A cascaded knowledge distillation method with intermediate teachers improves efficiency of vision-language models like LLaVA while achieving state-of-the-art results on seven VQA benchmarks.
EM-KD: distilling efficient multimodal large language model with unbalanced vision tokens
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1roles
baseline 1polarities
baseline 1representative citing papers
citing papers explorer
-
LLaVA-CKD: Bottom-Up Cascaded Knowledge Distillation for Vision-Language Models
A cascaded knowledge distillation method with intermediate teachers improves efficiency of vision-language models like LLaVA while achieving state-of-the-art results on seven VQA benchmarks.