Photo of Ang Li

Ang Li

Assistant Professor, ECE, University of Maryland College Park

I am currently a tenure-track assistant professor in the Department of Electrical and Computer Engineering at University of Maryland College Park. Before joining UMD, I was a Research Associate in Qualcomm AI Research. I obtained Ph.D. from Duke University under the supervision of Professor Yiran Chen. My research interests lie in the intersection of machine learning and edge computing, with a focus on building large-scale networked and trustworthy intelligent systems to solve practical problems in a collaborative, scalable, secure, and ubiquitous manner.

Openings: I’m looking for highly motivated Ph.D., master students, and research interns to join my group. If you are interested, please send an email to angliece@umd.edu with your CV and transcripts attached.

Openings: I'm looking for highly motivated Ph.D., master students, and research interns to join my group. If you are interested, please send an email to angliece@umd.edu with your CV and transcripts attached.

News

Research Vision

Efficient, scalable, and privacy-preserving distributed learning across heterogeneous edge devices.

Our work on federated learning addresses key challenges including device heterogeneity (Hermes, MobiCom'21; FedMask, SenSys'21), communication efficiency (LotteryFL, SEC'21), asynchronous training (FedSEA, SenSys'22), client sampling (Fed-CBS, ICML'23), and optimization (FedNAR, NeurIPS'23; FedHyper, ICLR'24). We also explore federated fine-tuning of large language models (Flora, NeurIPS'24; EdgeLoRA, MobiSys'25).

Building large-scale intelligent systems that are robust, efficient, and secure for real-world deployment.

We develop techniques for efficient inference and serving of large models, including Mixture-of-Experts systems (SiDA, MLSys'24), model compression, and edge deployment. Our research also covers trustworthy AI including privacy-preserving representation learning (TIPRDC, KDD'20), defense against model poisoning (FL-WBC, NeurIPS'21), and fairness in AI systems (ICLR'25).

Applying AI innovations to solve real-world challenges in healthcare, EDA, and beyond.

We leverage machine learning to address critical challenges in healthcare (NeuroSymAD for Alzheimer's diagnosis, MedOrch for medical reasoning, Fair Diagnosis), electronic design automation (SymRTLO, NeurIPS'24; VeriReason; MCP4EDA; AutoEDA), and autonomous driving (AutoFed, MobiCom'23).

Awards & Honors

Publications

Loading publications...

Invited Talks

Academic Service

Teaching

Theoretical and practical aspects of computer systems security. Topics covered include symmetric/asymmetric encryption, message authentication, digital signatures, access control, as well as network security, web security and cloud security. Students acquire tools necessary for designing secure computer systems and programs and for defending against malicious threats (e.g., viruses, worms, denial of service).

  • Prerequisite: Minimum grade of C- in ENEE350
  • Lectures: Mon/Wed 11:00AM-12:15PM; classroom: EGR 1108

Course Website

Principles and applications of federated learning. Federated optimization, statistical and system homogeneity models, variations of federated aggregation, security and privacy considerations, foundation models.

  • Prerequisite: ENEE436 or CMSC422
  • Lectures: Mon/Wed 3:30PM-4:45PM; classroom: EGR 0135

Course Website

CASE Lab

CASE (Collaborative, Automated, Scalable, and Efficient Intelligence) Lab is an active research group at University of Maryland College Park. Our research interests lie in developing cutting-edge algorithms and systems that are not only robust and efficient but also scalable across diverse applications.

Ph.D. Students

Master Students

Visitors / Interns