Hao Kong

HP-NTU Digital Manufacturing Corporate Lab, Nanyang Technological University, 639798, Singapore, School of Computer Science and Engineering, Nanyang Technological University, 639798, Singapore

Papers on Lattice

Total citations

Topics

h-index

Research focus

Architecture Design (Transformers, SSMs, MoE) (1)Inference & Quantization (1)

Frequent co-authors

Shuo Huai (1)Di Liu (1)Weichen Liu (1)Ravi Subramaniam (1)

Papers (1)

Dec 1, 2022

Dec 1, 2022·also HP Inc.

Latency-constrained DNN architecture learning for edge systems using zerorized batch normalization

Achieving real-time performance on edge devices, this method reduces GoogLeNet's latency from 40.32 ms to 34 ms with minimal accuracy loss, while VGG-19 sees a latency drop from 119.98 ms to 34 ms with an accuracy gain.

Shuo Huai, Di Liu, Hao Kong +4

Architecture Design (Transformers, SSMs, MoE)Inference & Quantization

Search

Hao Kong

Research focus

Frequent co-authors

Papers (1)