AI RESEARCH
Align-KD: Distilling Cross-Modal Alignment Knowledge for Mobile Vision-Language Model Enhancement
arXiv CS.CV
•
ArXi:2412.01282v2 Announce Type: replace Vision-Language Models (VLMs) bring powerful understanding and reasoning capabilities to multimodal tasks. Meanwhile, the great need for capable aritificial intelligence on mobile devices also arises, such as the AI assistant software. Some efforts try to migrate VLMs to edge devices to expand their application scope. Simplifying the model structure is a common method, but as the model shrinks, the trade-off between performance and size becomes and difficult.