I am currently a Professor at the School of Computer Science, Central South University. Previously, I served as a Postdoctoral Researcher in the Department of Computer Science and Technology at Tsinghua University.

My research bridges computer vision and deep learning systems, with a primary focus on on-device and edge intelligence, system optimizations for resource-constrained devices, and efficient visual computing.

I earned my B.Sc., M.Sc., Ph.D. degrees all in computer science, from Central South University, China, in 2016, 2018 and 2023. I was a visiting scholar at HCS Lab, Seoul National University in 2022-2023. I also joined HEX group at Microsoft Research Asia(MSRA) from Sept. 2019 to Mar. 2020, and Institute for AI Industry Research(AIR), Tsinghua University from Aug. 2021 to Apr. 2022 as a research intern, respectively.

I am actively looking for self-motivated students with interests in edge intellengece and AIoT. If you are interested, please send me an email.

News

• [Feb. 2026]^New Our paper, "SRDrone: LLM-Driven Self-Refinement for Embodied Drone Task Planning", is accepted by IEEE TMC! Congratulations to Xicheng!
• [Jan. 2026]^New Our paper, "Context Learning for Multi-Agent Discussion", is accepted by ICLR 2026! Congratulations to Xingyuan!
• [Dec. 2025]^New Our paper, "EarAuth: Towards Practical Cardiac Vibration Authentication on COTS Wireless Earbuds", is accepted by IEEE INFOCOM 2026! Congratulations to Yongjian!
• [Aug. 2025] Our paper, "MobiFuse: A High-Precision On-device Depth Perception System with Multi-Data Fusion", is accpeted by IEEE TMC!
• [Aug. 2025] We have been awarded the Best Paper Award at AIoTSys 2025！
• [July 2025] Our paper, "Towards On-device NPU-Friendly Neural Network Operator Optimization", is accpeted by AIoTSys'25! Congratulations to Ye!
• [June 2025] Our paper, "FocusX: All-in-Focus Image Synthesis for Dynamic Scenes on Mobile Devices", is accpeted by MobiCom'25!
• [May 2025] Our paper, "Towards ubiquitous intelligence: Current status and prospects of on-device large language models", is accpeted by Bulletin of National Natural Science Foundation of China《中国科学基金》!
• [Jan. 2025] Our paper, "On-Device Intelligence Acceleration Technologies: A Survey", is accpeted by Acta Electronica Sinica《电子学报》!
• [Nov. 2024] Our paper, "MAML-RAL: Learning Domain-Invariant HOI Rules for Real-Time Video Matting", is accepted by IEEE Transactions on Circuits and Systems for Video Technology! Congratulations to Jiang!
• [Oct. 2024] I was recognized as the 2024 ACM SIGAPP China Outstanding Doctoral Dissertation Award!
• [Sep. 2024] Our paper, "Heterogeneous Parallel Acceleration for Edge Intelligence Systems: Challenges and Solutions", is accepted by IEEE Consumer Electronics Magazine!
• [Sep. 2024] Our paper, "FL-Joint: Joint Aligning Features and Labels in Federated Learning for Data Heterogeneity", is accepted by Complex & Intelligent System! Congratulations to Wenxin!
• [Aug. 2024] Our paper, "Mobile Generative AI: Opportunities and Challenges", is accepted IEEE Wireless Communications! Congratulations to Ye!
• [July 2024] Our paper, "MultiCounter: Multiple Action Agnostic Repetition Counting in Untrimmed Videos", is accepted by ECAI 2024! Congratulations to Yin!
• [Mar. 2024] Our paper, "MBSeg: Real-Time Contour-Based Method Instance Segmentation for Egocentric Vision", is accepted by IEEE Internet of Things Journal(IoTJ)! Congratulations to Wei.
• [Dec. 2023] Finished my PhD with Outstanding Graduate Award from Central South University.
• [Aug. 2023] Our paper, "Ego3DPose: Capturing 3D Cues from Binocular Egocentric Views", is accepted by ACM SIGGRAPH Asia 2023! Congratulations to Taeho Kang!
• [July 2023] Our paper, "HiMoDepth: Efficient Training-free High-resolution On-device Depth Perception", is accepted by IEEE Transactions on Mobile Computing.
• [Sep. 2022] I join the HCS Lab as a visiting research at Seoul National University in Korea, advised by Prof. Youngki Lee.
• [Aug. 2022] I will give a talk on Hunan Province "Big Data and Artificial Intelligence" Innovation Forum.
• [June 2022] Our paper, "MobiDepth: Real-Time Depth Estimation Using On-Device Dual Cameras", is accepted by ACM MobiCom'22 !
• Show more
[Jan. 2022] Our paper, "MVPose: Realtime Multi-Person Pose Estimation using Motion Vector on Mobile Devices", is accepted by IEEE Transactions on Mobile Computing.
[Aug. 2021] I joined the Insitute for AI Industry Research(AIR), at Tsinghua University. Mentor: Prof.Yunxin Liu.
[Apr. 2021] Our paper," Optimizing Federated Learning on Device Heterogeneity with A Sampling Strategy", is accepted by IEEE IWQoS 2021.
[Sep. 2020] Our paper, "MobiPose: Real-Time Multi-Person Pose Estimation on Mobile Devices", is accepted by ACM SenSys'20 !

Contact

Address: Central South University, Changsha, 400083, China
Office Location: Room 405, Comprehensive Laboratory Building, Xiaoxiang Campus
Email: zhangjinrui (at) csu (dot) edu (dot) cn