Graft merges two domain-specialized multimodal models by combining channel-wise gating, entropy-based global weighting, and an activation compatibility score to improve fusion without retraining.
Duet: A tuning-free device-cloud collaborative parameters generation framework for efficient device model generalization
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
-
Graft: Integrating the Domain Knowledge via Efficient Parameter Synergy for MLLMs
Graft merges two domain-specialized multimodal models by combining channel-wise gating, entropy-based global weighting, and an activation compatibility score to improve fusion without retraining.