Tag
Proposes a quantum-inspired hybrid classical-quantum framework for image classification using a mixture of experts, demonstrating improved performance and reduced failure rate on MNIST and Fashion-MNIST datasets.
This paper introduces a tensor network model to capture the influence of emotional valence on the order-dependent structure of children's recognition memory, achieving 77.98% accuracy and demonstrating the value of quantum-inspired methods for modelling cognitive phenomena.
This paper proposes quantum-inspired recurrent models (QKAN-FWPs) for traffic-matrix forecasting, demonstrating superior accuracy with fewer parameters compared to LSTM baselines.
This paper introduces EP-HUBO, a quantum-inspired method that treats evidence selection in chain-of-thought reasoning as a combinatorial optimization problem, significantly improving performance on legal reasoning benchmarks like MMLU-Pro law and LEXam by allowing minority-but-correct hypotheses to override noisy majorities.
A research paper proposing a four-stage hybrid framework for solar and wind energy forecasting, utilizing a quantum-inspired variational kernel for residual correction and a generative AI layer for explainability.
This paper introduces Gated QKAN-FWP, a scalable quantum-inspired sequence learning framework that combines Fast Weight Programmers with Kolmogorov-Arnold Networks using single-qubit data re-uploading circuits.