EvoComp compresses visual tokens in MLLMs by 3x while retaining 99.3% accuracy via an evolutionary labeling strategy that searches for low-loss, semantically diverse token subsets.
What kind of visual tokens do we need? training- free visual token pruning for multi-modal large language models from the perspective of graph
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
EvoComp: Learning Visual Token Compression for Multimodal Large Language Models via Semantic-Guided Evolutionary Labeling
EvoComp compresses visual tokens in MLLMs by 3x while retaining 99.3% accuracy via an evolutionary labeling strategy that searches for low-loss, semantically diverse token subsets.