Structural pruning with finetuning plus hidden-state distillation recovers most performance in multimodal LLMs, with 5% of training data sufficient at moderate compression levels.
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
-
Investigating Structural Pruning and Recovery Techniques for Compressing Multimodal Large Language Models: An Empirical Study
Structural pruning with finetuning plus hidden-state distillation recovers most performance in multimodal LLMs, with 5% of training data sufficient at moderate compression levels.