Gen AI at the Edge: Qualcomm AI Research at CVPR 2024
Analysis
This article from Practical AI discusses Qualcomm AI Research's contributions to the CVPR 2024 conference. The focus is on advancements in generative AI and computer vision, particularly emphasizing efficiency for mobile and edge deployments. The conversation with Fatih Porikli highlights several research papers covering topics like efficient diffusion models, video-language models for grounded reasoning, real-time 360° image generation, and visual reasoning models. The article also mentions demos showcasing multi-modal vision-language models and parameter-efficient fine-tuning on mobile phones, indicating a strong focus on practical applications and on-device AI capabilities.
Key Takeaways
- •Qualcomm AI Research is presenting multiple papers at CVPR 2024 focusing on generative AI and computer vision.
- •The research emphasizes efficiency for mobile and edge deployments.
- •Key areas of research include efficient diffusion models, video-language models, and on-device image generation.
“We explore efficient diffusion models for text-to-image generation, grounded reasoning in videos using language models, real-time on-device 360° image generation for video portrait relighting...”