I am a Research Assistant Professor at the Institute for AI Industry Research (AIR), Tsinghua University. I received a Ph.D. degree and a Bachelor’s degree in Computer Science, both from Peking University. I had also worked as a Visiting PhD Student at Carnegie Mellon University. Before joining AIR, I was a Senior Researcher in the Systems Research Group at Microsoft Research Asia (MSRA).
My current research interests can be summarized as Edge AI, which includes the following two aspects:
- Edge AI Efficiency - Building systems to improve the efficiency of AI models, or designing AI models that can run efficiently at the edge.
- Edge AI Reliability - Improving the reliability of AI models deployed at the edge, by making them more robust, generalizable, and privacy-preserving.
I’ve published in premier venues of mobile computing, artificial intelligence, and software engineering, including a best paper nomination in UbiComp 2016 and a best paper in IS-EUD 2017. Some of the papers have become popular open-source tools (DroidBot, PrivacyStreams, Humanoid, etc.) in the area.
Our team is recruiting PostDocs, research engineers, and interns. Please feel free to contact me if you are interested.
News
- 📢 2023/03 – Our paper “ConvReLU++: Reference-based Lossless Acceleration of Conv-ReLU Operations on Mobile CPU” is conditionally accepted to MobiSys 2023! Congratulations to Rui Kong and Yizhen Yuan for their first top-conference paper!
- 📢 2023/02 – Our paper “PatchCensor: Patch Robustness Certification for Transformers via Exhaustive Testing” is accepted to TOSEM! Thank Yuheng Huang for the hard work and insightful discussions!
- 📢 2022/11 – Our paper “AdaptiveNet: Post-deployment Neural Architecture Adaptation for Diverse Edge Environments” is accepted to MobiCom 2023! Congratulations to Wen Hao for his first (top-conference) paper. Much thanks to our collaborators @Zunshuai Zhang, @Shiqi Jiang, @Yunxin Liu and industry partners!
- 📢 2022/10 – My project proposal on “Neurosymbolic Programming Approaches to Reliable Edge AI” is approved and funded by NSFC. Very excited to start this cool direction.
- 📢 2022/06 – Our paper “MobiDepth: Real-Time Depth Estimation Using On-Device Dual Cameras” is accepted to MobiCom 2022! Congratulations to Jinrui Zhang and other great coauthors.
- 📢 2022/05 – Our paper “FedBalancer: Data and Pace Control for Efficient Federated Learning on Heterogeneous Clients” got accepted to MobiSys 2022! We propose to accelerate FL training through fine-grained client data selection and deadline control. Thanks to awesome collaborators Jaemin and Prof. Sung-Ju Lee at KAIST.
- 📢 2022/03 – Our paper “WhyGen: Explaining ML-powered Code Generation by Referring to Training Examples” is accepted to the Demo track of ICSE 2022. Congratulations to Weixiang for his first publication! This paper introduces an interesting idea to address the widely-concerned recitation problem in DL-based code generators.
- 📢 2022/03 – Our paper “Representational Continuity for Unsupervised Continual Learning” got accepted to ICLR 2022 (Oral presentation)!
Current Research
- Improving edge AI efficiency
- Enhancing edge AI reliability
Selected Recent Publications
Venue | Authors & Title | Tags & Links |
---|---|---|
[MobiSys 2023] | Rui Kong, Yuanchun Li*, Yizhen Yuan, Linghe Kong. “ConvReLU++: Reference-based Lossless Acceleration of Conv-ReLU Operations on Mobile CPU” | pdf code |
[MobiCom 2023] | Hao Wen, Yuanchun Li*, Zunshuai Zhang, Shiqi Jiang, Xiaozhou Ye, Ye Ouyang, Yaqin Zhang, Yunxin Liu. “AdaptiveNet: Post-deployment Neural Architecture Adaptation for Diverse Edge Environments” | arxiv code |
[MobiSys 2022] | Jaemin Shin, Yuanchun Li*, Yunxin Liu, Sung-Ju Lee. “FedBalancer: Data and Pace Control for Efficient Federated Learning on Heterogeneous Clients” | arxiv code |
[ICSE 2022] | Ziqi Zhang, Yuanchun Li*, Jindong Wang, Bingyan Liu, Ding Li, Xiangqun Chen, Yao Guo, Yunxin Liu. “ReMoS: Reducing Defect Inheritance in Transfer Learning via Relevant Model Slicing” | pdf code |
[UbiComp 2021] | Bingyan Liu, Yuanchun Li*, Yao Guo, Xiangqun Chen, Yunxin Liu. “PMC: A Privacy-preserving Deep Learning Model Customization Framework for Edge Computing” | [pdf] [code] |
[ISSTA 2021] | Yuanchun Li, Ziqi Zhang, Bingyan Liu, Ziyue Yang, Yunxin Liu. “ModelDiff: Testing-based DNN Similarity Comparison for Model Reuse Detection” | [arxiv] [code] |
[ICSE 2021] | Yuanchun Li, Jiayi Hua, Haoyu Wang, Chunyang Chen, Yunxin Liu. “DeepPayload: Black-box Backdoor Attack on Deep Learning Models through Neural Payload Injection” | [arxiv] |
[UbiComp 2017] | Yuanchun Li, Fanglin Chen, Toby Jia-jun Li, Yao Guo, Gang Huang, Matthew Fredrikson, Yuvraj Agarwal, Jason I. Hong. “PrivacyStreams: Enabling Transparency in Personal Data Processing for Mobile Apps.” | [pdf] Star |
[ICSE 2017] | Yuanchun Li, Ziyue Yang, Yao Guo and Xiangqun Chen. “DroidBot: A Lightweight UI-Guided Test Input Generator for Android.” | [pdf] Star |
[UbiComp 2016] | Yuanchun Li, Yao Guo, Xiangqun Chen. “PERUIM: Understanding Mobile Application Privacy With Permission-UI Mapping.” Honorable Mention Award! | [pdf] |