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

Japanese Journal of Applied Physics

Multi-bit state discrimination using machine learning for IQ -encoded spin-qubit readout

DUANLIAN ZHANG, Naoya Negami, Raisei Mizokuchi, Shunsuke Ota, Riku Wada, Tetsuo Kodera

Published Feb 12, 2026• 0 citations
Publisher

Abstract

Abstract Semiconductor spin qubits are compatible with CMOS processes and support high integration density, making them promising for scalable quantum computing. Yet multiplexed readout remains a bottleneck. Frequency multiplexing is bandwidth-limited, while time multiplexing introduces sequential latency and extra power. We adopt in-phase ( I )–quadrature ( Q ) encoding, mapping readout signals to the complex ( I – Q ) plane to enable parallel multi-qubit discrimination and compact, digitally processable representations, compatible with both resonator-based and inductor-less electrical readout. We develop machine-learning classifiers trained on synthesized IQ datasets that emulate spin-qubit measurements with noise, drift, and varied constellation layouts. Across wide signal-to-noise ratios, the models outperform conventional thresholding and sustain high accuracy, demonstrating robust state discrimination under realistic conditions. By improving qubit-state decoding in a digitally scalable form, this work supports larger spin-qubit arrays and more efficient cryogenic readout architectures.

DOI
10.35848/1347-4065/ae4520

Related papers

Superconducting-qubit readout using next-generation reservoir computing

Robert Kent, Benjamin Lienhard, Gregory P. Lafyatis +1 more

Quantum processors require rapid and high-fidelity simultaneous measurements of many qubits. While superconducting qubits are among the leading modalities toward a useful quantum processor, their readout remains a bottleneck. Traditional approaches to processing measurement data often struggle to account for crosstalk present in frequency-multiplexed readout, the preferred method to reduce the resource overhead. Recent approaches to address this challenge use neural networks to improve the state-discrimination fidelity. However, they are computationally expensive to train and evaluate, resulting in increased latency and poor scalability as the number of qubits increases. We present an alternative machine learning approach based on next-generation reservoir computing that constructs polynomial features from the measurement signals and maps them to the corresponding qubit states. This method is highly parallelizable, avoids the costly nonlinear activation functions common in neural networks, and supports real-time training, enabling fast evaluation, adaptability, and scalability. Despite its lower computational complexity, our reservoir approach is able to maintain high qubit-state-discrimination fidelity. Relative to traditional methods, our approach achieves error reductions of up to 50% and 11% on single- and five-qubit datasets, respectively, and delivers up to 2.5x crosstalk reduction on the five-qubit dataset. Compared with recent machine-learning methods, evaluating our model requires 100x fewer multiplications for single-qubit and 2.5x fewer for five-qubit models. This work demonstrates that reservoir computing can enhance qubit-state discrimination while maintaining scalability for future quantum processors.

arXiv:2506.15771•Physical Review Applied•Mar 2, 2026•2 citations

Multi-Stage Mamba-Based Architecture for Fast and Scalable Superconducting Qubit Readout

Luca Otting, Xiaorang Guo, Emmanouil Giortamis +3 more

Reliable qubit readout is a critical bottleneck toward fault-tolerant quantum computing (FTQC). In superconducting quantum processors, readout operations are both error-prone and high-latency. These challenges become more severe in frequency-multiplexed architectures, where signal crosstalk among neighboring qubits significantly degrades readout fidelity. Existing machine learning (ML)-based approaches rely on feed-forward neural networks (FNNs) that suffer from large parameter sizes and lack an end-to-end network that jointly addresses relaxation errors and discriminates qubit states. In this work, we present a multi-stage qubit state discriminator based on the Mamba model, which enables efficient sequence modeling with linear complexity. The first stage performs initial state discrimination, followed by a refinement stage that identifies and mitigates relaxation-induced errors. Our lightweight model achieves a geometric mean readout fidelity of 0.906, outperforming the best-reported state-of-the-art method while reducing parameter size by 49.6%; our optimal model further reaches 0.911. Both models remain robust across varying input trace lengths, maintaining a high fidelity of 0.893 at readout durations as short as 500 $ns$, achieving up to a 26% reduction in logical error rate over prior work in quantum error correction (QEC).

quant-pharXiv:2607.11668•Jul 14, 2026•0 citations

Quantized NN Workflow for Low-Latency Multi-Qubit State Discrimination on FPGA

Pradeep Kumar Gautam, Shantharam Kalipatnapu, H Shankaranarayanan +4 more

Measuring a qubit state is a fundamental but error-prone task in quantum computing. As the number of qubits increases, scalable readout demands multiplexed qubit measurement, which often suffers from crosstalk and other nonidealities. The conventional approach of qubit state detection often struggles with scalability and noise resilience. Neural network (NN)-based discriminators have emerged as a promising alternative, offering superior performance for inferring qubit states from multiplexed signals. However, their deployment on hardware platforms like Field programmable gate arrays (FPGA) is hindered by computation complexity, resource constraints, and latency. In this work, we present an end-to-end methodology for designing and deploying quantized NN-based multi-qubit state discriminators on FPGAs. We demonstrate that implementing a fully connected neural network accelerator for multi-qubit readout is advantageous, balancing computational complexity with low latency requirements without significant loss in accuracy. We significantly reduce the FPGA footprint and latency of the neural network by employing quantization-aware training (QAT) to quantize weights, activations, and inputs, and leveraging automated mapping flows for efficient, hardware-aware design-space exploration and optimization. The hardware accelerator performs frequency-multiplexed readout of five superconducting qubits in 26.7 ns, on a radio frequency system on chip (RFSoC) ZCU111 FPGA. These modules can be implemented and integrated into existing FPGA based quantum control and readout platforms, making them ready for experimental deployment.

International Symposium on Highly Efficient Accelerators and Reconfigurable Technologies (HEART)•Jun 17, 2026•0 citations

Time-series based quantum state discrimination

Samuel Jung, Neel Vora, Akel Hashim +2 more

Abstract Measurement errors in quantum computers are very detrimental to quantum computations. The ability to efficiently and accurately readout quantum states is crucial for quantum error correction schemes and quantum algorithms. Readout fidelity is typically limited by a poor signal-to-noise (SNR) ratio between the quantum states we intend to classify, as well as energy relaxation (e.g., $T_1$ decay) from an excited state to a lower state during readout. Superconducting quantum bits (qubit), one of the leading candidates for scalable quantum computing hardware, are particularly limited by energy relaxation due to their relatively short coherence times. While most approaches for classifying the results of readout on superconducting qubits typically utilize clustering algorithms (e.g., a Gaussian mixture model) on integrated readout signals, these cannot distinguish between a quantum bit that was in the ground state prior to measurement from a qubit that decays to the ground state during measurement. For this reason, we instead propose using machine learning (ML) on the raw (non-integrated) analog signal and classification models on the full time series data (i.e., the \emph{trajectory}). We observe that time series classification methods, such as our chosen long short-term memory (LSTM) model, in combination with filtering and feature engineering techniques, consistently outperform clustering models. In particular, we find that the largest improvements come from reclassifying points in the boundary regions between neighboring clusters. These boundary points correspond to measurement records that deviate from the typical cluster, likely due to transient or noisy features in the signal that are not captured when the data is integrated. By retaining temporal information, sequence-aware models such as LSTMs can better discriminate these trajectories, whereas clustering methods based on integrated values are more prone to misclassifications.

•Apr 13, 2026•0 citations

Code Division Multiplexing based Readout Scheme for Spin Qubits

Jean-Baptiste Casanova, Quentin Schmidt, Baptiste Jadot +4 more

Large-scale, fault-tolerant quantum computing requires the integration of a substantial number of quantum bits (qubits). Efficient readout of these qubits depends on the underlying technology but invariably calls for scalable multiplexed schemes. This paper introduces a novel digital code multiplexing approach for charge readout in quantum computing. Operating entirely at digital levels, the proposed scheme eliminates the need for complex waveform or sinusoidal signal generation. Unlike conventional reflectometry, where the number of qubits dictates the number of physical resonant circuits, our method only influences the digital clock frequency, enabling a more compact and scalable implementation. We demonstrate this scheme by modulating two industrial single-electron transistors (SETs) through a transimpedance amplifier (TIA)-based readout chain operating at 4.2~K. Experimental results show that the proposed method reliably distinguishes SET conductivity states under multiplexing, achieving a bit-error rate (BER) below $10^{-3}$ within an integration time of $4.55~\mu$s.

