SyMerge merges models via single-layer adaptation and expert-guided self-labeling to achieve task synergy, reporting SOTA results on vision, dense prediction, and NLP tasks.
Merging multi-task models via weight-ensembling mixture of experts
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SyMerge: From Non-Interference to Synergistic Merging via Single-Layer Adaptation
SyMerge merges models via single-layer adaptation and expert-guided self-labeling to achieve task synergy, reporting SOTA results on vision, dense prediction, and NLP tasks.