CABS+ prunes task vectors with a conflict-aware, balanced sparsification step and sets merging coefficients through CMA-ES search, improving efficiency and average merged-model performance.
Toward Effective Model Merging in Semantic Segmen- tation,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
CABS+: Efficient and Scalable Model Merging via Conflict-Aware Sparsification and Adaptive Weight Allocation
CABS+ prunes task vectors with a conflict-aware, balanced sparsification step and sets merging coefficients through CMA-ES search, improving efficiency and average merged-model performance.