DF-Merge unifies task arithmetic and Fisher merging and uses Bayesian optimization to tune per-task coefficients, reporting improved multi-task accuracy on T5 benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Dynamic Fisher-weighted Model Merging via Bayesian Optimization
DF-Merge unifies task arithmetic and Fisher merging and uses Bayesian optimization to tune per-task coefficients, reporting improved multi-task accuracy on T5 benchmarks.