A language-guided token pruning method cuts LLaVA-1.5 inference FLOPs by 62.1% with only about 0.45% average benchmark loss.
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
-
LVPruning: An Effective yet Simple Language-Guided Vision Token Pruning Approach for Multi-modal Large Language Models
A language-guided token pruning method cuts LLaVA-1.5 inference FLOPs by 62.1% with only about 0.45% average benchmark loss.