2 papers
cs.AI2026
Post-Hoc Merging is Not Enough: Many-Shot Model Merging with Loss-Gap Balancing
Kyungjin Im, Miru Kim, Chanin Eom +1
Model merging has become a practical post-training strategy for building a single multi-task large language model (LLM) by combining multiple task-specialized models. However, most…
cs.LG2026
Fed-ADE: Adaptive Learning Rate for Federated Post-adaptation under Distribution Shift
Heewon Park, Mugon Joe, Miru Kim +2
Federated learning (FL) in post-deployment settings must adapt to non-stationary data streams across heterogeneous clients without access to ground-truth labels. A major challenge…