Searcharxiv⌕ Search

arXiv subjects

En-Jui Kuo

Publications and source records attributed to En-Jui Kuo.

At least 19 recordsLinked to original sources
arXiv2026

Affine-Profile Stabilizer Thresholds for Magic in Codeword-Stabilized Quantum Codes

Codeword-stabilized quantum codes give a unified graph-state description of stabilizer and nonadditive quantum error-correcting codes. Although each individual CWS word state is stabilizer, coherent superpositions of different word states can be nonstabilizer. We develop a CWS-adapted magic-witness framework that isolates this codeword coherence and converts it into certified lower bounds on robustness of magic. The main result is an exact reduction of the stabilizer threshold of a natural CWS coherence witness to a finite-geometric problem over the classical CWS word set. For general weighted superpositions, the threshold is computed by enumerating affine intersections and affine-quadratic phases. For equal-weight superpositions, the phase optimization collapses, and the threshold is determined entirely by how many CWS words can lie in affine flats of each dimension. Thus a quantum optimization over stabilizer states becomes a classical affine-incidence problem. This reduction yields a fixed-parameter algorithm, an analytic lower bound for an infinite union-stabilizer family, and exact rational certificates for several standard nonadditive CWS examples. The framework also clarifies why exact enumeration fails for large structured families and identifies the remaining task as an affine-intersection problem. The result provides a geometric mechanism by which nonlinear CWS word sets generate certifiable magic.

quant-ph↗
arXiv2026

Hybrid Quantum-inspired Kolmogorov-Arnold Networks for Privacy-Aware Federated Biosignal Learning

Electrocardiogram (ECG) recordings are sensitive biomedical data, limiting the ability of hospitals and wearable devices to share raw signals for centralized model training. Federated learning addresses this practical privacy constraint by enabling collaborative model training while keeping raw biosignal data at their respective sources. However, federated ECG classification remains challenging due to limited client-side samples, imbalanced arrhythmia labels, and non-independent and identically distributed (non-IID) data across clients. These constraints require classifiers that are both communication-efficient and robust to cross-client distribution shifts. In this work, we evaluate a hybrid quantum-inspired Kolmogorov-Arnold network (HQKAN) against a multilayer perceptron (MLP) for five-class arrhythmia classification on the MIT-BIH dataset and three-class classification on the INCART dataset under federated averaging (FedAvg). Across multiple client configurations, HQKAN improves most aggregate and minority-class metrics while using 37.35% fewer trainable parameters and reducing communication cost by 24.89% on MIT-BIH; on INCART, it achieves corresponding reductions of 44.81% and 36.41%. These results indicate that HQKAN offers a compact, communication-efficient and robust alternative to the MLP baseline for privacy-aware federated learning on biosignal data.

cs.LG↗
arXiv2026

Complementary Matrix-Gated QKAN Fast-Weight Programmers for Quantum Dynamics Forecasting

Sequence models must decide what to write into memory and what to retain. In quantum and quantum-inspired sequence learning, nonlinear recurrent updates often require repeated circuit evaluations and sequential backpropagation through time, making long contexts costly. Gated fast-weight programmers (FWPs) based on quantum-inspired Kolmogorov-Arnold networks (QKANs) alleviate this bottleneck by storing context in time-varying fast parameters. However, their scalar gate applies one retention-write balance to every fast-state coordinate, forcing all parameters to share a memory timescale. We introduce Self-Modulating QKAN-based FWPs, which replace this broadcast gate with low-rank-generated element-wise modulation of the new-proposal branch, a bounded old-state branch, or both. We further propose Complementary Matrix Gating (CMG), which uses one sigmoid matrix gate to retain the old state and its complement to write the new proposal. CMG provides coordinate-wise memory control while preserving the bounded convex update and affine prefix-scan structure of scalar gating, at the modulation-head cost of a single-branch rule. We compare four self-modulating rules with scalar gating across four FWP architectures combining classical and QKAN-based slow and fast programmers. Across seven single-step forecasting benchmarks and five sequence lengths, CMG gives the most consistent improvements for architectures whose fast programmer incorporates a QKAN-based module. In direct multi-step forecasting of Jaynes-Cummings and transmon-resonator dynamics simulated with CUDA-Q Dynamics, CMG models maintain mean-squared errors on the order of 0.001 or lower across forecasting horizons of 4, 8, and 16 steps, while improving on their scalar-gated counterparts by at least 91.2%. These results establish coordinate-wise complementary modulation as a stable and effective update for QKAN-based FWPs.

