients are assigned after recomposition…
cs.LG2025
SHEFL: Sparse Heterogeneous Ensemble Federated Learning with Group-Balanced Aggregation
Keumseo Ryum, Jinu Gong, Joonhyuk Kang
System heterogeneity in federated learning (FL) requires training workloads and communication demands to be adapted to client resource capacities. Federated ensemble learning distr…