Gate-based quantum generative models have been limited to small images, because their quantum resources grow with the size of the data. The Quantum Feature Amplification Network (QFAN) removes this limit. It reuses a single few-qubit circuit to generate the data block by block, each block conditioned on a compact summary of those before it, with the circuit's measurement outcomes as the source of randomness. The number of qubits is set by the block rather than by the data, and the number of circuits per training step does not grow with the data either. In simulations with only four qubits, QFAN generates full-resolution calorimeter showers from the CaloChallenge Dataset~1 benchmark, 368 voxels each, and learns their correlations and shower-to-shower fluctuations. A three-qubit version generates 12- and 25-pixel images on IBM quantum hardware. This brings high-dimensional scientific data within reach of near-term quantum generative models.
Gate-based quantum generative models have been limited to small images, because their quantum resources grow with the size of the data. The Quantum Feature Amplification Network (QFAN) removes this limit. It reuses a single few-qubit circuit to generate the data block by block, each block conditioned on a compact summary of those before it, with the circuit's measurement outcomes as the source of randomness. The number of qubits is set by the block rather than by the data, and the number of circuits per training step does not grow with the data either. In simulations with only four qubits, QFAN generates full-resolution calorimeter showers from the CaloChallenge Dataset~1 benchmark, 368 voxels each, and learns their correlations and shower-to-shower fluctuations. A three-qubit version generates 12- and 25-pixel images on IBM quantum hardware. This brings high-dimensional scientific data within reach of near-term quantum generative models.
The practical use of quantum generative models has been limited to scalability issues and noise in the hardware used to implement the model in versions, however quantum generative models have demonstrated to be useful in learning accurate data distributions that are hard to predict, including complex aspects of semantic information, art, naturalistic data, speech, electrodynamic quantum systems, among others. The paper suggests a generative assessable and noisy hybrid quantum AI quantification and suggests mixing adaptive quantum circuit design, error- Delhi trained, and multi-computer running. The adaptive circuit design minimizes the two-qubit gate interactions that enhances robustness and is still expressive. The mistake-conscious training is dynamically optimized to adjust circuit parameters to noise calibration at a constant-time, thus allowing it to operate stably with gate error rates up to 0.12%. To manage scalability, generative computation is spread among a number of relatively small quantum processors by the framework, with an almost linear scaling efficiency. On IBM quantum hardware, the model is demonstrated and validated on three applications; synthetic data generation to boost machine learning, medical image synthesis, and molecular structure generation to discover drugs. Findings indicate that quantum resource consumption is cut down by about 35 percent without compromising the generative quality, which proves that quantum-assisted AI systems can be used in the near future.
Quantum generative modeling is a rapidly evolving discipline at the intersection of quantum computing and machine learning. Contemporary quantum machine learning is generally limited to toy examples or heavily restricted datasets with few elements. This is not only due to the current limitations of available quantum hardware but also due to the absence of inductive biases arising from application-agnostic designs. Current quantum solutions must resort to tricks to scale down high-resolution images, such as relying heavily on dimensionality reduction or utilizing multiple quantum models for low-resolution image patches. Building on recent developments in classical image loading to quantum computers, we circumvent these limitations and train quantum Wasserstein GANs on the established classical MNIST and Fashion-MNIST datasets. Using the complete datasets, our system generates full-resolution images across all ten classes and establishes a new state-of-the-art performance with a single end-to-end quantum generator without tricks. As a proof-of-principle, we also demonstrate that our approach can be extended to color images, exemplified on the Street View House Numbers dataset. We analyze how the choice of variational circuit architecture introduces inductive biases, which crucially unlock this performance. Furthermore, enhanced noise input techniques enable highly diverse image generation while maintaining quality. Finally, we show promising results even under quantum shot noise conditions.
