Liya Yuan

Liya Yuan

Liya Yuan is an open source & standardization engineer in ZTE, focusing on the field of AI for telecommunication network. She is currently the Technical Steering Committee (TSC) chair of AI project Adlik, which is incubated in Linux Foundation AI Foundation. She also takes an active part in ITU-T standardization activities and serves as WG3 chair in ITU-T Autonomous Network focus group.

Share this speaker
Share This Speaker
  • Organization
    ZTE
  • Profession
    Open Source & Standardization Engineer
Related sessions
Online
30 November 2023
09:00 - 11:00
EST - New York
CST - Beijing
PST - Los Angeles
Artificial Intelligence has already been widely adopted in 5G networks...
Discovery - AI/ML in 5G
OnlineGOAL 4GOAL 9
25 October 2023
13:00 - 15:00
EST - New York
CST - Beijing
PST - Los Angeles
The ITU AI/ML in 5G Challenge in 2023 (Fourth edition)...
Discovery - AI/ML in 5G
OnlineGOAL 4GOAL 9
14 December 2022
13:30 - 15:30
EST - New York
CST - Beijing
PST - Los Angeles
The ITU AI/ML in 5G Challenge rallies like-minded students and...
OnlineGOAL 17GOAL 9
12 September 2022
09:00 - 11:00
EST - New York
CST - Beijing
PST - Los Angeles
AI has been rolled out in different business industries with...
Banner Open Source EVent
OnlineGOAL 9
21 October 2021
08:00 - 12:00
EST - New York
CST - Beijing
PST - Los Angeles
Hear from one of the largest technology and telecommunications companies...
OnlineGOAL 10GOAL 17
17 July 2020
14:00 - 15:00
EST - New York
CST - Beijing
PST - Los Angeles
The talk will describe the problem ITU-ML5G-PS-018 DNN Inference Optimization.  This problem is about how to optimize inference efficiency of deep learning models since computing efficiency, memory footprint and inference latency tends to be the bottleneck when deploying large deep learning models. The problem will be described in details in the presentation, including why we propose this problem, status quo of related research, what are expected from the competitors/participants and some suggestions will be given. Hopefully more competitors will get intested in this problem and propose their innovative solutions.