Multi-Stage Mamba-Based Architecture for Fast and Scalable Superconducting Qubit Readout
arXiv:2607.11668
The paper proposes a lightweight, multi-stage neural architecture based on the Mamba model to improve the speed and fidelity of superconducting qubit readout, especially in frequency-multiplexed systems, by jointly handling state discrimination and relaxation errors.
Abstract
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 , achieving up to a 26% reduction in logical error rate over prior work in quantum error correction (QEC).
Accepted at IEEE International Conference on Quantum Computing and Engineering (QCE) 2026