quant-ph↗
arXiv2026

Rethinking Quantum Continual Learning with Quantum Fisher Information

Quantum continual learning aims to train quantum models on sequential tasks without losing previously learned knowledge. However, variational quantum classifiers (VQCs) are prone to catastrophic forgetting under nonstationary task distributions. We propose quantum elastic weight consolidation (QEWC), a quantum Fisher information (QFI)-informed regularization method for mitigating forgetting. Unlike conventional elastic weight consolidation based on classical Fisher information (CFI), which measures parameter importance through measurement-dependent output statistics, QEWC uses QFI to quantify the intrinsic sensitivity of the parameterized quantum state. This gives an information-geometric view in which important parameters are identified by the local response of the quantum state manifold. We evaluate QEWC on VQCs trained on sequential binary classification tasks, including classical image-classification and quantum phase-classification tasks. Simulations show that sequential training without regularization causes severe forgetting, while both CFI-based EWC and QFI-based QEWC improve retention of previous tasks. Mechanistic analyses further show that the two methods impose different regularization geometries: CFI acts selectively on measurement-sensitive directions, whereas QFI imposes a denser state-geometric constraint over parameter space. Under depolarizing noise, CFI values are strongly suppressed by degraded measurement statistics, while QFI preserves a more stable sensitivity structure of the noisy parameterized quantum state. These results establish QEWC as a physically motivated approach for studying and mitigating forgetting in quantum continual learning through quantum-state geometry.

quant-ph↗
arXiv2026

Near-Optimal Mode Scaling for Finite-Dimensional Boson Sampling via Lie-Algebraic Leakage Bounds

Boson sampling demonstrates quantum advantage through the interference of indistinguishable particles, with output probabilities governed by matrix permanents. Realizing it on deterministic, matter-based platforms requires encoding the bosonic modes in finite-dimensional local Hilbert spaces, which introduces a leakage channel absent in linear optics: multi-particle bunching beyond the local truncation $d$. We develop a unified framework for non-interacting sampling on the irreducible representations of compact Lie groups, in which the transition amplitude is the immanant of a submatrix of the single-particle transition matrix, recovering the permanent in the bosonic case. Within this framework we bound the bunching leakage through a Dyson-series analysis: decomposing the correlated many-body leakage operator into independent random matrices and applying non-commutative concentration inequalities, we prove, in a Gaussian model of the transition matrix, that its spectral norm concentrates at $\tilde{O}(\sqrt{n})$ rather than the $O(n)$ worst-case of prior spin-based emulations; the passage to the physical Haar ensemble is reduced to a single submatrix-comparison input, verified at leading order. Exact numerics across local dimensions $d=2$--$5$ indicate that the bound is tight, the Haar-ensemble norm matching the closed form $\sqrt{d(n-d+1)}$ to sub-percent accuracy. This tightens the required mode number from $m=\Omega(n^4)$ to the near-optimal $m=\tilde{\Omega}(n^{1+2/(d-1)})$; for a spin-1 representation ($d=3$) the overhead falls to $m=\tilde{\Omega}(n^2)$, matching the collision-free threshold. The result is independent of particle statistics and applies across finite-dimensional Lie-symmetric architectures, quantifying the spatial resources needed to preserve sampling hardness.

quant-ph↗
arXiv2026

An Iterative Dual-Channel Neural Quantum State Algorithm for Selected Configuration Interaction

Accurately solving the electronic Schr\"{o}dinger equation for strongly correlated systems remains a central challenge in quantum chemistry, where the exponential growth of configuration space limits the applicability of exact methods. Selected Configuration Interaction (SCI) algorithms address this challenge by adaptively constructing compact determinantal expansions, yet their efficiency depends critically on the quality of the sampling strategy used to identify chemically important configurations. Here we introduce the Handover Iterative Neural Quantum State (HI-NQS) algorithm, which embeds a classically trained autoregressive Transformer neural quantum state within the iterative sample--diagonalize--update framework of Sample-Based Quantum Diagonalization. A dual-channel Transformer architecture with explicit spin-up/spin-down cross-attention encodes fermionic spin structure as an architectural inductive bias, enabling expressive and physically informed wavefunction representations. After each subspace diagonalization, the resulting eigenvector is distilled back into the network through a factorized spin-marginal teacher signal, establishing a closed feedback loop between generative sampling and exact diagonalization. Benchmarks across a range of small molecules and a systematic nitrogen active-space series demonstrate that HI-NQS achieves chemical accuracy on all systems tested, with determinant-count scaling substantially more favorable than conventional CIPSI-based SCI for all but the smallest active spaces. All calculations are performed on GPU hardware without quantum computing resources, establishing HI-NQS as an efficient and scalable purely classical approach to the selected configuration interaction problem.

