AI RESEARCH
Tunable MAGMAX: Preference-Aware Model Merging for Continual Learning
arXiv CS.LG
•
ArXi:2605.20803v1 Announce Type: new Continual learning (CL) aims to train models sequentially on multiple tasks while mitigating catastrophic forgetting of previously learned knowledge. Recent advances in large pre-trained models (LPMs) and model merging techniques, such as MAGMAX, have nstrated effective CL performance by combining task-specific parameters. However, existing methods primarily focus on average performance across all tasks and do not adequately address how to construct models accommodating different deployment environments or varying user preferences.