Answers are grounded in this paper and cite their sources.
Continuous-variable (CV) quantum systems provide a versatile platform for quantum information processing, in which quantum states can be represented in the quadrature phase space. In realistic implementations, environmental noise, primarily photon loss and dephasing, progressively degrades these states. Machine-learning-based quantum error mitigation (QEM) has recently emerged as a promising approach to suppress such noise; however, existing methods are typically limited to the training horizon and require training data that cover the entire evolution, which is experimentally demanding. Here we introduce a framework for extrapolative quantum error mitigation based on a time-conditioned Swin Transformer. By combining the nonlocal phase-space representation of the Swin Transformer with continuous time conditioning through adaptive layer normalization, the model learns a time-conditioned correction map for noisy CV states. Numerical simulations under both Markovian and non-Markovian noise demonstrate reduced reconstruction error beyond the training horizon compared with the unrepaired noisy input. These results establish temporal extrapolation as a viable strategy for reducing the training-data burden in CV quantum error mitigation.
No takes yet. Share an insight, caveat, or question.
Zhang et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: