VISion On Request: Enhanced VLLM efficiency with sparse, dynamically selected, vision-language interactions
Paper • 2603.23495 • Published • 3
Yassine Ouali
youali
·
AI & ML interests
None yet
Recent Activity
liked a model 9 months ago
iiiorg/piiranha-v1-detect-personal-information liked a dataset 12 months ago
lmms-lab/LLaVA-OneVision-DataOrganizations
None yet