Specialized microchips that manage signals at the cutting edge of wireless technology are difficult and expensive to design. The 2023 paper details a system that reduces what used to take weeks of highly skilled work down to hours.

The researchers, led by Kaushik Sengupta, professor of electrical and computer engineering, developed an AI system that designs complicated electromagnetic structures and circuits by starting with a set of desired outcomes and working backwards to find the optimal architecture. Conventional methods work the other way around. The new approach often results in counter-intuitive and surprising designs. But the AI-designed chips have demonstrated real improvements, operating across a record frequency range covering all millimeter-wave bands from 30 to 94 GHz, and increasing energy efficiency. 

The paper’s authors include Emir Ali Karahan, the lead author and a graduate student at Princeton; Zheng Liu, who was a graduate student at Princeton and currently works at the Kilby Labs at Texas Instruments. The award was presented at the IEEE International Solid-State Circuits Conference, held in San Francisco in February of 2025.

The IEEE Journal of Solid-State Circuits is the premier journal in the field of integrated circuits. Produced by the IEEE Solid-State Circuits Society, the journal debuted in 1966 as an archive of major presentations from conferences expanded into journal length papers. 

Sengupta is a director and co-founder of Princeton’s program in advanced communications technology, the Next-G Initiative, which launched in 2023. He is a fellow of the IEEE and has received numerous honors from various IEEE societies. Other past honors include a DARPA Young Faculty Award, an Office of Naval Research Young Investigator Award, and a Bell Labs Prize. Sengupta joined the Princeton faculty in 2013 after completing his Ph.D. at the California Institute of Technology.