arXiv subjects

Kai Wen

Publications and source records attributed to Kai Wen.

At least 19 recordsLinked to original sources

arXiv2026

A generalized variational quantum linear solver on photonic platform

Based on a photonic computing platform, we experimentally validate a generalized variational quantum linear solver (VQLS) by systematically solving four-dimensional linear equation systems across different fields. In the complex field, in addition to solving non-singular systems that admit a unique solution, we investigate ill-conditioned problems arising from singularity--an issue frequently encountered in practical applications. To tackle these challenges, we introduce perturbation terms, a treatment inspired by Tikhonov regularization, and develop an algorithm capable of handling a wide range of systems. Furthermore, we extend the VQLS to the finite field F2 by redesigning the cost function to incorporate modulo 2 and imposing several constraints on the solution vector. This modulo 2 VQLS is inherently free from singularity. It is adapt to stabilizer coding theory and may find applications in areas such as decoders and the design of quantum gate sequences. Therefore, our work demonstrates the practical potential of VQLS in quantum computing, providing a solid experimental foundation and methodological guidance for its real-world applications.

quant-ph↗

arXiv2026

EPIC-CIM: Training Convolutional Neural Networks on a Coherent Ising Machine via Equilibrium Propagation

Quantum convolutional neural networks, due to the involvement of quantum measurements and discrete quantum state evolution, face inherent training challenges associated with non-differentiable operations and discrete optimization dynamics, which make conventional gradient-based learning difficult to apply effectively. In this context, energy-based learning provides a promising alternative by reformulating network training as an energy minimization process without explicit gradient backpropagation.In this framework, input data are processed through convolutional operations, followed by quantum sampling to generate intermediate binary representations, while the output layer also relies on quantum sampling to produce final predictions. The overall network energy is composed of convolutional feature matching terms, linear coupling terms at the output layer, and global output constraint terms, enabling both parameter updates and feature evolution to be described through physically interpretable energy dynamics. Furthermore, under the equilibrium propagation mechanism, the energy difference between the free phase and the weakly clamped phase is exploited to drive parameter updates without explicit gradient computation, thereby enabling stable and consistent learning in non-differentiable and discrete spaces. While remaining consistent with classical convolutional learning theory, the proposed framework enhances interpretability and observability through quantum energy modeling, offering a unified physical perspective for efficient QCNN training and the integration of quantum computing with artificial intelligence.

quant-ph↗

arXiv2026

A Modular Benchmark of Variational Quantum Attack Algorithms for S-DES

Variational quantum algorithms (VQAs) have emerged as a promising approach to quantum cryptanalysis on noisy intermediate-scale quantum (NISQ) devices. Although numerous variational attack schemes have been proposed for symmetric cryptosystems, a systematic and modular benchmarking framework to evaluate their performance is still lacking. In this work, we present a comprehensive benchmark study of variational quantum attacks on the Simplified Data Encryption Standard (S-DES), focusing on the modular design choices that determine attack efficiency. We formulate variational quantum attacks within a unified framework consisting of four components: initial state preparation, parameterized circuit (Ansatz) design, cost function construction, and classical optimization. Through numerical simulations, we systematically compare representative design alternatives and evaluate their combinations in terms of convergence behavior, success probability, and effective time complexity. We further introduce standardized metrics for assessing variational quantum attack performance. Our results reveal clear performance hierarchies among different modular configurations and show that carefully optimized designs can significantly outperform naive quantum search. This work establishes a principled benchmark methodology for variational quantum cryptanalysis and positions S-DES as a practical testbed for evaluating quantum attacks on symmetric ciphers in the NISQ era.

quant-ph↗

arXiv2026

Exact and Asymptotically Complete Robust Verifications of Neural Networks via Ising Solvers

