Cunxi Yu

Cunxi Yu is an Assistant Professor in the Department of Electrical and Computer Engineering (ECE) at the University of Maryland, College Park, and an affiliated faculty member in the Department of Computer Science (CS). He holds a Ph.D. from UMass Amherst (2017) and has held postdoctoral positions at Cornell University and EPFL. His research focuses on novel algorithms, systems, and hardware designs for computing and security, with notable contributions in formal verification, logic synthesis, and optical neural networks. He has received prestigious awards including the NSF CAREER Award (2021) and Best Paper Awards at ASPLOS (2025) and DAC (2023).

Dr. Yu's academic journey includes prior roles at the University of Utah and industry collaborations with IBM Research. He advises a dynamic research group with PhD students in ECE and CS, and mentors undergraduate researchers. His work bridges formal methods with machine learning, emphasizing practical tools like BoolE (Best Paper Nomination, DAC 2025) and SmoothE (Best Paper Award, ASPLOS 2025). He actively contributes to conferences such as ASAP, ICCAD, and DAC through organizing committees and TPC roles.

Key research areas include:
- Formal Verification: Algebraic techniques for arithmetic circuits, equivalence checking, and e-graph-based reasoning.
- Optical Computing: Design frameworks like LightRidge for diffractive optical neural networks.
- Hardware Automation: Reinforcement learning for logic synthesis (e.g., MapTune, Gamora) and EDA tool development.
- Security: Reverse engineering of camouflaged circuits and cryptographic hardware verification.

His grants include a $900K NSF grant (2024) with Prof. Zhiru Zhang (Cornell) for hardware synthesis. Recent milestones include NVIDIA Academic Research Awards (2025) and DARPA funding for combinatorial optimization.