Design, Automation, and Test in Europe•Apr 20, 2026•0 citations

13.5 An 18.5µW/qubit Cryo-CMOS Charge-Readout IC Demonstrating QAM Multiplexing for Spin Qubits

Quentin Schmidt, Baptiste Jadot, Brian Martinez +6 more

Spin qubits are a promising candidate for large-scale fault-tolerant quantum computing due to2footprint per qubit, higher operating temperature (up to 1K [1]) and possible compatibility with industrial CMOS processes [2], [3]. However, the need for a simultaneous ~µs readout of thousands of devices is especially challenging in terms of power consumption and footprint per qubit [4], [5]. Frequency-domain multiplexed (FDM) reflectometry architectures using cryo-CMOS have been introduced in [6], [7], [8] but these circuits require bulky > 100µm2inductors and do not match readout time specifications using actual quantum devices. Besides, current integrator readout schemes have been proposed [9], [10], but offer no scaling perspectives beyond time-domain multiplexing, leading to strong constraints in terms of bandwidth and power consumption. Recently, [4] introduced a capacitive-feedback transimpedance amplifier achieving an inductor-less FDM readout of two quantum dots [11]. Nevertheless, the demonstrated power consumption per qubit of 214µW/qubit remains too high to match the maximum heat dissipation allowed near quantum devices [12] in a large-scale perspective. Moreover, the used On-Off Keying (OOK) modulations are limited to one qubit per carrier, thus requiring high bandwidth and power consumption in order to read thousands of qubits.

