Recent Ph.D. graduate Zishen Wan, currently an assistant professor at Columbia University, was recognized for research addressing key computing challenges in physical AI.

Georgia Tech School of Electrical and Computer Engineering (ECE) Ph.D. graduate Zishen Wan recently received two highly selective dissertation recognitions for his research on computing systems for physical artificial intelligence (AI).

His dissertation, “Tailored Computing: Cross-Layer System, Architecture, and Silicon Co-Design for Physical Intelligence,” earned the ACM Outstanding Ph.D. Dissertation Award in Electronic Design Automation, presented by the Association for Computing Machinery’s Special Interest Group on Design Automation (SIGDA), and the FCCM Outstanding Ph.D. Dissertation Award from the IEEE International Symposium on Field-Programmable Custom Computing Machines.

Each award is given to only one dissertation each year.

“I’m deeply honored to have my dissertation recognized by the ACM SIGDA and FCCM communities,” Wan said. “These awards are especially meaningful because they recognize research that connects computer architecture, systems, and silicon. Georgia Tech gave me the opportunity to work across these disciplines, and I’m grateful to my advisors, collaborators, and the ECE community for the mentorship and support that made this work possible.”

Physical AI includes robots and autonomous systems that perceive their surroundings, reason about what to do, and act in the real world. These systems must respond quickly within tight limits on computing power and energy, while remaining reliable as conditions change.

Wan’s dissertation explored a cross-layer co-design spanning computer architecture, software systems, and silicon, instead of the more traditional approach of optimizing singular layers of the computing stack.

This new approach can be applied to the emerging forms of AI, including neuro-symbolic reasoning, embodied and robotic AI, and multi-agent systems, with the goal of making these systems more efficient, reliable, and scalable. 

Wan recently defended the dissertation and joined Columbia University as a tenure-track assistant professor in fall 2026, where he continues to research computing for AI and AI for computing.

While at ECE, Wan was advised by Steve W. Chaddick School Chair Arijit Raychowdhury and Associate Professor Tushar Krishna. 

He was also active in many of ECE’s research programs, particularly the Georgia Tech-led JUMP 2.0 CoCoSys Center, a Semiconductor Research Corporation (SRC) JUMP 2.0 program. His work while at Georgia Tech received many other awards, including being named a Machine Learning and Systems Rising Star.

Related Content