G-Prune prunes visual tokens for MLLMs via graph-based information propagation, cutting LLaVA-NeXT FLOPs by about 63% with small accuracy loss.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
What Kind of Visual Tokens Do We Need? Training-free Visual Token Pruning for Multi-modal Large Language Models from the Perspective of Graph
G-Prune prunes visual tokens for MLLMs via graph-based information propagation, cutting LLaVA-NeXT FLOPs by about 63% with small accuracy loss.