arXiv:2608. 15820v1 Announce Type: cross Abstract: We present QuantumPhaseNet, a gauge-covariant geometric and quantum-spectral extension of Transformer representations.
arXiv:2609.06000v1 Announce Type: cross Abstract: We propose ModularPhaseNet, a classical and integer-computable discretization of the continuous complex phase geometry introduced in QuantumPhaseNet....
arXiv:2608. 06846v1 Announce Type: cross Abstract: We test whether a parameterized quantum circuit (PQC) improves a hybrid quantum-classical model's performance on classical datasets, using an interface-matched classical map as the control while holding all other components fixed.
QART is a quantum‑classical hybrid architecture that augments a language model with quantum encoding, CIM‑based QUBO optimization, and quantum decoding to improve long‑horizon reasoning. The authors claim that, under certain assumptions, QART can maintain a non‑zero probability of recovering an optimal reasoning path while traditional autoregressive LLMs see their acceptance probability drop to zero as cumulative risk grows. Experiments on six benchmarks with three backbone models show that QART outperforms the baselines in 14 of 15 pairings, with relative gains up to 84.0% on SciCode.
The study compared a quantum-kernel support vector machine (QSVM) and a variational quantum classifier (VQC) against five tuned classical models across six public clinical datasets, using identical inputs and cross-validation splits. Neither quantum model significantly outperformed any classical counterpart; pooled results showed QSVM differed from a matched RBF SVM by only –0.006 AUROC, and VQC differed from the best classical model by –0.007 AUROC. The authors also introduced the QML-Health-READY eight‑domain reporting framework to guide credible claims in quantum machine learning for health.
The paper demonstrates that quantum transformer blocks can be intrinsically interpretable by tracking quantum mutual information, entanglement entropy, and state fidelity across layers. Experiments on four synthetic tasks show that learned mutual information aligns with task structure, entanglement is essential for accuracy, and mutual information predicts prediction correctness. These findings are validated on IBM Quantum hardware, illustrating that quantum computation’s physics can provide observable interpretability signals.
arXiv:2610.34492v1 Announce Type: cross Abstract: This work proposes a self-attention mechanism based on the fully connected quantum Boltzmann machine (FC-QBM), and further constructs a fully connect...
arXiv:2609.14529v1 Announce Type: cross Abstract: Rigorous empirical validation of quantum machine learning on natural language tasks remains scarce. We evaluate a 10-qubit hybrid quantum-classical v...
The paper investigates the use of classically simulated quantum layers in vision‑language models, specifically adding or replacing components in the LLaVA‑OneVision backbone. Experiments with 4‑ and 8‑qubit circuits show that inserting a quantum layer after the visual projector can raise development accuracy by 2.28 percentage points, while replacing the final decoder feed‑forward sublayer reduces trainable parameters by 13.07 million with only a modest drop in accuracy. The study also evaluates robustness against six attack scenarios, mapping where quantum layers improve or degrade performance and security in multimodal models.
arXiv:2604. 23931v2 Announce Type: replace-cross Abstract: Variational quantum circuits (VQCs) are a leading approach to quantum machine learning on near-term devices, yet it remains unclear which circuit architecture yields the best accuracy-parameter trade-off on classical tabular data.
arXiv:2607. 22516v1 Announce Type: cross Abstract: A central design principle in modern machine learning and artificial intelligence is to align a model's inductive bias with the structure of its input data.
The paper identifies a representational limitation of amplitude encoding in quantum neural networks: normalization makes the encoding invariant to nonzero real rescaling of inputs, which restricts the hypothesis class regardless of the circuit architecture. The authors derive a condition for deterministic preprocessing that removes this ambiguity and propose a fixed nonlinear feature map that distinguishes all real inputs while keeping logarithmic qubit scaling. Experiments on three classification benchmarks and a synthetic dataset show that this new encoding improves accuracy by 21–44 % over both conventional amplitude and angle encodings and a classical neural network.
arXiv:2607.21411v1 Announce Type: cross Abstract: Quantum transfer learning (QTL) is often evaluated by replacing a classical classifier with a fixed variational quantum head, but this hides a key qu...