Digest of technical papers/Digest of technical papers - IEEE International Solid-State Circuits Conference•Feb 16, 2025•5 citations
Abstract Semiconductor spin qubits are compatible with CMOS processes and support high integration density, making them promising for scalable quantum computing. Yet multiplexed readout remains a bottleneck. Frequency multiplexing is bandwidth-limited, while time multiplexing introduces sequential latency and extra power. We adopt in-phase ( I )–quadrature ( Q ) encoding, mapping readout signals to the complex ( I – Q ) plane to enable parallel multi-qubit discrimination and compact, digitally processable representations, compatible with both resonator-based and inductor-less electrical readout. We develop machine-learning classifiers trained on synthesized IQ datasets that emulate spin-qubit measurements with noise, drift, and varied constellation layouts. Across wide signal-to-noise ratios, the models outperform conventional thresholding and sustain high accuracy, demonstrating robust state discrimination under realistic conditions. By improving qubit-state decoding in a digitally scalable form, this work supports larger spin-qubit arrays and more efficient cryogenic readout architectures.
Quantum processors require rapid and high-fidelity simultaneous measurements of many qubits. While superconducting qubits are among the leading modalities toward a useful quantum processor, their readout remains a bottleneck. Traditional approaches to processing measurement data often struggle to account for crosstalk present in frequency-multiplexed readout, the preferred method to reduce the resource overhead. Recent approaches to address this challenge use neural networks to improve the state-discrimination fidelity. However, they are computationally expensive to train and evaluate, resulting in increased latency and poor scalability as the number of qubits increases. We present an alternative machine learning approach based on next-generation reservoir computing that constructs polynomial features from the measurement signals and maps them to the corresponding qubit states. This method is highly parallelizable, avoids the costly nonlinear activation functions common in neural networks, and supports real-time training, enabling fast evaluation, adaptability, and scalability. Despite its lower computational complexity, our reservoir approach is able to maintain high qubit-state-discrimination fidelity. Relative to traditional methods, our approach achieves error reductions of up to 50% and 11% on single- and five-qubit datasets, respectively, and delivers up to 2.5x crosstalk reduction on the five-qubit dataset. Compared with recent machine-learning methods, evaluating our model requires 100x fewer multiplications for single-qubit and 2.5x fewer for five-qubit models. This work demonstrates that reservoir computing can enhance qubit-state discrimination while maintaining scalability for future quantum processors.
Reliable qubit readout is a critical bottleneck toward fault-tolerant quantum computing (FTQC). In superconducting quantum processors, readout operations are both error-prone and high-latency. These challenges become more severe in frequency-multiplexed architectures, where signal crosstalk among neighboring qubits significantly degrades readout fidelity. Existing machine learning (ML)-based approaches rely on feed-forward neural networks (FNNs) that suffer from large parameter sizes and lack an end-to-end network that jointly addresses relaxation errors and discriminates qubit states. In this work, we present a multi-stage qubit state discriminator based on the Mamba model, which enables efficient sequence modeling with linear complexity. The first stage performs initial state discrimination, followed by a refinement stage that identifies and mitigates relaxation-induced errors. Our lightweight model achieves a geometric mean readout fidelity of 0.906, outperforming the best-reported state-of-the-art method while reducing parameter size by 49.6%; our optimal model further reaches 0.911. Both models remain robust across varying input trace lengths, maintaining a high fidelity of 0.893 at readout durations as short as 500 nsnsns, achieving up to a 26% reduction in logical error rate over prior work in quantum error correction (QEC).
Measuring a qubit state is a fundamental but error-prone task in quantum computing. As the number of qubits increases, scalable readout demands multiplexed qubit measurement, which often suffers from crosstalk and other nonidealities. The conventional approach of qubit state detection often struggles with scalability and noise resilience. Neural network (NN)-based discriminators have emerged as a promising alternative, offering superior performance for inferring qubit states from multiplexed signals. However, their deployment on hardware platforms like Field programmable gate arrays (FPGA) is hindered by computation complexity, resource constraints, and latency. In this work, we present an end-to-end methodology for designing and deploying quantized NN-based multi-qubit state discriminators on FPGAs. We demonstrate that implementing a fully connected neural network accelerator for multi-qubit readout is advantageous, balancing computational complexity with low latency requirements without significant loss in accuracy. We significantly reduce the FPGA footprint and latency of the neural network by employing quantization-aware training (QAT) to quantize weights, activations, and inputs, and leveraging automated mapping flows for efficient, hardware-aware design-space exploration and optimization. The hardware accelerator performs frequency-multiplexed readout of five superconducting qubits in 26.7 ns, on a radio frequency system on chip (RFSoC) ZCU111 FPGA. These modules can be implemented and integrated into existing FPGA based quantum control and readout platforms, making them ready for experimental deployment.
Abstract Measurement errors in quantum computers are very detrimental to quantum computations. The ability to efficiently and accurately readout quantum states is crucial for quantum error correction schemes and quantum algorithms. Readout fidelity is typically limited by a poor signal-to-noise (SNR) ratio between the quantum states we intend to classify, as well as energy relaxation (e.g., T1T_1T1​ decay) from an excited state to a lower state during readout. Superconducting quantum bits (qubit), one of the leading candidates for scalable quantum computing hardware, are particularly limited by energy relaxation due to their relatively short coherence times. While most approaches for classifying the results of readout on superconducting qubits typically utilize clustering algorithms (e.g., a Gaussian mixture model) on integrated readout signals, these cannot distinguish between a quantum bit that was in the ground state prior to measurement from a qubit that decays to the ground state during measurement. For this reason, we instead propose using machine learning (ML) on the raw (non-integrated) analog signal and classification models on the full time series data (i.e., the \emph{trajectory}). We observe that time series classification methods, such as our chosen long short-term memory (LSTM) model, in combination with filtering and feature engineering techniques, consistently outperform clustering models. In particular, we find that the largest improvements come from reclassifying points in the boundary regions between neighboring clusters. These boundary points correspond to measurement records that deviate from the typical cluster, likely due to transient or noisy features in the signal that are not captured when the data is integrated. By retaining temporal information, sequence-aware models such as LSTMs can better discriminate these trajectories, whereas clustering methods based on integrated values are more prone to misclassifications.
Large-scale, fault-tolerant quantum computing requires the integration of a substantial number of quantum bits (qubits). Efficient readout of these qubits depends on the underlying technology but invariably calls for scalable multiplexed schemes. This paper introduces a novel digital code multiplexing approach for charge readout in quantum computing. Operating entirely at digital levels, the proposed scheme eliminates the need for complex waveform or sinusoidal signal generation. Unlike conventional reflectometry, where the number of qubits dictates the number of physical resonant circuits, our method only influences the digital clock frequency, enabling a more compact and scalable implementation. We demonstrate this scheme by modulating two industrial single-electron transistors (SETs) through a transimpedance amplifier (TIA)-based readout chain operating at 4.2~K. Experimental results show that the proposed method reliably distinguishes SET conductivity states under multiplexing, achieving a bit-error rate (BER) below 10−310^{-3}10−3 within an integration time of 4.55 μ4.55~\mu4.55 μs.
Spin qubits are a promising candidate for large-scale fault-tolerant quantum computing due to2footprint per qubit, higher operating temperature (up to 1K [1]) and possible compatibility with industrial CMOS processes [2], [3]. However, the need for a simultaneous ~µs readout of thousands of devices is especially challenging in terms of power consumption and footprint per qubit [4], [5]. Frequency-domain multiplexed (FDM) reflectometry architectures using cryo-CMOS have been introduced in [6], [7], [8] but these circuits require bulky > 100µm2inductors and do not match readout time specifications using actual quantum devices. Besides, current integrator readout schemes have been proposed [9], [10], but offer no scaling perspectives beyond time-domain multiplexing, leading to strong constraints in terms of bandwidth and power consumption. Recently, [4] introduced a capacitive-feedback transimpedance amplifier achieving an inductor-less FDM readout of two quantum dots [11]. Nevertheless, the demonstrated power consumption per qubit of 214µW/qubit remains too high to match the maximum heat dissipation allowed near quantum devices [12] in a large-scale perspective. Moreover, the used On-Off Keying (OOK) modulations are limited to one qubit per carrier, thus requiring high bandwidth and power consumption in order to read thousands of qubits.