About Me
I am currently an assistant professor at the Intelligent Processor Research Center, Institute of Computing Technology, Chinese Academy of Sciences. I obtained my Ph.D. degree from the Institute of Computing Technology, Chinese Academy of Sciences in 2024, advised by Prof. Wen Ji. I have an exchange visit to the High Performance Computing for Artificial Intelligence (HPC-AI) Lab at the National University of Singapore, advised by Yang You.
My research interests include multimedia systems, edge/cloud computing, LLM inference optimization, and efficient AI system design. I have served as a reviewer of ACM MM, NeurIPS, ICML, ICLR, AISTATS, lEEE Transactions on ETCl, lEEE Vehicular Technology Magazine, etc. I am also actively involved in the standardization of the End-Edge-Cloud system. I am a member of the IEEE Digital Retina Systems (3161 WG) Standards Working Group, which is the world’s first international standards organization focused on vision end-edge-cloud systems.
🔥Long-term Recruiting: I am looking for visiting students (bachelor, master, or Ph.D.), feel free to contact me at yangzheming@ict.ac.cn if interested in my research.
Research Interests
- Multimedia System and Distributed Inference
- End-Edge-Cloud Collaborative Optimization
- Design of Efficient Machine Learning System
- LLM Inference Optimization
- Visual Internet of Things (V-IoT)
Education
- 2019.09 – 2024.12, Institute of Computing Technology, Chinese Academy of Sciences, PhD in Computer Science.
- 2023.10 – 2024.09, National University of Singapore (NUS), Visiting Scholar.
- 2021.02 – 2022.08, Peng Cheng National Laboratory, Visiting PhD Student.
- 2018.01 – 2018.02, Peking University, Research Intern.
- 2015.09 – 2019.06, North China University of Science and Technology, B.Sc in Electronic Engineering.
News
- [2024.11]: 🎉🎉 Our paper “MSBA: Adaptive Multi-Stream Data Transmission Method with Bandwidth Awareness for End-Cloud Systems” won the IFTC Best Paper Award!
- [2024.02]: 🎉🎉 Our paper “Adaptive Joint Configuration Optimization for Collaborative Inference in Edge-Cloud Systems” has been accepted by Science China-Information Sciences!
- [2023.07]: 🎉🎉 Our paper “JAVP: Joint-Aware Video Processing with Edge-Cloud Collaboration for DNN Inference” has been accepted by ACM MM 2023!
- [2023.03]: 🎉🎉 Our paper “Visual E2C: AI-Driven Visual End-Edge-Cloud Architecture for 6G in Low-Carbon Smart Cities” has been accepted by IEEE Wireless Communications!
- [2021.01]: 🎉🎉 Our paper “An Intelligent End–Edge–Cloud Architecture for Visual IoT-Assisted Healthcare Systems” has been accepted by IEEE Internet of Things Journal!
- [2020.12]: 🎉🎉 Our paper won the IEEE ISPA Outstanding Paper Award!
Publications
- Under Review
- Zheming Yang, Wen Ji, Qi Guo, Dieli Hu, Chang Zhao, Xiaowei Li, Xuanlei Zhao, Yi Zhao, Chaoyu Gong, and Yang You. “CDIO: Cross-Domain Inference Optimization with Resource Preference Prediction for Edge-Cloud Collaboration”. arXiv preprint arXiv:2502.04078. [PDF]
- Zheming Yang, Yuanhao Yang, Chang Zhao, Qi Guo, Wenkai He, and Wen Ji. “PerLLM: Personalized Inference Scheduling with Edge-Cloud Collaboration for Diverse LLM Services”. arXiv preprint arXiv:2405.14636. [PDF]
- Xuanlei Zhao, Shenggan Cheng, Chang Chen, Zangwei Zheng, Ziming Liu, Zheming Yang, and Yang You. “DSP: Dynamic Sequence Parallelism for Multi-Dimensional Transformers”. arXiv preprint arXiv:2403.10266. [PDF]
- Yi Zhao, Juepeng Zheng, Guowen Li, Yushan Lai, Kangrui Du, Lixian Zhang, Runmin Dong, Jinxiao Zhang, Mengxuan Chen, Wayne Zhang, Litong Feng, Zheming Yang, Chaoyu Gong, Yang You and Haohuan Fu. “Learning Global Land Cover Mapping Through a Highly-Scalable Weakly-Supervised Method”.
- Wenkai He, Xiaqing Li, Peiyi Han, Rui Zhang, Yifan Hao, Yuanbo Wen, Zheming Yang, Xing Hu, Zidong Du, and Qi Guo. “GM2: Generalizing Pre-Routing Static Timing Analysis Across Multiple Design Modes by Incorporating Customized Features”.
