The University of Southampton
Email:
lx2u16@soton.ac.uk

Lei Xun 

https://www.linkedin.com/in/lx2u16/

PhD research
Software and Hardware Co-design for Efficient Acceleration of Embedded Machine Learning

Invited seminar titled "Dynamic DNNs Meet Runtime Resource Management" (Recording)

  • at University of Cambridge CaMLSys Lab
  • at Arm Research ML Group

Top-tier publications (Google Scholar)

  • [CVPR'W 2021] Dynamic-OFA: Runtime DNN Architecture Switching for Performance Scaling on Heterogeneous Embedded Platforms: paper, talk and code
  • [DATE 2020] Optimising Resource Management for Embedded Machine Learning: paper

Conference talks (Recording)

  • CVPR'W 2021
  • TinyML EMEA 2021 (Student poster, ranked 4th of all 50 submissions)
  • DATE 2020
  • MLCAD 2019

Internship

Incoming ML Research Intern at Nokia Bell Labs in Cambridge, UK

May 2021 - Feb 2022 CPU Performance Research Intern at Huawei R&D in Cambridge, UK

Freelance

Academic Translator at Nature Portfolio in Shanghai, China

Services

  • Technical Program Committee Member at CVPR 2022 efficient computer vision workshop
  • Reviewer at BMVC2021

Supervisor

Affiliation

Education

  • 2018-2022 PhD EEE - University of Southampton
  • 2016-2017 MSc System on Chip - Distinction - University of Southampton
  • 2013-2016 BEng Electronic Engineering - 2.1 - University of Sheffield

Others

Publications

Xun, Lei, Tran-Thanh, Long, Al-Hashimi, Bashir and Merrett, Geoff (2020) Optimising resource management for embedded machine learning. Di Natale, Giorgio, Bolchini, Cristiana and Vatajelu, Elena-Ioana (eds.) In Proceedings of the 2020 Design, Automation and Test in Europe Conference and Exhibition, DATE 2020. pp. 1556-1561 . (doi:10.23919/DATE48585.2020.9116235).

Xun, Lei (2019) Dataset for "Optimising Resource Management for Embedded Machine Learning". University of Southampton doi:10.5258/SOTON/D1154 [Dataset]

Xun, Lei (2020) Dataset for "Incremental Training and Group Convolution Pruning for Runtime DNN Performance Scaling on Heterogeneous Embedded Platforms". University of Southampton doi:10.5258/SOTON/D1245 [Dataset]

Xun, Lei, Tran-Thanh, Long, Al-Hashimi, Bashir and Merrett, Geoff (2020) Incremental training and group convolution pruning for runtime DNN performance scaling on heterogeneous embedded platforms. In 1st ACM/IEEE Workshop on Machine Learning for CAD (MLCAD 2019). pp. 1-6 .

Xun, Lei (2021) Dataset for "Dynamic-OFA: Runtime DNN Architecture Switching for Performance Scaling on Heterogeneous Embedded Platforms". University of Southampton doi:10.5258/SOTON/D1804 [Dataset]

Lou, Wei, Xun, Lei, Sabetsarvestani, Mohammadamin, Bi, Jia, Hare, Jonathon and Merrett, Geoff (2021) Dynamic-OFA: Runtime DNN architecture switching for performance scaling on heterogeneous embedded platforms. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops 2021. pp. 3104-3112 .

Xun, Lei, Al-Hashimi, Bashir, Hare, Jonathon and Merrett, Geoff (2021) Runtime DNN performance scaling through resource management on heterogeneous embedded platforms. tinyML EMEA Technical Forum 2021. 07 - 10 Jun 2021.

Parry, Hishan (2021) Dataset for "Dynamic Transformer for Efficient Machine Translation on Embedded Devices". University of Southampton doi:10.5258/SOTON/D1908 [Dataset]

Parry, Hishan, Xun, Lei, Sabetsarvestani, Mohammadamin, Bi, Jia, Hare, Jonathon and Merrett, Geoff (2021) Dynamic transformer for efficient machine translation on embedded devices. In 3rd ACM/IEEE Workshop on Machine Learning for CAD (MLCAD 2021). 6 pp .

Safarpour, Mehdi, Xun, Lei, Merrett, Geoff and Silven, Olli (2021) A high-level approach for energy efficiency improvement of FPGAs by voltage trimming. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems. (doi:10.1109/TCAD.2021.3127153).

Xun, Lei, Al-Hashimi, Bashir, Hare, Jonathon and Merrett, Geoff (2022) Dynamic DNNs meet runtime resource management on mobile and embedded platforms. UK Mobile, Wearable and Ubiquitous Systems Research Symposium 2022, UCL, London, United Kingdom. 04 - 05 Jul 2022. (In Press)

Contact

Share this profile FacebookTwitterWeibo