CABS+: Efficient and Scalable Model Merging via Conflict-Aware Sparsification and Adaptive Weight Allocation
arXiv cs.AI1mo4 min read
arXiv:2608.12842v1 Announce Type: new Abstract: Model merging has recently attracted significant attention as a promising paradigm for constructing unified multi-task models without requiring additional retraining. However, parameter conflicts and knowledge interference across tasks often degrade merged-model performance. Prior work introduced Conflict-Aware and Balanced Sparsification (CABS), which reduces parameter interference through structured pruning and sequential masking. However, CABS relies on grid search to determine scaling coefficients, resulting in exponential time complexity, wh
