Bingqian Lu

About

Bingqian Lu is a researcher specializing in edge computing, deep neural network (DNN) optimization, and efficient machine learning deployment. Their work addresses one of the most pressing challenges in modern AI: bridging the gap between computationally intensive neural network models and the resource-constrained edge devices that increasingly need to run them. Lu's most notable contribution, "Automating Deep Neural Network Model Selection for Edge Inference" (2019), tackles the complex problem of selecting optimal DNN configurations for edge deployment, earning 17 citations and establishing Lu as a thoughtful voice in the edge inference space. This work builds on advances in model compression to make real-world DNN inference viable on devices such as smartphones, drones, and wearables — settings where cloud dependency is impractical or undesirable. Their follow-up poster presentation in 2020 further expanded this vision, exploring scalable optimization strategies for DNNs operating under edge constraints. Lu's research is particularly valuable to the growing community of engineers and scientists working at the intersection of AI and embedded systems, offering principled, automated approaches to a problem that would otherwise require exhaustive manual tuning. Their contributions help democratize AI by making powerful models accessible beyond data center walls.

Research Focus

Key Achievements

Top Papers

1. 1
   Automating Deep Neural Network Model Selection for Edge Inference

   17 citations · 2019
2. 2
   Poster: Scaling Up Deep Neural Network optimization for Edge Inference

   3 citations · 2020

Key Collaborators

Contact & Links