A training-free, sample-wise model merging method that rescales task vectors based on representation similarity outperforms several static merging baselines on vision and language benchmarks.
On lazy training in differentiable programming
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
SE-Merging: A Self-Enhanced Approach for Dynamic Model Merging
A training-free, sample-wise model merging method that rescales task vectors based on representation similarity outperforms several static merging baselines on vision and language benchmarks.