Quantum computing promises new capabilities beyond classical computation. Mid-circuit measurements (MCMs) enable error correction and outcome-dependent control, but their reliability is limited by noise on superconducting hardware. These operations depend on accurate quantum state discrimination (QSD), which assigns measured signals to state labels. Neural network-based (NN-based) QSD improves this assignment, yet its error remains bounded below by the Bayes risk of the available readout distributions. A complementary challenge is state deterioration as successive measurements accumulate and circuit execution advances, making static calibration less representative of the workload. We present Lifting, a QSD framework that addresses both challenges through repetition encoding, neural decoding, and in situ calibration. Encoding supplies joint in-phase and quadrature (I-Q) readout signals from the target and auxiliary qubits, while contextual calibration trains the decoder for the conditions encountered during execution. Our theoretical analysis shows that retaining additional channels from a fixed joint distribution cannot increase Bayes risk and establishes sufficient conditions for contraction of an overlap-based upper bound. Experiments across three IBM processors evaluate the framework on repeated stabilizer measurement, parity-check, and teleportation workloads.
Quantum computing promises new capabilities beyond classical computation. Mid-circuit measurements (MCMs) enable error correction and outcome-dependent control, but their reliability is limited by noise on superconducting hardware. These operations depend on accurate quantum state discrimination (QSD), which assigns measured signals to state labels. Neural network-based (NN-based) QSD improves this assignment, yet its error remains bounded below by the Bayes risk of the available readout distributions. A complementary challenge is state deterioration as successive measurements accumulate and circuit execution advances, making static calibration less representative of the workload. We present Lifting, a QSD framework that addresses both challenges through repetition encoding, neural decoding, and in situ calibration. Encoding supplies joint in-phase and quadrature (I-Q) readout signals from the target and auxiliary qubits, while contextual calibration trains the decoder for the conditions encountered during execution. Our theoretical analysis shows that retaining additional channels from a fixed joint distribution cannot increase Bayes risk and establishes sufficient conditions for contraction of an overlap-based upper bound. Experiments across three IBM processors evaluate the framework on repeated stabilizer measurement, parity-check, and teleportation workloads.
This work addresses the critical challenge of accurately and swiftly identifying quantum states in superconducting quantum processors, with a particular focus on qubit (two-level) states. It introduces QubiCML, an innovative FPGA-based system designed for in-situ, real-time quantum state discrim-ination, which is essential for mid-circuit measurements and the implementation of advanced error correction techniques. By integrating a multi-layer neural network on the FPGA platform, QubiCML achieves exceptional accuracy and low latency in distinguishing quantum states. Traditional methods of quantum state discrimination rely heavily on offline data processing, which is inadequate due to the brief coherence time of quantum states and significant communication delays. QubiCML overcomes these limitations by utilizing in-situ machine learning for state discrimination, enabling real-time state determination in just 54 ns. It optimizes readout RF pulses and digital local oscillator (DLO) signals, significantly enhancing the fidelity of state discrimination. This capability enables mid-circuit measurements (MCM), which we successfully deployed using the QubiCML system. The system has been rigorously evaluated on in-house superconducting quantum processors, demonstrating an impressive average accuracy of 98.5%. QubiCML's modular architecture supports scalability across various qubits, making it adaptable to different quantum computing setups. Its real-time feedback capabilities are particularly beneficial for efficient quantum algorithm development and optimization. This system represents a groundbreaking advance-ment in the field of quantum computing, offering a robust tool for real-time quantum state discrimination. QubiCML has the potential to become the standard method for state discrimination, providing the quantum computing community with a powerful solution to push the boundaries of current technology.
Distributed Quantum Computing (DQC) and Quantum Error Correction (QEC) rely on dynamic circuits that include Mid-Circuit Measurements (MCMs) and classical feedback. These operations present a major bottleneck: MCMs suffer from high error rates that lead to real-time branching errors, while MCM and classical feedback latencies amplify decoherence errors. Current hardware controllers, qubit-state discriminators, and software error mitigation techniques fail to address these challenges holistically.
We propose MCMit, a hardware-software co-design to mitigate branching and latency-induced errors. MCMit introduces a scalable, constant-latency multi-control branch instruction for faster classical feedback and two qubit-state discriminators, a transformer, and a CNN, with high accuracy even under short measurement durations. On the software side, static MCM elimination and stochastic branching complement the hardware by mitigating residual branching errors that persist despite hardware improvements.
We implement MCMit on Qubic and evaluate it using experimentally extracted QPU readout traces. Our branch instruction reduces feedback latency by up to 70\%, improving circuit depths by up to 7× over Qubic. Our CNN discriminator achieves up to 62\% higher accuracy for short measurement durations than the baselines, driving 1.2−9.4× lower logical error rates in QEC. Last, our software mitigation improves fidelity by 18--30\% over baseline methods in DQC workloads.
