Curator's Take
This research tackles one of the most persistent challenges in superconducting quantum computers: crosstalk between qubits during two-qubit gate operations, which can severely degrade computational accuracy as systems scale up. The novel physics-guided neural control framework represents a promising fusion of machine learning with quantum control theory, automatically generating smoother, more robust control pulses that outperform traditional optimization methods like Krotov's approach. What makes this particularly compelling is the method's focus on practical constraints and real-world noise conditions, suggesting it could translate directly to improving gate fidelities in current superconducting quantum processors from IBM, Google, and others. The emphasis on worst-case performance improvements is especially valuable for near-term quantum applications where reliability under varying conditions remains a critical bottleneck.
— Mark Eatherly
Summary
The potential of quantum computing is fundamentally constrained by the inherent susceptibility of qubits to noise and crosstalk, particularly during multi-qubit gate operations. Existing strategies, such as hardware isolation and dynamical decoupling, face limitations in scalability, experimental feasibility, and robustness against complex noise sources. In this manuscript, we propose a physics-guided neural control (PGNC) framework to generate robust control pulses for superconducting transmon qubit systems, specifically targeting crosstalk mitigation. By combining a hardware aware parameterization with a Hamiltonian-informed objective that accounts for condition-dependent crosstalk distortions, PGNC steers the search toward smooth and physically realizable pulses while efficiently exploring high dimensional control landscapes. Numerical simulations for the CZ gate demonstrate superior fidelity and pulse smoothness compared to a Krotov baseline under matched constraints. Taken together, the results show consistent and practically meaningful improvements in both nominal and perturbed conditions, with pronounced gains in worst-case fidelity, supporting PGNC as a viable route to robust control on near-term transmon devices.