physics.chem-ph↗
arXiv2026

Lattice-quantile estimation of {\pi} and convex-region integrals from coined two-dimensional quantum walks

Monte Carlo integration is fundamentally limited by the M^(-1/2) rate that the Cramer-Rao bound imposes on any sample-mean estimator of an expectation value, regardless of how the samples are drawn. Coined discrete-time quantum walks (DTQWs) are known to spread ballistically - their position variance scales as T^2 against the diffusive T of classical random walks - yet this faster spreading has not been exploited for numerical integration. We show that coupling the ballistic scaling of a 2D DTQW to the Hardy-Huxley asymptotic for Gauss circle lattice counts produces estimators whose dominant error is a deterministic number-theoretic residual controlled by walk depth T, not a statistical fluctuation controlled by sample count M. The construction replaces the empirical mean of a sample-mean estimator with the ratio N(R-hat)/R-hat^2 of a lattice count to the square of a radial position quantile, a structural change that sidesteps the Cramer-Rao barrier. A single batch of measurements then propagates through classically precomputed multipliers to cover an entire family of integrals simultaneously. We develop the framework for convex smooth domains via Kraetzel's lattice asymptotic and for smooth integrals with convex or annular super-level sets via Cavalieri's principle, and provide a parameter-free identity for the bias floor (validated to within 1.5x across all tested depths). Every experiment is benchmarked against the classical random walk with the identical estimator to isolate the quantum contribution; the framework is oracle-free in the QAE sense (no controlled unitary encoding the integrand is required) and structurally distinct from quantum amplitude estimation and Szegedy-walk approaches. These ratios compare measurement counts at fixed precision and do not include quantum circuit execution cost.

quant-ph↗
arXiv2026

Split-Head Quantum Generative Adversarial Network for Crystalline Material Discovery

The discovery of novel crystalline materials is a critical challenge in computational materials science, often limited by the spatial representation limitations and mode collapse typical of classical generative models. Traditionally, developing Quantum GANs for continuous 3D space is hindered by the limited capacity of near-term hardware. To overcome this, we adapt a physics-informed "split-head" architecture right from the quantum trunk to explicitly decouple macroscopic lattice bounds from microscopic atomic coordinates, significantly maximizing resource efficiency. This study disentangles the contributions of quantum circuits from these architectural priors by evaluating a Split-Head Quantum Generative Adversarial Network against an architecture-matched classical ablation model. Evaluated on the highly constrained Mg-Mn-O system, the results reveal a highly nuanced performance dichotomy between the advanced models. The architecture-matched classical ablation model demonstrated superior thermodynamic precision. Conversely, the integration of quantum circuits in the SH-QGAN drove unparalleled structural breadth and latent space exploration, more than doubling the ablation's geometric validity and successfully generating novel, metastable candidates converging on the Mg2MnO4 stoichiometry. These findings clarify that while architectural separation of cell and atom generation drives strict thermodynamic precision, quantum feature mapping independently provides the spatial diversity necessary to overcome mode collapse. Both mechanisms offer distinct, complementary enhancements for the generative discovery of advanced materials.

quant-ph↗
arXiv2026

Gated QKAN-FWP: Scalable Quantum-inspired Sequence Learning

Fast Weight Programmers (FWPs) encode temporal dependencies through dynamically updated parameters rather than recurrent hidden states. Quantum FWPs (QFWPs) extend this idea with variational quantum circuits (VQCs), but existing implementations rely on multi-qubit architectures that are difficult to scale on noisy intermediate-scale quantum (NISQ) devices and expensive to simulate classically. We propose gated QKAN-FWP, a fast-weight framework that integrates FWP with Quantum-inspired Kolmogorov-Arnold Network (QKAN) using single-qubit data re-uploading circuits as learnable nonlinear activation, known as DatA Re-Uploading ActivatioN (DARUAN). We further introduce a scalar-gated fast-weight update rule that stabilizes parameter evolution, supported by a theoretical analysis of its adaptive memory kernel, geometric boundedness, and parallelizable gradient paths. We evaluate the framework across time-series benchmarks, MiniGrid reinforcement learning, and highlight real-world solar cycle forecasting as our main practical result. In the long-horizon setting with 528-month input window and 132-month forecast horizon, our 12.5k-parameter model achieves lower scaled Mean Square Error (MSE), peak amplitude error, and peak timing error than a suite of classical recurrent baselines with up to 13x more parameters, including Long Short-Term Memory (LSTM) networks (25.9k-89.1k parameters), WaveNet-LSTM (167k), Vanilla recurrent neural network (11.5k), and a Modified Echo State Network (132k). To validate NISQ compatibility, we further deploy the trained fast programmer on IonQ and IBM Quantum processors, recovering forecasting accuracy within 0.1% relative MSE of the noiseless simulator at 1024 shots. These results position gated QKAN-FWP as a scalable, parameter-efficient, and NISQ-compatible approach to quantum-inspired sequence modeling.

