About me

I am Yan Lu and a Computer Science Ph.D. student at New York University advised by Sam Bowman. I’m interested in unconstrained resource-aware machine learning systems and collaborative on-device learning algorithms. Prior to NYU, I got B.Tech from Sichuan University. Currently, I'm maintaining a open-source project named Awesome-Multi-Camera-Network. I am very fortunate to collaborate closely with Dr. Yuanchao Shu and Dr. Shiqi Jiang from Microsoft Research.

Recently, I am very interested in efficient inference engines for vision transformer networks.

Work and Internship

• Institute of Computing Technology, Chinese Academy of Sciences (2017.06-2017.09): Intelligent Palm Print Recognition Systems (Advised by Dr. Xinhua Zeng)

• Microsoft Research in Asia (2018.2-2018.9): Collaborative Learning (Advised by Dr. Yuanchao Shu and Dr. Yunxin Liu)

Selected Publications [Google Scholar]

1. [SEC 2019] Yan Lu, Yuanchao Shu, Xu Tan, Yunxin Liu, Mengyu Zhou, Qi Chen and Dan Pei. "Collaborative Learning between Cloud and End Devices: An Empirical Study on Location Prediction". In The Fourth ACM/IEEE Symposium on Edge Computing, 2019. [PDF]

2. [TIOT 2022] Zheng Dong, Yan Lu, Guangmo Tong, Yuanchao Shu, Shuai Wang, Weisong Shi. "WatchDog: Real-time Vehicle Tracking on Geo-distributed Edge Nodes". ACM Transactions on Internet of Things, 2022. [PDF]

3. [SenSys 2022] Yan Lu, Shiqi Jiang, Ting Cao, Yuanchao Shu. "Turbo: Opportunistic Enhancement for Edge Video Analytics". ACM SenSys 2022 (conditionally accepted). [arXiv preprint] [Slides] [Code]

4. Yan Lu, Zhun Zhong, Yuanchao Shu. "Multi-View Domain Adaptive Object Detection in Surveillance Cameras". [arXiv preprint]

Useful External Links

• The simple guide to git: git-guide

• Purdue Online Writing Lab (OWL): Purdue-OWL

• Linux and C Programming (Chinese version): Online Course

• Dive into Deep Learning (Dr. Mu Li): Online Book

• UW Deep Learning Systems (Prof. Tianqi Chen): CSE 599W

• UCB Machine Learning Systems (Prof. Joseph E. Gonzalez): CS294