AI at the Edge: Qualcomm AI Research at NeurIPS 2024
Analysis
This article from Practical AI discusses Qualcomm's AI research presented at the NeurIPS 2024 conference. It highlights several key areas of focus, including differentiable simulation in wireless systems and other scientific fields, the application of conformal prediction to information theory for uncertainty quantification in machine learning, and efficient use of LoRA (Low-Rank Adaptation) on mobile devices. The article also previews on-device demos of video editing and 3D content generation models, showcasing Qualcomm's AI Hub. The interview with Arash Behboodi, director of engineering at Qualcomm AI Research, provides insights into the company's advancements in edge AI.
Key Takeaways
- •Qualcomm is presenting research on differentiable simulation, conformal prediction, and LoRA at NeurIPS 2024.
- •The research focuses on improving AI performance and efficiency, particularly on mobile devices.
- •Qualcomm is showcasing on-device demos of video editing and 3D content generation models.
“We dig into the challenges and opportunities presented by differentiable simulation in wireless systems, the sciences, and beyond.”