The Quantum Angle Generator (QAG) is a new generative model for quantum computers. It consists of a parameterized quantum circuit trained with an objective function. The QAG model utilizes angle encoding for the conversion between the generated quantum data and classical data. Therefore, it requires one qubit per feature or pixel, while the output resolution is adjusted by the number of shots performing the image generation. This approach allows the generation of highly precise images on recent quantum computers. In this paper, the model is optimised for a High Energy Physics (HEP) use case generating simplified one-dimensional images measured by a specific particle detector, a calorimeter. With a reasonable number of shots, the QAG model achieves an elevated level of accuracy. The advantages of the QAG model are lined out - such as simple and stable training, a reasonable amount of qubits, circuit calls, circuit size and computation time compared to other quantum generative models, e.g. quantum GANs (qGANs) and Quantum Circuit Born Machines.
Simulating the showers that particles deposit in a calorimeter, the detector that records their energy across many cells, is one of the largest computing costs in high-energy physics, and fast generative surrogates are needed. Quantum circuits have been proposed as such surrogates, but demonstrations on calorimeter data have either required a register that grows with the image, roughly one qubit per cell, or have passed the information between parts of the image through a classical channel. We remove both constraints for this problem, using a construction drawn from the sequential-generation and hidden-quantum-Markov-model literature. A shower image is generated block by block on a fixed register of six qubits. Three of them, the memory, are never measured. They hold what the circuit knows about the blocks already generated as a quantum state, so the correlations between distant parts of the image cross each block boundary as unmeasured amplitudes. The other three are measured and reset once per block, and each outcome selects the energy pattern of one block. The register size is set by the block, so adding cells to the image adds steps to the sequence, not qubits. We call the model a coherent-memory Born machine (CoMB), a Born machine being a circuit whose measurement statistics are the generated distribution. Its training loss grows only linearly with the number of blocks and never requires enumerating the image distribution, and a depth-two instance runs on an IBM superconducting processor. On a twelve-cell benchmark the model reproduces the energy distribution of every cell, the correlation matrix between cells, and the total-energy spectrum. Removing the three memory qubits, with everything else unchanged, produces independent blocks. Every correlation between blocks is carried by the unmeasured qubits and by nothing else.
Quantum machine learning is a promising paradigm for learning from limited data, a central bottleneck in domains such as medical imaging, clinical trials, and rare diseases. Quantum convolutional neural networks (QCNNs) are particularly attractive in this setting, combining a hierarchical architecture with strong inductive bias and a parameter count that grows only logarithmically with system size. Their appeal rests on the generalization bounds of Caro et al. (2022), which show that the generalization error of a quantum model scales with the number of trainable parameters rather than with the Hilbert-space dimension, placing QCNNs in a potentially sample-efficient regime. We develop a hardware-compatible QCNN with mid-circuit measurement and classical feed-forward, and show on a binary handwritten-digit task that strong test performance is achievable from as few as 10 training samples, with the generalization error decreasing as the training set grows. At a matched 45-parameter budget the QCNN learns where an equally small classical convolutional network stays at chance, although an unconstrained classical baseline with roughly 25,000 parameters remains strongest when data are plentiful. Transpiling amplitude and angle encoded circuits across image resolutions from 2x2 to 512x512 pixels then exposes the dominant scaling bottleneck: amplitude encoding stays qubit-efficient but grows extremely deep, whereas angle encoding stays shallow but becomes qubit-prohibitive. On the medically motivated BreastMNIST benchmark the QCNN does not surpass the unconstrained classical network, yet it learns consistently above chance using orders of magnitude fewer parameters. Our results indicate that for QCNNs, learning from few samples is attainable in practice, whereas scaling to realistic image data is constrained less by optimization than by data encoding and hardware execution.
Quantum-based generative models offer a promising approach for simulating complex phenomena in high-energy physics, such as calorimeter showers used for particle identification and energy reconstruction at the LHC. We propose the Quantum Angle Generator (QAG), a variational quantum model trained with a Maximum Mean Discrepancy loss to generate images from the probabilistic outputs of quantum circuits. We study model and training hyperparameters, assess the impact of quantum noise during training and inference, and evaluate the QAG in both noiseless simulations and simulated Noisy Intermediate-Scale Quantum hardware. Results show that the QAG can adapt through learning to hardware-induced noise, yielding stable, high-quality outputs even under significant noise and calibration variability.