cs.LG↗
arXiv2026

Quantum Magic in early FTQC: From Diagonal Clifford Hierarchy No-Go Theorems to Architecture Design Blueprints

We address the circuit-design problem of maximizing quantum magic in early fault-tolerant quantum computing (early FTQC), where logical dynamics natively take the form of alternating Clifford layers and diagonal non-Clifford layers. To render this optimization analytically tractable, we first prove a uniqueness theorem: for operational magic functionals built from Pauli expectation values, the axioms of faithfulness and tensor-product additivity force a R\'enyi-type dependence on the Pauli-spectrum. Leveraging the closed phase-polynomial description of the diagonal Clifford hierarchy, we derive exact Pauli-spectrum expressions and tight bounds for a shallow-layer model. These bounds expose a zero-magic mechanism and prove that maximal magic strictly requires graph-state preconditioning. Consequently, we establish our first no-go theorem: hierarchy level alone cannot universally order operational magic. Extending our framework to the $N$-layer model motivated by the Space-Time Efficient Analog Rotation (STAR) architecture, we obtain an exact iterative update rule for the Pauli spectrum. This yields a second no-go theorem: no state-independent sequence of operations can guarantee monotonic magic improvement. Together, these theorems demonstrate that algebraic gate structures are fundamentally insufficient to dictate resource generation. To overcome this, we reframe early FTQC gate selection as a state-aware, differentiable optimization over continuous analog parameters. Finally, we identify a severe kinematic expressibility bottleneck in architectures restricted to single-qubit $Z$-rotations and show that introducing nonlinear diagonal phases, such as multi-qubit $Z$-rotation, shatters this bottleneck. This provides a fundamental principle for demonstrating early FTQC, establishing scalable magic generation as a foundational benchmark for evaluating early FTQC architectures.

quant-ph↗
arXiv2026

Do Quantum Transformers Help? A Systematic VQC Architecture Comparison on Tabular Benchmarks

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. We present a systematic empirical comparison of four VQC families -- multi-layer fully-connected (FC-VQC), residual (ResNet-VQC), hybrid quantum-classical transformer (QT), and fully quantum transformer (FQT) -- across five regression and classification benchmarks. Our key findings are: \textbf{(i)}~FC-VQCs achieve 90-96\% of the $R^2$ of attention-based VQCs while using 40-50\% fewer parameters, and consistently outperform equal-capacity MLPs (mean $R^2{=}0.829$ vs.\ MLP$_{720}$'s $0.753$ on Boston Housing, 3-seed average); \textbf{(ii)}~FC-VQC's Type~4 inter-block connectivity provides partial cross-token mixing that approximates the role of attention -- explicit quantum self-attention yields only marginal gains on most datasets while significantly increasing parameter count; \textbf{(iii)}~expressibility saturates at circuit depth~${\approx}\,3$, explaining why shallow VQCs already cover the Hilbert space effectively; \textbf{(iv)}~LayerNorm on the fully quantum transformer improves classification accuracy, suggesting normalization is important when all operations are quantum; \textbf{(v)}~in our noise study on Boston Housing, FQT degrades gracefully under depolarizing noise while QT collapses. All results are validated across three random seeds. These findings provide practical architectural guidance for deploying VQCs on near-term quantum hardware.

