Geng Yuan

TL;DR: The CirCNN architecture is proposed, a universal DNN inference engine that can be implemented in various hardware/software platforms with configurable network architecture (e.g., layer type, size, scales, etc) and FFT can be used as the key computing kernel which ensures universal and small-footprint implementations.

TL;DR: CirCNN as discussed by the authors utilizes the Fast Fourier Transform (FFT)-based fast multiplication, simultaneously reducing the computational complexity (both in inference and training) and the storage complexity from O(n2) to O(nlogn) with negligible accuracy loss.

TL;DR: This work proves that properly designed transformers can reach extremely low latency on mobile devices while maintaining high performance 1 based architectures, whereby the latency-driven analysis of ViT architecture and the experimental results validate the claim: powerful vision transformer can achieve ultra-fast inference speed on the edge.

TL;DR: This work proposes YOLObile framework, a real-time object detection on mobile devices via compression-compilation co-design, and proposes a novel block-punched pruning scheme for any kernel size.

TL;DR: It is concluded that structured pruning has a greater potential compared to non-structured pruning and the first fully binarized (for all layers) DNNs can be lossless in accuracy in many cases.