We present an Ising-compatible framework for formal neural-network robustness verification under bounded input perturbations. For piecewise-linear activations, the Exact Logarithmic PWL Model (Log-PWL) provides an exact, sound, and complete formulation with a state-optimal logarithmic encoding, reducing the binary variables per neuron from linear to information-theoretically minimal logarithmic complexity. For general bounded element-wise activations, the Asymptotic Step-Envelope Model (Step-Env) uses sound piecewise-constant envelopes whose lower and upper neuron states remain decision variables coupled to a common adversarial input. We prove that its globally optimized output bounds converge uniformly to the true network extrema as the segment width vanishes, yielding asymptotic completeness of verification. We further develop a hybrid Benders solver with output-sensitive iteration bounds, leveraging a Helly-based conflict compression theory to avoid generic exponential cut explosion. Interval pruning, certificate transfer for pruned networks, and layerwise classical--Ising partitioning further reduce spin requirements. Experiments show exact certification fidelity for piecewise-linear networks and near-reference accuracy for sigmoid networks with compact spin budgets.

cs.LG↗

arXiv2026

Kaiwu-PyTorch-Plugin: Bridging Deep Learning and Photonic Quantum Computing for Energy-Based Models and Active Sample Selection

This paper introduces the Kaiwu-PyTorch-Plugin (KPP) to bridge Deep Learning and Photonic Quantum Computing across multiple dimensions. KPP integrates the Coherent Ising Machine into the PyTorch ecosystem, addressing classical inefficiencies in Energy-Based Models. The framework facilitates quantum integration in three key aspects: accelerating Boltzmann sampling, optimizing training data via Active Sampling, and constructing hybrid architectures like QBM-VAE and Q-Diffusion. Empirical results on single-cell and OpenWebText datasets demonstrate KPPs ability to achieve SOTA performance, validating a comprehensive quantum-classical paradigm.

quant-ph↗

arXiv2026

OpenVTON-Bench: A Large-Scale High-Resolution Benchmark for Controllable Virtual Try-On Evaluation

Recent advances in diffusion models have significantly elevated the visual fidelity of Virtual Try-On (VTON) systems, yet reliable evaluation remains a persistent bottleneck. Traditional metrics struggle to quantify fine-grained texture details and semantic consistency, while existing datasets fail to meet commercial standards in scale and diversity. We present OpenVTON-Bench, a large-scale benchmark comprising approximately 100K high-resolution image pairs (up to $1536 \times 1536$). The dataset is constructed using DINOv3-based hierarchical clustering for semantically balanced sampling and Gemini-powered dense captioning, ensuring a uniform distribution across 20 fine-grained garment categories. To support reliable evaluation, we propose a multi-modal protocol that measures VTON quality along five interpretable dimensions: background consistency, identity fidelity, texture fidelity, shape plausibility, and overall realism. The protocol integrates VLM-based semantic reasoning with a novel Multi-Scale Representation Metric based on SAM3 segmentation and morphological erosion, enabling the separation of boundary alignment errors from internal texture artifacts. Experimental results show strong agreement with human judgments (Kendall's $\tau$ of 0.833 vs. 0.611 for SSIM), establishing a robust benchmark for VTON evaluation.

cs.CV↗

arXiv2026

Near-optimal discrimination of displaced squeezed binary signals using displacement, inverse-squeezing, and photon-number-resolving detection

We propose an inverse-squeezing Kennedy receiver for discriminating binary phase-shift-keyed displaced squeezed vacuum states. The receiver combines a Kennedy-type nulling displacement, an orthogonally oriented inverse-squeezing operation and photon-number-resolving detection with a maximum-a-\emph{posteriori} threshold rule. Its key mechanism is that the inverse-squeezing stage converts transmitter-side squeezing into enhanced photon-number contrast, or equivalently an effective coherent-state energy gain, that can be directly exploited at the measurement stage. Under ideal equal-prior conditions, the receiver surpasses the standard quantum limit for squeezed-state binary phase-shift keying at approximately $N\approx 0.3$, outperforms the Helstrom bound of coherent-state binary phase-shift keying at approximately $N\approx 0.4$, and reaches the 1\% error level near $N\approx 0.6$. We further analyze its performance under realistic imperfections, including finite detector efficiency, dark counts, channel phase diffusion, receiver thermal noise and transmission loss. The results show that adaptive thresholding preserves robust performance against detector and noise imperfections over practical parameter ranges, whereas transmission loss progressively suppresses the squeezing-enabled advantage. These findings indicate that, for the fixed source parametrization adopted in this work, the proposed receiver is most advantageous in the low-loss regime, especially at low source energies.

