We develop a robust circuit design framework that involves the variation information in the optimization process.

We develop a deep learning framework for robust RF-based vital signs sensing.

This paper provides an overview of efficient deep learning methods, systems and applications.

SPVNAS enhances Point-Voxel Convolution in large-scale outdoor scenes with sparse convolutions. With 3D Neural Architecture Search (3D-NAS), it efficiently and effectively searches the optimal 3D neural network architecture under a given resource constraint.

APQ is an efficient AutoML framework for joint optimization of neural architecture, pruning, and quantization.

HAT NAS framework leverages the hardware feedback in the neural architecture search loop, providing a most suitable model for the target hardware platform. The results on different hardware platforms and datasets show that HAT searched models have better accuracy-efficiency trade-offs.