Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

arXiv:2511.12524 · Physical Review Applied

Autonomously Designed Pulses for Precise, Site-Selective Control of Atomic Qubits

Sanghyo Park, Seuk Lee, Keunyoung Lee, Minhyeok Kim, Donggyu Kim

quant-phSubmitted Nov 16, 2025• Announced Nov 18, 2025• 1 citation
arXivHTMLPDF

Abstract

Quantum computers based on cold-atom arrays offer long-lived qubits with programmable connectivity, yet their progress toward fault-tolerant operation is limited by the relatively low fidelity of site-selective local control. We introduce an artificial-intelligence (AI) framework that overcomes this limitation. Trained on atom-laser dynamics, a deep neural network autonomously designs composite pulses that improve local control fidelities tenfold while remaining compatible with existing control hardware. We further demonstrate the robustness of these pulses against optical aberrations and beam misalignment. This approach establishes AI-trained pulse compilation for high-fidelity qubit control and can be readily extended to other atom-like platforms, such as trapped ions and solid-state color centers.

DOI
10.1103/dspx-fgp2

Related papers

High-fidelity local addressing of trapped ions and atoms by composite sequences of laser pulses

Svetoslav S. Ivanov, Nikolay V. Vitanov

A vital requirement for a quantum computer is the ability to locally address, with high fidelity, any of its qubits without affecting their neighbors. We propose an addressing method using composite sequences of laser pulses that dramatically reduces the addressing error in a lattice of closely spaced atoms or ions and at the same time significantly enhances the robustness of qubit manipulations. To this end, we design novel (to our knowledge) high-fidelity composite pulses for the most important single-qubit operations. In principle, this method allows one to beat the diffraction limit, for only atoms situated in a small spatial region around the center of the laser beam are excited, well within the laser beam waist.

arXiv:1106.0272•Optics Letters•Mar 29, 2011•55 citations

Intelligent Optimal Control of Rydberg Gates with Incremental-Update Deep Reinforcement Learning

Yue Cai, Hanlin Zhang, Keye Zhang +1 more

Deep reinforcement learning (DRL), acting as a novel and powerful paradigm for quantum optimal control, offers transformative opportunities for advancing neutral-atom quantum computing. In this work, we theoretically demonstrate a DRL-based framework for realizing Rydberg controlled-NOT gates that achieve both high speed and high fidelity through the synchronous modulation of multiple pulse parameters without any prior heuristic ansatz. By introducing an incremental-update learning policy, our framework effectively regularizes the exploration of the control landscape, ensuring the generation of smooth, experimentally feasible pulse profiles while significantly reducing computational overhead compared to conventional schemes. Crucially, the framework autonomously discovers an early-cutoff policy by optimally reconciling operation speed with high-precision coherent control. Our optimized protocol achieves a peak average fidelity of 0.9991, significantly outperforming conventional methods and surpassing the critical fault-tolerant threshold. This work establishes a generalizable, AI-driven pathway for designing high-performance quantum gates and provides a robust paradigm for autonomous control field optimization across diverse qubit platforms.

quant-pharXiv:2605.04628•May 7, 2026•0 citations

Hardware Co-Designed Optimal Control for Programmable Atomic Quantum Processors via Reinforcement Learning

Ding, Qian, Dirk Englund

Developing scalable, fault-tolerant atomic quantum processors requires precise control over large arrays of optical beams. This remains a major challenge due to inherent imperfections in classical control hardware, such as inter-channel crosstalk and beam leakage. In this work, we introduce a hardware co-designed intelligent quantum control framework to address these limitations. We construct a mathematical model of the photonic control hardware, integrate it into the quantum optimal control (QOC) framework, and apply reinforcement learning (RL) techniques to discover optimal control strategies. We demonstrate that the proposed framework enables robust, high-fidelity parallel single-qubit gate operations under realistic control conditions, where each atom is individually addressed by an optical beam. Specifically, we implement and benchmark three optimization strategies: a classical hybrid Self-Adaptive Differential Evolution-Adam (SADE-Adam) optimizer, a conventional RL approach based on Proximal Policy Optimization (PPO), and a novel end-to-end differentiable RL method. Using SADE-Adam as a baseline, we find that while PPO performance degrades as system complexity increases, the end-to-end differentiable RL consistently achieves gate fidelities above 99.9$\%$, exhibits faster convergence, and maintains robustness under varied channel crosstalk strength and randomized dynamic control imperfections.

arXiv:2504.11737•Apr 16, 2025•0 citations

Neural-network-designed pulse sequences for robust control of singlet-triplet qubits