quant-ph↗

arXiv2025

A versatile coherent Ising computing platform

Coherent Ising Machines (CIMs) have emerged as a hybrid form of quantum computing devices designed to solve NP-complete problems, offering an exciting opportunity for discovering optimal solutions. Despite challenges such as susceptibility to noise-induced local minima, we achieved notable advantages in improving the computational accuracy and stability of CIMs. We conducted a successful experimental demonstration of CIM via femto-second laser pumping that integrates optimization strategies across optical and structural dimensions, resulting in significant performance enhancements. The results are particularly promising. An average success rate of 55% was achieved to identify optimal solutions within a Mobius Ladder graph comprising 100 vertices. Compared with other alternatives, the femto-second pulse results in significantly higher peak power, leading to more pronounced quantum effects and lower pump power in optical fiber based CIMs. In addition, we have maintained an impressive success rate for a continuous period of 8 hours, emphasizing the practical applicability of CIMs in real-world scenarios. Furthermore, our research extends to the application of these principles in practical applications such as molecular docking and credit scoring. The results presented substantiate the theoretical promise of CIMs, paving the way for their integration into large-scale practical applications.

quant-ph↗

arXiv2025

Quantum-Boosted High-Fidelity Deep Learning

A fundamental limitation of probabilistic deep learning is its predominant reliance on Gaussian priors. This simplistic assumption prevents models from accurately capturing the complex, non-Gaussian landscapes of natural data, particularly in demanding domains like complex biological data, severely hindering the fidelity of the model for scientific discovery. The physically-grounded Boltzmann distribution offers a more expressive alternative, but it is computationally intractable on classical computers. To date, quantum approaches have been hampered by the insufficient qubit scale and operational stability required for the iterative demands of deep learning. Here, we bridge this gap by introducing the Quantum Boltzmann Machine-Variational Autoencoder (QBM-VAE), a large-scale and long-time stable hybrid quantum-classical architecture. Our framework leverages a quantum processor for efficient sampling from the Boltzmann distribution, enabling its use as a powerful prior within a deep generative model. Applied to million-scale single-cell datasets from multiple sources, the QBM-VAE generates a latent space that better preserves complex biological structures, consistently outperforming conventional Gaussian-based deep learning models like VAE and SCVI in essential tasks such as omics data integration, cell-type classification, and trajectory inference. It also provides a typical example of introducing a physics priori into deep learning to drive the model to acquire scientific discovery capabilities that breaks through data limitations. This work provides the demonstration of a practical quantum advantage in deep learning on a large-scale scientific problem and offers a transferable blueprint for developing hybrid quantum AI models.

cs.LG↗

arXiv2025

Alleviating CoD in Renewable Energy Profile Clustering Using an Optical Quantum Computer

The traditional clustering problem of renewable energy profiles is typically formulated as a combinatorial optimization that suffers from the Curse of Dimensionality (CoD) on classical computers. To address this issue, this paper first proposed a kernel-based quantum clustering method. More specifically, the kernel-based similarity between profiles with minimal intra-group distance is encoded into the ground-state of the Hamiltonian in the form of an Ising model. Then, this NP-hard problem can be reformulated into a Quadratic Unconstrained Binary Optimization (QUBO), which a Coherent Ising Machine (CIM) can naturally solve with significant improvement over classical computers. The test results from a real optical quantum computer verify the validity of the proposed method. It also demonstrates its ability to address CoD in an NP-hard clustering problem.

quant-ph↗

arXiv2025

Towards Provable and Scalable Training of Quantized Neural Networks with Ising Optimization

