Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perception

Benchmark Model Rank Results
visual-question-answering-vqa-on-hr-bench-4kZwZ-4B–Overall: 81.75
visual-question-answering-vqa-on-hr-bench-4kZwZ-7B–Overall: 75.38
visual-question-answering-vqa-on-hr-bench-4kZwZ-8B–Overall: 84.38
visual-question-answering-vqa-on-hr-bench-8kZwZ-4B–Overall: 79.50
visual-question-answering-vqa-on-hr-bench-8kZwZ-7B–Overall: 73.25
visual-question-answering-vqa-on-hr-bench-8kZwZ-8B–Overall: 82.00