Xu-Chen Yang, Man‐Hong Yung, Xin Wang

Composite pulses are essential for universal manipulation of singlet-triplet spin qubits. In the absence of noise, they are required to perform arbitrary single-qubit operations due to the special control constraint of a singlet-triplet qubit, while in a noisy environment, more complicated sequences have been developed to dynamically correct the error. Tailoring these sequences typically requires numerically solving a set of nonlinear equations. Here we demonstrate that these pulse sequences can be generated by a well-trained, double-layer neural network. For sequences designed for the noise-free case, the trained neural network is capable of producing almost exactly the same pulses known in the literature. For more complicated noise-correcting sequences, the neural network produces pulses with slightly different line shapes, but the robustness against noises remains comparable. These results indicate that the neural network can be a judicious and powerful alternative to existing techniques in developing pulse sequences for universal fault-tolerant quantum computation.

arXiv:1708.00238•Physical Review A•Apr 16, 2018•39 citations

A fiber array architecture for atom quantum computing

Xiao Li, Jiayi Hou, Jia-Chao Wang +8 more

Arrays of single atoms trapped in optical tweezers are increasingly recognized as a promising platform for scalable quantum computing. In both the fault-tolerant and NISQ eras, the ability to individually control qubits is essential for the efficient execution of quantum circuits. Time-division multiplexed control schemes based on atom shuttling or beam scanning have been employed to build programmable neutral atom quantum processors, but achieving high-rate, highly parallel gate operations remains a challenge. Here, we propose a fiber array architecture for atom quantum computing capable of fully independent control of individual atoms. The trapping and addressing lasers for each individual atom are emitted from the same optical waveguide, enabling robust control through common-mode suppression of beam pointing noise. Using a fiber array, we experimentally demonstrate the trapping and independent control of ten single atoms in two-dimensional optical tweezers, achieving individually addressed single-qubit gates with an average fidelity of 0.9966(3). More significantly, we perform simultaneous arbitrary single-qubit gates on four randomly selected qubits, resulting in an average fidelity of 0.9961(4). Our work paves the way for time-efficient execution of quantum algorithms on neutral atom quantum computers.

arXiv:2411.08502•Nature Communications•Nov 4, 2025•9 citations

Adaptive AI for Pulse-Level Quantum Control

Sanjeev Shapkota, Yayu Mo, Sanjaya Lohani

The Control Variational Quantum Eigensolver (ctrl-VQE) directly optimizes microwave pulses to enable faster and lower-error quantum-state preparation, but its continuous control landscape re- quires efficient search strategies. We demonstrate that a reinforcement-learning agent based on a deep Q learning network can autonomously discover high-performance pulse sequences using only system parameters and a reward function. The approach is fully general for superconducting qubit platforms, requires no ansatz, and operates at nanosecond resolution compatible with hardware con- straints. As a proof of concept, we apply the method to ground-state preparation of the Hydrogen molecule on a simulated superconducting device. The agent consistently identifies optimized control sequences that achieve high fidelity and outperform random-search baselines. These results highlight adaptive learning as a promising hardware-ready framework for pulse-level quantum control.