quant-ph↗
arXiv2026

Few-Shot Continual Learning for 3D Brain MRI with Frozen Foundation Models

Foundation models pretrained on large-scale 3D medical imaging data face challenges when adapted to multiple downstream tasks under continual learning with limited labeled data. We address few-shot continual learning for 3D brain MRI by combining a frozen pretrained backbone with task-specific Low-Rank Adaptation (LoRA) modules. Tasks arrive sequentially -- tumor segmentation (BraTS) and brain age estimation (IXI) -- with no replay of previous task data. Each task receives a dedicated LoRA adapter; only the adapter and task-specific head are trained while the backbone remains frozen, thereby eliminating catastrophic forgetting by design (BWT=0). In continual learning, sequential full fine-tuning suffers severe forgetting (T1 Dice drops from 0.80 to 0.16 after T2), while sequential linear probing achieves strong T1 (Dice 0.79) but fails on T2 (MAE 1.45). Our LoRA approach achieves the best balanced performance across both tasks: T1 Dice 0.62$\pm$0.07, T2 MAE 0.16$\pm$0.05, with zero forgetting and $<$0.1\% trainable parameters per task, though with noted systematic age underestimation in T2 (Wilcoxon $p<0.001$). Frozen foundation models with task-specific LoRA adapters thus offer a practical solution when both tasks must be maintained under few-shot continual learning.

eess.IV↗
arXiv2026

Meta-Learning for GPU-Accelerated Quantum Many-Body Problems

We explore the industrial and scientific applicability of the VQE-LSTM framework by integrating meta-learning with GPU accelerated quantum simulation using NVIDIA's CUDA-Q (CUDAQ) platform. This work demonstrates how an LSTM-FC meta-initialization module can extend the practical reach of the Variational Quantum Eigensolver (VQE) in both chemistry and physics domains. In the chemical regime, the framework predicts ground-state energies of molecular Hamiltonians derived from PySCF, achieving near FCI accuracy while maintaining favorable O(N^2) scaling with molecular size. In the physical counterpart, we applied the same model to quantized Simple Harmonic Motion systems (SHM), successfully reproducing its ground and excited states through VQE and Variational Quantum Deflation (VQD) methods. Benchmark results on NVIDIA GPUs reveal significant speedups over CPU-based implementations, validating CUDAQ's capability to handle large-scale variational workloads efficiently. Overall, this study establishes VQE-LSTM as a viable and scalable approach for GPU accelerated quantum simulation, bridging quantum chemistry and condensed-matter physics through a unified, meta-learned initialization strategy.

quant-ph↗
arXiv2026

FreqLens: Interpretable Frequency Attribution for Time Series Forecasting

Time series forecasting models often lack interpretability, limiting their adoption in domains requiring explainable predictions. We propose \textsc{FreqLens}, an interpretable forecasting framework that discovers and attributes predictions to learnable frequency components. \textsc{FreqLens} introduces two key innovations: (1) \emph{learnable frequency discovery} -- frequency bases are parameterized via sigmoid mapping and learned from data with diversity regularization, enabling automatic discovery of dominant periodic patterns without domain knowledge; and (2) \emph{axiomatic frequency attribution} -- a theoretically grounded framework that provably satisfies Completeness, Faithfulness, Null-Frequency, and Symmetry axioms, with per-frequency attributions equivalent to Shapley values. On Traffic and Weather datasets, \textsc{FreqLens} achieves competitive or superior performance while discovering physically meaningful frequencies: all 5 independent runs discover the 24-hour daily cycle ($24.6 \pm 0.1$h, 2.5\% error) and 12-hour half-daily cycle ($11.8 \pm 0.1$h, 1.6\% error) on Traffic, and weekly cycles ($10\times$ longer than the input window) on Weather. These results demonstrate genuine frequency-level knowledge discovery with formal theoretical guarantees on attribution quality.

cs.LG↗
arXiv2026

A Unified SPD Token Transformer Framework for EEG Classification: Systematic Comparison of Geometric Embeddings

Spatial covariance matrices of EEG signals are Symmetric Positive Definite (SPD) and lie on a Riemannian manifold, yet the theoretical connection between embedding geometry and optimization dynamics remains unexplored. We provide a formal analysis linking embedding choice to gradient conditioning and numerical stability for SPD manifolds, establishing three theoretical results: (1) BWSPD's $\sqrt{\kappa}$ gradient conditioning (vs $\kappa$ for Log-Euclidean) via Daleckii-Kre\u{\i}n matrices provides better gradient conditioning on high-dimensional inputs ($d \geq 22$), with this advantage reducing on low-dimensional inputs ($d \leq 8$) where eigendecomposition overhead dominates; (2) Embedding-Space Batch Normalization (BN-Embed) approximates Riemannian normalization up to $O(\varepsilon^2)$ error, yielding $+26\%$ accuracy on 56-channel ERP data but negligible effect on 8-channel SSVEP data, matching the channel-count-dependent prediction; (3) bi-Lipschitz bounds prove BWSPD tokens preserve manifold distances with distortion governed solely by the condition ratio $\kappa$. We validate these predictions via a unified Transformer framework comparing BWSPD, Log-Euclidean, and Euclidean embeddings within identical architecture across 1,500+ runs on three EEG paradigms (motor imagery, ERP, SSVEP; 36 subjects). Our Log-Euclidean Transformer achieves state-of-the-art performance on all datasets, substantially outperforming classical Riemannian classifiers and recent SPD baselines, while BWSPD offers competitive accuracy with similar training time.