Training quantized neural networks remains fundamentally challenging due to non-convex loss landscapes and discrete parameter spaces. We introduce an exact Quadratic Constrained Binary Optimization (QCBO) framework with provable guarantees. We first characterize the stratified topology of network zero-loss level sets: generic interior strata are smooth, yet globally optimal components can remain disconnected even under overparameterization. To address this non-convex obstruction, we compile finite-depth architectures with parameter codebooks and Forward Interval Propagation (FIP)-bounded states into bounded QCBOs, yielding an exact completely positive convex formulation that preserves the global discrete optimum with zero relaxation gap. To overcome monolithic sample scaling, we formulate sample-wise Decomposed Lower-Bound Optimization (DLBO) to reduce each Ising call from dataset to single-sample scale. The DLBO moment hierarchy also forms a Hamiltonian-locality hierarchy, with order two giving an auxiliary-free pairwise QUBO oracle and higher orders trading interaction locality for tighter bounds. Strictly feasible discrete parameters are recovered via Spectral--ADMM and randomized rounding. Experiments on a coherent Ising machine achieve $94.95\%$ accuracy on binary Fashion-MNIST (coats vs. sandals) at 1.1-bit precision, demonstrating resilience against low-bit representational collapse. Multi-class DLBO evaluations on 3-class Fashion-MNIST, 3-class Wine, and 3-class Digits further validate scalable convergence.

cs.LG↗

arXiv2025

Soliton eigenvalue control by interaction of circularly polarized lights in a nonlinear fiber

We propose a physical method for controlling soliton eigenvalues in optical fibers, which is realized through the interaction between circularly polarized lights. Using this method, we not only achieve the decomposition of high-order solitons (HOSs) with different orders, but also realize physical processes of reconstructing HOSs for the first time. Compared with existing methods, our approach ensures accurate measurement of the discrete eigenvalues of HOSs while exhibiting higher decomposition efficiency. It is worth noting that the probe soliton, which induces these phenomena, plays a key role. The requirement for a moderate steepness of the probe suggests the presence of an uncertainty principle in the measurement of soliton eigenvalues, similar to the detection of microscopic particles. Our results can deepen the understanding of microscopic properties of solitons and their interaction mechanisms, and moreover provide a promising all-optical solution for the design of eigenvalue-based multiplexers and demultiplexers.

physics.optics↗

arXiv2025

QAMA: Scalable Quantum Annealing Multi-Head Attention Operator for Deep Learning

Attention mechanisms underpin modern deep learning, while the quadratic time and space complexity limit scalability for long sequences. To address this, Quantum Annealing Multi-Head Attention (QAMA) is proposed, a novel drop-in operator that reformulates attention as an energy-based Hamiltonian optimization problem. In this framework, token interactions are encoded into binary quadratic terms, and quantum annealing is employed to search for low-energy configurations that correspond to effective attention patterns. Unlike classical sparse or approximate attention methods that rely on hand-crafted heuristics, QAMA allows sparsity structures to emerge naturally from the optimization process. Theoretically, computational complexity is analysed through single-spin flip dynamics, providing time to solution runtime bounds that depend on the spectral properties of the annealing Hamiltonian. Empirically, evaluation on both natural language and vision benchmarks shows that, across tasks, accuracy deviates by at most 2.7 points from standard multi-head attention, while requiring only linear qubits in sequence length. Visualizations further reveal that the Hamiltonian penalty terms induce meaningful and interpretable sparsity across heads. Finally, deployment on a coherent Ising machine validates the feasibility of running QAMA on real quantum hardware, showing tangible inference-time reductions compared with classical implementations. These results highlight QAMA as a pioneering and scalable step toward integrating quantum optimization devices into deep neural architectures, providing a seamlessly integrable and hardware-compatible alternative to conventional attention mechanisms. This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible.

