Selective fine-tuning of language-specific shallow layers identified by neuron activation analysis improves multilingual vision-language performance with only 14% of parameters tuned.
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
UNVERDICTED 1representative citing papers
citing papers explorer
-
Language-Specific Layer Matters: Efficient Multilingual Enhancement for Large Vision-Language Models
Selective fine-tuning of language-specific shallow layers identified by neuron activation analysis improves multilingual vision-language performance with only 14% of parameters tuned.