DMM merges highly divergent domain-specific models without data sharing by synthesizing pseudo-data from normalization statistics and distilling knowledge, achieving state-of-the-art performance on unimodal and multimodal benchmarks.
It contains a total of 18,036 image–text pairs anno- tated with humanitarian categories, enabling evaluation of cross-modal classification tasks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Domain-Adaptive Model Merging Across Disconnected Modes
DMM merges highly divergent domain-specific models without data sharing by synthesizing pseudo-data from normalization statistics and distilling knowledge, achieving state-of-the-art performance on unimodal and multimodal benchmarks.