quant-ph↗

arXiv2025

Multi-Prompt Style Interpolation for Fine-Grained Artistic Control

Text-driven image style transfer has seen remarkable progress with methods leveraging cross-modal embeddings for fast, high-quality stylization. However, most existing pipelines assume a \emph{single} textual style prompt, limiting the range of artistic control and expressiveness. In this paper, we propose a novel \emph{multi-prompt style interpolation} framework that extends the recently introduced \textbf{StyleMamba} approach. Our method supports blending or interpolating among multiple textual prompts (eg, ``cubism,'' ``impressionism,'' and ``cartoon''), allowing the creation of nuanced or hybrid artistic styles within a \emph{single} image. We introduce a \textit{Multi-Prompt Embedding Mixer} combined with \textit{Adaptive Blending Weights} to enable fine-grained control over the spatial and semantic influence of each style. Further, we propose a \emph{Hierarchical Masked Directional Loss} to refine region-specific style consistency. Experiments and user studies confirm our approach outperforms single-prompt baselines and naive linear combinations of styles, achieving superior style fidelity, text-image alignment, and artistic flexibility, all while maintaining the computational efficiency offered by the state-space formulation.

cs.GR↗

arXiv2025

HiQ-Lip: A Hierarchical Quantum-Classical Method for Global Lipschitz Constant Estimation of ReLU Networks

Estimating the global Lipschitz constant of neural networks is crucial for understanding and improving their robustness and generalization capabilities. However, precise calculations are NP-hard, and current semidefinite programming (SDP) methods face challenges such as high memory usage and slow processing speeds. In this paper, we propose HiQ-Lip, a hybrid quantum-classical hierarchical method that leverages quantum computing to estimate the global Lipschitz constant. We tackle the estimation by converting it into a Quadratic Unconstrained Binary Optimization problem and implement a multilevel graph coarsening and refinement strategy to adapt to the constraints of contemporary quantum hardware. Our experimental evaluations on fully connected neural networks demonstrate that HiQ-Lip not only provides estimates comparable to state-of-the-art methods but also significantly accelerates the computation process. In specific tests involving two-layer neural networks with 256 hidden neurons, HiQ-Lip doubles the solving speed and offers more accurate upper bounds than the existing best method, LiPopt. These findings highlight the promising utility of small-scale quantum devices in advancing the estimation of neural network robustness.

cs.LG↗

arXiv2024

Apparatus for producing single strontium atoms in an optical tweezer array

We outline an experimental setup for efficiently preparing a tweezer array of $^{88}$Sr atoms. Our setup uses permanent magnets to maintain a steady-state two-dimensional magneto-optical trap (MOT) which results in a loading rate of up to $10^{8}$ s$^{-1}$ at 5 mK for the three-dimensional blue MOT. This enables us to trap $2\times10^{6}$ $^{88}$Sr atoms at 2 $μ$K in a narrow-line red MOT with the $^{1}$S$_{0}$ $\rightarrow$ $^{3}$P$_{1}$ intercombination transition at 689 nm. With the Sisyphus cooling and pairwise loss processes, single atoms are trapped and imaged in 813 nm optical tweezers, exhibiting a lifetime of 2.5 minutes. We further investigate the survival fraction of a single atom in the tweezers and characterize the optical tweezer array using a release and recapture technique. Our platform paves the way for potential applications in atomic clocks, precision measurements, and quantum simulations.

physics.app-ph↗

arXiv2024

Creation of a tweezer array for cold atoms utilizing a generative neural network

Optical tweezers have become essential tools for dynamically manipulating objects, ranging from microspheres or biological molecules to neutral atoms. In this study, we demonstrate the creation of tweezer arrays using a generative neural network, which allows for the trapping of neutral atoms with tunable atom arrays. We have successfully loaded cold strontium atoms into various optical tweezer patterns generated by a spatial light modulator (SLM) integrated with generative models. Our approach shortens the process time to control the SLM wtih minimal time delay, eliminating the need for repeated re-optimization of the hologram for the SLM.

physics.optics↗

arXiv2024

Multi-reservoir enhanced loading of tweezer atom arrays

We introduce a species-independent method for improved loading into a single-atom optical tweezer array, utilizing iterative loading with multiple reservoir tweezers. Demonstrated with dual wavelength tweezer arrays of $^{88}$Sr atoms, our approach achieves a 96$\%$ loading rate after four reload cycles. This method can significantly enhance existing tweezer rearrangement protocols, potentially reducing iteration time and optical power consumption, thereby enabling a larger number of atoms in a quantum logic device.

physics.atom-ph↗