aimagelab/ReflectiVA
Image-Text-to-Text • 8B • Updated
• 147 • 2
ReflectiVA
Models and data for ReflectiVA: Augmenting Multimodal LLMs with Self-Reflective Tokens for Knowledge-based Visual Question Answering [CVPR 2025]
Models and data for ReflectiVA: Augmenting Multimodal LLMs with Self-Reflective Tokens for Knowledge-based Visual Question Answering [CVPR 2025]