VISA aggregates removed visual tokens into kept ones via a semantic similarity graph, guided group-wise by text tokens, and claims a better accuracy versus speed trade-off for multimodal LLM inference.
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
UNVERDICTED 1representative citing papers
citing papers explorer
-
VISA: Group-wise Visual Token Selection and Aggregation via Graph Summarization for Efficient MLLMs Inference
VISA aggregates removed visual tokens into kept ones via a semantic similarity graph, guided group-wise by text tokens, and claims a better accuracy versus speed trade-off for multimodal LLM inference.