cs.LG↗
arXiv2025

Quantum Temporal Convolutional Neural Networks for Cross-Sectional Equity Return Prediction: A Comparative Benchmark Study

Quantum machine learning offers a promising pathway for enhancing stock market prediction, particularly under complex, noisy, and highly dynamic financial environments. However, many classical forecasting models struggle with noisy input, regime shifts, and limited generalization capacity. To address these challenges, we propose a Quantum Temporal Convolutional Neural Network (QTCNN) that combines a classical temporal encoder with parameter-efficient quantum convolution circuits for cross-sectional equity return prediction. The temporal encoder extracts multi-scale patterns from sequential technical indicators, while the quantum processing leverages superposition and entanglement to enhance feature representation and suppress overfitting. We conduct a comprehensive benchmarking study on the JPX Tokyo Stock Exchange dataset and evaluate predictions through long-short portfolio construction using out-of-sample Sharpe ratio as the primary performance metric. QTCNN achieves a Sharpe ratio of 0.538, outperforming the best classical baseline by approximately 72\%. These results highlight the practical potential of quantum-enhanced forecasting model, QTCNN, for robust decision-making in quantitative finance.

cs.LG↗
arXiv2025

QKAN-LSTM: Quantum-inspired Kolmogorov-Arnold Long Short-term Memory

Long short-term memory (LSTM) models are a particular type of recurrent neural networks (RNNs) that are central to sequential modeling tasks in domains such as urban telecommunication forecasting, where temporal correlations and nonlinear dependencies dominate. However, conventional LSTMs suffer from high parameter redundancy and limited nonlinear expressivity. In this work, we propose the Quantum-inspired Kolmogorov-Arnold Long Short-Term Memory (QKAN-LSTM), which integrates Data Re-Uploading Activation (DARUAN) modules into the gating structure of LSTMs. Each DARUAN acts as a quantum variational activation function (QVAF), enhancing frequency adaptability and enabling an exponentially enriched spectral representation without multi-qubit entanglement. The resulting architecture preserves quantum-level expressivity while remaining fully executable on classical hardware. Empirical evaluations on three datasets, Damped Simple Harmonic Motion, Bessel Function, and Urban Telecommunication, demonstrate that QKAN-LSTM achieves superior predictive accuracy and generalization with a 79% reduction in trainable parameters compared to classical LSTMs. We extend the framework to the Jiang-Huang-Chen-Goan Network (JHCG Net), which generalizes KAN to encoder-decoder structures, and then further use QKAN to realize the latent KAN, thereby creating a Hybrid QKAN (HQKAN) for hierarchical representation learning. The proposed HQKAN-LSTM thus provides a scalable and interpretable pathway toward quantum-inspired sequential modeling in real-world data environments.

quant-ph↗
arXiv2025

Quantum Reinforcement Learning-Guided Diffusion Model for Image Synthesis via Hybrid Quantum-Classical Generative Model Architectures

Diffusion models typically employ static or heuristic classifier-free guidance (CFG) schedules, which often fail to adapt across timesteps and noise conditions. In this work, we introduce a quantum reinforcement learning (QRL) controller that dynamically adjusts CFG at each denoising step. The controller adopts a hybrid quantum--classical actor--critic architecture: a shallow variational quantum circuit (VQC) with ring entanglement generates policy features, which are mapped by a compact multilayer perceptron (MLP) into Gaussian actions over $\Delta$CFG, while a classical critic estimates value functions. The policy is optimized using Proximal Policy Optimization (PPO) with Generalized Advantage Estimation (GAE), guided by a reward that balances classification confidence, perceptual improvement, and action regularization. Experiments on CIFAR-10 demonstrate that our QRL policy improves perceptual quality (LPIPS, PSNR, SSIM) while reducing parameter count compared to classical RL actors and fixed schedules. Ablation studies on qubit number and circuit depth reveal trade-offs between accuracy and efficiency, and extended evaluations confirm robust generation under long diffusion schedules.

quant-ph↗