quant-pharXiv:2609.08727•Sep 9, 2026•0 citations
Quantum computers based on cold-atom arrays offer long-lived qubits with programmable connectivity, yet their progress toward fault-tolerant operation is limited by the relatively low fidelity of site-selective local control. We introduce an artificial-intelligence (AI) framework that overcomes this limitation. Trained on atom-laser dynamics, a deep neural network autonomously designs composite pulses that improve local control fidelities tenfold while remaining compatible with existing control hardware. We further demonstrate the robustness of these pulses against optical aberrations and beam misalignment. This approach establishes AI-trained pulse compilation for high-fidelity qubit control and can be readily extended to other atom-like platforms, such as trapped ions and solid-state color centers.
A vital requirement for a quantum computer is the ability to locally address, with high fidelity, any of its qubits without affecting their neighbors. We propose an addressing method using composite sequences of laser pulses that dramatically reduces the addressing error in a lattice of closely spaced atoms or ions and at the same time significantly enhances the robustness of qubit manipulations. To this end, we design novel (to our knowledge) high-fidelity composite pulses for the most important single-qubit operations. In principle, this method allows one to beat the diffraction limit, for only atoms situated in a small spatial region around the center of the laser beam are excited, well within the laser beam waist.
Deep reinforcement learning (DRL), acting as a novel and powerful paradigm for quantum optimal control, offers transformative opportunities for advancing neutral-atom quantum computing. In this work, we theoretically demonstrate a DRL-based framework for realizing Rydberg controlled-NOT gates that achieve both high speed and high fidelity through the synchronous modulation of multiple pulse parameters without any prior heuristic ansatz. By introducing an incremental-update learning policy, our framework effectively regularizes the exploration of the control landscape, ensuring the generation of smooth, experimentally feasible pulse profiles while significantly reducing computational overhead compared to conventional schemes. Crucially, the framework autonomously discovers an early-cutoff policy by optimally reconciling operation speed with high-precision coherent control. Our optimized protocol achieves a peak average fidelity of 0.9991, significantly outperforming conventional methods and surpassing the critical fault-tolerant threshold. This work establishes a generalizable, AI-driven pathway for designing high-performance quantum gates and provides a robust paradigm for autonomous control field optimization across diverse qubit platforms.
Developing scalable, fault-tolerant atomic quantum processors requires precise control over large arrays of optical beams. This remains a major challenge due to inherent imperfections in classical control hardware, such as inter-channel crosstalk and beam leakage. In this work, we introduce a hardware co-designed intelligent quantum control framework to address these limitations. We construct a mathematical model of the photonic control hardware, integrate it into the quantum optimal control (QOC) framework, and apply reinforcement learning (RL) techniques to discover optimal control strategies. We demonstrate that the proposed framework enables robust, high-fidelity parallel single-qubit gate operations under realistic control conditions, where each atom is individually addressed by an optical beam. Specifically, we implement and benchmark three optimization strategies: a classical hybrid Self-Adaptive Differential Evolution-Adam (SADE-Adam) optimizer, a conventional RL approach based on Proximal Policy Optimization (PPO), and a novel end-to-end differentiable RL method. Using SADE-Adam as a baseline, we find that while PPO performance degrades as system complexity increases, the end-to-end differentiable RL consistently achieves gate fidelities above 99.9%\%%, exhibits faster convergence, and maintains robustness under varied channel crosstalk strength and randomized dynamic control imperfections.
Composite pulses are essential for universal manipulation of singlet-triplet spin qubits. In the absence of noise, they are required to perform arbitrary single-qubit operations due to the special control constraint of a singlet-triplet qubit, while in a noisy environment, more complicated sequences have been developed to dynamically correct the error. Tailoring these sequences typically requires numerically solving a set of nonlinear equations. Here we demonstrate that these pulse sequences can be generated by a well-trained, double-layer neural network. For sequences designed for the noise-free case, the trained neural network is capable of producing almost exactly the same pulses known in the literature. For more complicated noise-correcting sequences, the neural network produces pulses with slightly different line shapes, but the robustness against noises remains comparable. These results indicate that the neural network can be a judicious and powerful alternative to existing techniques in developing pulse sequences for universal fault-tolerant quantum computation.
Arrays of single atoms trapped in optical tweezers are increasingly recognized as a promising platform for scalable quantum computing. In both the fault-tolerant and NISQ eras, the ability to individually control qubits is essential for the efficient execution of quantum circuits. Time-division multiplexed control schemes based on atom shuttling or beam scanning have been employed to build programmable neutral atom quantum processors, but achieving high-rate, highly parallel gate operations remains a challenge. Here, we propose a fiber array architecture for atom quantum computing capable of fully independent control of individual atoms. The trapping and addressing lasers for each individual atom are emitted from the same optical waveguide, enabling robust control through common-mode suppression of beam pointing noise. Using a fiber array, we experimentally demonstrate the trapping and independent control of ten single atoms in two-dimensional optical tweezers, achieving individually addressed single-qubit gates with an average fidelity of 0.9966(3). More significantly, we perform simultaneous arbitrary single-qubit gates on four randomly selected qubits, resulting in an average fidelity of 0.9961(4). Our work paves the way for time-efficient execution of quantum algorithms on neutral atom quantum computers.
The Control Variational Quantum Eigensolver (ctrl-VQE) directly optimizes microwave pulses to enable faster and lower-error quantum-state preparation, but its continuous control landscape re- quires efficient search strategies. We demonstrate that a reinforcement-learning agent based on a deep Q learning network can autonomously discover high-performance pulse sequences using only system parameters and a reward function. The approach is fully general for superconducting qubit platforms, requires no ansatz, and operates at nanosecond resolution compatible with hardware con- straints. As a proof of concept, we apply the method to ground-state preparation of the Hydrogen molecule on a simulated superconducting device. The agent consistently identifies optimized control sequences that achieve high fidelity and outperform random-search baselines. These results highlight adaptive learning as a promising hardware-ready framework for pulse-level quantum control.