A 1.8B-parameter vision-language model, Eve, uses elastic visual experts and type-aware token routing to reach a 68.87% average on six VLM benchmarks while preserving language performance.
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
-
Eve: Efficient Multimodal Vision Language Models with Elastic Visual Experts
A 1.8B-parameter vision-language model, Eve, uses elastic visual experts and type-aware token routing to reach a 68.87% average on six VLM benchmarks while preserving language performance.