A collaboration between ORNL, IonQ, NVIDIA, and UT Knoxville introduced DQAOA-GPT, a generative AI framework that synthesizes quantum optimization circuits, eliminating iterative parameter-tuning. This framework significantly reduces circuit synthesis runtime to a constant 28 seconds and doubles solution quality for higher-order unconstrained binary optimization (HUBO) problems, as presented at IEEE Quantum Week 2026. DQAOA-GPT replaces traditional trial-and-error with a transformer model trained on high-performing circuit profiles, allowing hybrid algorithms to scale subproblem sizes efficiently.
The post IonQ, ORNL, NVIDIA, and UT Knoxville Advance AI-Driven Generative Quantum Circuit Synthesis appeared first on Quantum Computing Report .