Di Liu
About
Di Liu is an Associate Professor at Department of Computer Science, Norwegian University of Science and Technology (NTNU), Norway. In prior to that, he was a research fellow at Nanyang Technological University, Singapore and a faculty member at Yunnan University, China. He received his PhD degree from Leiden University, The Netherlands, and both his MEng and BEng degrees from Northwestern Polytechnical University, China.
Research
His general research interests are edge intelligence, embedded systems, real-time scheduling.
- Efficient deep learning algorithms for edge systems
- Adaptive deep learning models for edge systems
- Hardware-aware deep learning model optimizations
Publications
2023
-
Ma, Ye-Da;
Zhao, Zhi-Chao;
Liu, Di;
He, Zhenli;
Zhou, Wei.
(2023)
OCAP: On-device Class-Aware Pruning for personalized edge DNN models.
Journal of systems architecture
Academic article
-
Zhang, Zhi-Yuan;
Ren, Hao;
He, Zhenli;
Zhou, Wei;
Liu, Di.
(2023)
Improving robustness of convolutional neural networks using element-wise activation scaling.
Future generations computer systems
Academic article
-
He, Zhenli;
Xu, Yanan;
Liu, Di;
Zhou, Wei;
Li, Keqin.
(2023)
Energy-efficient computation offloading strategy with task priority in cloud assisted multi-access edge computing.
Future generations computer systems
Academic article
2022
-
Huai, Shuo;
Liu, Di;
Kong, Hao;
Liu, Weichen;
Subramaniam, Ravi;
Makaya, Christian.
(2022)
Latency-constrained DNN architecture learning for edge systems using zerorized batch normalization.
Future generations computer systems
Academic article
Journal publications
-
Ma, Ye-Da;
Zhao, Zhi-Chao;
Liu, Di;
He, Zhenli;
Zhou, Wei.
(2023)
OCAP: On-device Class-Aware Pruning for personalized edge DNN models.
Journal of systems architecture
Academic article
-
Zhang, Zhi-Yuan;
Ren, Hao;
He, Zhenli;
Zhou, Wei;
Liu, Di.
(2023)
Improving robustness of convolutional neural networks using element-wise activation scaling.
Future generations computer systems
Academic article
-
He, Zhenli;
Xu, Yanan;
Liu, Di;
Zhou, Wei;
Li, Keqin.
(2023)
Energy-efficient computation offloading strategy with task priority in cloud assisted multi-access edge computing.
Future generations computer systems
Academic article
-
Huai, Shuo;
Liu, Di;
Kong, Hao;
Liu, Weichen;
Subramaniam, Ravi;
Makaya, Christian.
(2022)
Latency-constrained DNN architecture learning for edge systems using zerorized batch normalization.
Future generations computer systems
Academic article