- Selected Published
- Zheming Yang, Wen Ji, and Zhi Wang. “Adaptive Joint Configuration Optimization for Collaborative Inference in Edge-Cloud Systems”. Science China-Information Sciences, 2024. (CCF-A)
- Wen Ji, Zheming Yang*, Zhi Wang, Bin Guo, and Bo Shen. Visual End-Edge-Cloud Fusion Architecture: Key Technologies of Future Super Metropolitan Clusters (in Chinese). Science China Informationis, 2024, 54: 2518–2532. (CCF-A, First Student Author)
- Zheming Yang, Lulu Zuo, and Wen Ji. “Joint Optimization Method for Node Deployment and Resource Allocation Based on End-Edge Collaboration”. Computer Science, 2024. (CCF-B)
- Zheming Yang, Wen Ji, Qi Guo, and Zhi Wang. “JAVP: Joint-Aware Video Processing with Edge-Cloud Collaboration for DNN Inference”. ACM International Conference on Multimedia (MM). 2023: 9152-9160. (CCF-A) [PDF]
- Zheming Yang, Dieli Hu, Qi Guo, Lulu Zuo, and Wen Ji. “Visual E2C: AI-driven Visual End-Edge-Cloud Architecture for 6G in Low-carbon Smart Cities”. IEEE Wireless Communications, 2023, 30 (3), 204-210. (JCR-Q1 IF=12.9) [PDF]
- Zheming Yang, Bing Liang, and Wen Ji. “An Intelligent End–Edge–Cloud Architecture for Visual IoT-Assisted Healthcare Systems”. IEEE Internet of Things Journal, 2021, 8(23): 16779-16786. (JCR-Q1 IF=10.6) [PDF]
- Zheming Yang, and Wen Ji. “A Quality-Time Model of Heterogeneous Agents Measure for Crowd Intelligence”. IEEE International Symposium on Parallel and Distributed Processing with Applications (ISPA), 2020, pp. 1264-1270. (CCF-C) [PDF]
- Zheming Yang, and Wen Ji. “Meta measurement of intelligence with crowd network”. International Journal of Crowd Science, 2020, 4(3): 295-307. [PDF]
- Zheming Yang, and Wen Ji. “A Universal Intelligence Measurement Method Based on Meta-analysis”. Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), 2019: 493-498. [PDF]
- Wen Ji, Bing Liang, Yuqin Wang, Rui Qiu and Zheming Yang. “Crowd V-IoE: Visual Internet of Everything Architecture in AI-Driven Fog Computing”. IEEE Wireless Communications, 2020, 27(2): 51-57. (JCR-Q1 IF=12.9) [PDF]
- Ningzhou Li, Zheming Yang, Mingxuan Li, and Wen Ji. “JVAP: A Joint Video Acceleration Processing Architecture for Online Edge Systems”. IEEE International Conference on Systems, Man, and Cybernetics (SMC), 2023, pp. 1-6. [PDF]
- Linqing Zhai, Zheming Yang, and Wen Ji. “Understanding Crowd Intelligence in Large-scale Systems: A Hierarchical Binary Particle Swarm Optimization Approach”. IEEE International Symposium on Parallel and Distributed Processing with Applications (ISPA), 2020, pp. 728-735. [PDF]
- Hexiang Qiao, Zheming Yang, Bing Liang, and Wen Ji. “Crowd Intelligence Empowered Video Transmission in Ultra-Low-Bandwidth Constrained Circumstances”. IEEE International Symposium on Parallel and Distributed Processing with Applications (ISPA), 2020, pp. 721-727. [PDF]
Standard Contributions
- Zheming Yang, Wen Ji, Yaowei Wang, Xinbei Bai, Yan Lan, Jinyu Yuan, Zhi Wang, Bo Shen, Bin Guo, Peng Yang, Chunhao Zhao, and Haojie Zhao, “Digital Retina System Evaluation Index System”. Artificial Intelligence Technology Industry Strategic Alliance (AITISA) document, AI M1686, 2023.03.
- Zheming Yang, Bing Liang, Wen Ji, Xinbei Bai, Yaowei Wang, Jinyu Yuan, and Zhi Wang, “Edge-Cloud Collaborative Processing and Task Migration for Digital Retina System”. Artificial Intelligence Technology Industry Strategic Alliance (AITISA) document, AI M1630, 2022.06.
- Bo Shen, Bin Guo, Wen Ji, Zheming Yang, Yinglai Xi, Yaowei Wang, Xinbei Bai, and Jinyu Yuan, “Cloud Subsystem Functional Architecture and Functional Requirements”. Artificial Intelligence Technology Industry Strategic Alliance (AITISA) document, AI M1910, 2023.12.
- Lulu Zuo, Wen Ji, Yaowei Wang, Dieli Hu, Zheming Yang, Haijun Liu, Xinbei Bai, Yan Lan, and Ying Wang, “End-Edge System Metrics and Evaluation Architecture”. Artificial Intelligence Technology Industry Strategic Alliance (AITISA) document, AI M1869, 2023.12.
- Xinbei Bai, Chunhao Zhao, Zheming Yang, Yunhong Zhou, and Peng Chen, “Overall Collaborative Architecture and Capability Requirements for Digital Retina Systems”. Artificial Intelligence Technology Industry Strategic Alliance (AITISA) document, AI M1680, 2022.12.