Selectively fine-tuning only 40% of a multimodal LLM's layers and neurons can match or slightly beat full fine-tuning on multilingual image-to-text translation benchmarks, though the measured gains are marginal.
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
CONDITIONAL 1representative citing papers
citing papers explorer
-
LLaVA-NeuMT: Selective Layer-Neuron Modulation for Efficient Multilingual Multimodal Translation
Selectively fine-tuning only 40% of a multimodal LLM's layers and neurons can match or slightly beat full fine-tuning on multilingual image-to-text translation benchmarks, though the measured gains are marginal.