Accurate and timely quantum state discrimination is critical for quantum computing, particularly in protocols requiring mid-circuit measurement (MCM) and conditional feed-forward. While classical state readout in transistors is near-instantaneous, identifying the state of superconducting qubits remains latency-limited and error-prone. Existing approaches rely on post-processing measurement data transferred to host computers, introducing delays on the order of milliseconds -- vastly exceeding the coherence time of quantum states, which typically last only hundreds of microseconds. To bridge this latency gap, we present an in-situ machine learning (ML) inference engine implemented on a field-programmable gate array (FPGA), enabling real-time quantum state discrimination within 40 ns. Our system supports both two-level (qubit) and three-level (qutrit) systems and performs inference directly on digitized readout signals without host-side intervention. This low-latency operation facilitates mid-circuit measurements, where qubit states are measured and reused within a single quantum circuit, and enables real-time conditional operations essential for quantum error correction. Crucially, fast and accurate mid-circuit readout is a prerequisite for implementing practical fault-tolerant error correction, where errors must be detected and corrected within a single circuit cycle to preserve logical state coherence. We validate our system using superconducting transmon devices, demonstrating robust discrimination fidelity across multiple qubit and qutrit channels. Further, we implement a conditional qutrit logic protocol based on FPGA-resident state classification, highlighting the practical benefits of our approach for NISQ-era quantum algorithms and scalable fault-tolerant architectures.
This work presents QubiCML, a novel FPGA-based system engineered for real-time, in-situ discrimination of two- and three-level quantum states (quitrits) in superconducting quantum processors. Accurate and low-latency identification of quantum states is a critical enabler for scaling quantum computing, particularly as higher-dimensional systems such as qutrits are explored to increase information density, circuit depth, and gate expressivity. QubiCML integrates a lightweight, multi-layer neural network directly into FPGA hardware to classify the qutrit states∣g⟩,∣e⟩, and∣f⟩with high fidelity and minimal latency. Traditional state discrimination methods rely on offline post-processing, resulting in delays incompatible with the short coherence times of superconducting qubits. QubiCML overcomes this bottleneck by performing all inference operations within the FPGA fabric itself, achieving full quantum state discrimination within 66 ns (with softmax) or 40 ns (without softmax). The system supports fast reconfiguration via BRAM-stored parameters, enabling compatibility with varying quantum hardware and dynamic calibration environments. Additionally, we propose FPGA-friendly techniques for data normalization and fixed-point quantization to eliminate the overhead of floating-point and division operations—further optimizing the architecture for real-time deployment. We evaluate QubiCML on in-house superconducting hardware across multiple qubits and qutrits. The system achieves up to 97 % average accuracy for qutrits and up to 99 % for two-level systems, using readout windows as short as 650-750 ns. These results establish QubiCML as one of the first practical implementations of real-time qutrit state discrimination, marking an essential step toward mid-circuit measurements, dynamic feedback, and advanced error correction in higher-dimensional quantum computing.
Fast and accurate qubit-state assignment is essential for feedback, calibration, and error correction in quantum processors. In superconducting platforms, frequency-multiplexed readout makes this task intrinsically multivariate as measured traces can encode crosstalk, qubit-state relaxation events, and other transient nonidealities that are not fully captured by conventional matched filtering. Here, we introduce spiking neural network (SNN) discriminators for superconducting qubit readout. By processing the measurement window in successive time chunks, the networks exploit temporal structure and update classification scores as data arrive, rather than waiting until the end of the readout window. The spiking networks outperform matched-filter discrimination and approach the accuracy of a full-trace artificial neural network. Beyond reaching the performance of artificial neural networks, the key advantage of SNNs is that they provide a streaming, time-resolved estimate of the qubit state that evolves as the readout signal is acquired. Using quantisation-aware training and hls4ml synthesis, we further demonstrate that each FPGA inference update can be completed before the next readout chunk arrives. These results establish spiking neural networks as a promising route to low-latency, real-time qubit readout on FPGA hardware, with broader implications for time-critical quantum-control and scientific-inference applications.
Qutrit state readout is an important technology not only for execution of qutrit algorithms but also for erasure detection in error correction circuits and leakage error characterization of the gate set. Conventional technique using a specialized IQ discriminator requires memory intensive IQ data for input, and has difficulty in scaling up the system size. In this study, we propose the mid-circuit measurement based discrimination technique which exploits a binary discriminator for qubit readout. Our discriminator shows comparable performance with the IQ discriminator, and readily available for standard quantum processors calibrated for qubit control. We also demonstrate our technique can reimplement typical benchmarking and characterization experiments such as leakage randomized benchmarking and state population decay measurement.