Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP)

QGFORMER: Quantum-Classical Hybrid Transformer Architecture for Gravitational Wave Detection

Hu Jiaxiang, Liu Jiale

Published Dec 15, 2023• 6 citations
Publisher

Abstract

Gravitational Wave (GW) detection is a pivotal field in astrophysics, gaining prominence for its role in deciphering cosmic phenomena. Traditional machine learning algorithms in GW detection, while effective, grapple with challenges in parallelism, scalability, efficiency in handling high-dimensional data and noise interference. To mitigate these limitations, this paper proposes the Quantum-Gravitational Transformer (QGFormer), a novel quantum-classical hybrid transformer for gravitational wave detection. The QGFormer consists of a vision transformer encoder and a quantum classifier following the autoencoder architecture, which first segments the original input signal into small patches and maps them to higher dimensions, and then inputs the higher-dimensional feature map into the quantum classifier for prediction. The excellent parallelism inherent in the multi-head self-attention mechanism and quantum computing makes QGFormer expected to achieve high computational efficiency and scalability on quantum computing devices. Additionally, the super-density coding and quantum state compression techniques that could be used in these devices help mitigate the effects of noise. In experiments on the Gravitational Spy dataset, which utilizes data collected by the LIGO telescope, our results show that QGFormer outperforms the comparison models in accuracy and F1-score, demonstrating the promising future of quantum machine learning approaches in this field.

DOI
10.1109/iccwamtip60502.2023.10387052

Related papers

Quantum-Enhanced Vision Transformer for Flood Detection Using Remote Sensing Imagery

Soumyajit Maity, Behzad Ghanbarian

Reliable flood detection is critical for disaster management, yet classical deep learning models often struggle with the high-dimensional, nonlinear complexities inherent in remote sensing data. To mitigate these limitations, we introduced a novel Quantum-Enhanced Vision Transformer (ViT) that synergizes the global context-awareness of transformers with the expressive feature extraction capabilities of quantum computing. Using remote sensing imagery, we developed a hybrid architecture that processes inputs through parallel pathways, a ViT backbone and a quantum branch utilizing a 4-qubit parameterized quantum circuit for localized feature mapping. These distinct representations were fused to optimize binary classification. Results showed that the proposed hybrid model significantly outperformed a classical ViT baseline, increased overall accuracy from 84.48 % to 94.47 % and the F1-score from 0.841 to 0.944. Notably, the quantum integration substantially improved discriminative power in complex terrains for both class. These findings validate the potential of quantum-classical hybrid models to enhance precision in hydrological monitoring and earth observation applications.

arXiv:2603.13689•IEEE Dallas Circuits and Systems Conference (DCAS)•Apr 10, 2026•1 citation

Benchmarking Quantum Neural Networks Developed for MBHB Coalescence in the Context of LISA Space Mission

Maria Catalina Isfan, Laurentiu-Ioan Caramete, A. Caramete

Machine learning (ML) techniques are increasingly explored to analyse gravitational wave (GW) data expected from the Laser Interferometer Space Antenna (LISA). At the same time, advances in quantum computing have stimulated interest in quantum machine learning as a potential alternative to conventional approaches. We investigate the applicability of quantum, hybrid quantum-classical, and classical ML models to two tasks relevant for LISA observations of massive black hole binaries: GW signal detection and merger prediction. Using the Sangria dataset from the LISA Data Challenge, we benchmark several quantum architectures, including variational quantum classifiers (VQCs), post VQC hybrid models, quantum kernel methods, data reuploading classifiers, and quantum long short-term memory (QLSTM) networks, against classical support vector machines, multilayer perceptrons, recurrent neural networks, and LSTM networks. The models are trained on labelled data derived from the Sangria training dataset and evaluated on the corresponding blind dataset. For signal detection, several quantum models match or outperform classical baselines. In particular, the best performing hybrid post VQC architecture correctly identifies all signal samples in the blind dataset, while the standard VQC and data reuploading classifier achieve competitive detection rates. For merger detection and coalescence time estimation, however, the standard VQC emerges as the most reliable model, successfully localising all detected merger events with the lowest localisation errors. We further analyse the trade-offs between predictive performance, model complexity, and quantum circuit resources. Our results indicate that, although no universal quantum advantage is observed, selected quantum models can provide practical benefits for specific GW analysis tasks and represent promising candidates for future LISA data analysis pipelines.

arXiv:2610.39980•Oct 29, 2026•0 citations

Quantum variational rewinding for gravitational wave detection

Benjamin Rodrigues de Miranda, Domenica Dibenedetto, Niels M. P. Neumann +1 more

Abstract Gravitational waves carry information about far away phenomena which astronomers can use to form a better picture of the universe. Over the past few years, numerous gravitational waves have been detected using a method called matched filtering; however, this approach has two main drawbacks. First, it requires knowledge of the sought-after waveform beforehand. Second, it is infeasible for gravitational wave searches which are precise or cover a long time span. While attempts have been made to use classical machine learning to overcome these difficulties, the usage of quantum machine learning in this context is relatively unexplored. Quantum variational rewinding is a hybrid quantum-classical machine learning algorithm for time series anomaly detection. This work makes the first steps in investigating its potential for gravitational wave detection. Training and testing the algorithm was done without depending on synthetic data. In a noiseless simulated environment, quantum variational rewinding was able to pick out all confirmed gravitational wave signals from the background noise of a detector with perfect accuracy when filtering was applied before hand and was able to do so to a high degree of success without filtering. Anomaly detection with this algorithm was performed with two signals on quantum hardware as a proof of concept. Using Fisher information, both the capacity and the trainability of quantum variational rewinding are described so that future approaches can be compared in these regards. With new gravitational wave detectors under development, even more data will be generated for analysis in the future, compounding the existing bottlenecks in the search pipeline. As such, approaches which help tackle issues with the current approach to gravitational wave analysis are in demand, and the empirical results from this work assert that quantum computing should not be overlooked in this process.

Quantum Machine Intelligence•Feb 8, 2025•4 citations

Detection of Parkinson’s Disease using Quantum Transformers

Arepalli Peda Gopi, Meghana Reddy Boddapati, Geetha Chiranji +3 more

Parkinson disease (PD) is a neurological progressive disease that mainly impacts on speech, motor coordination and mobility, which causes a major reduction in the quality of life of patients. Timely and proper diagnosis is paramount to effective treatment, managing the symptoms, and monitoring the disease. As more biomedical data including voice signals and EEG recordings have become accessible, machine learning (ML) and artificial intelligence (AI) methods have been popular in automated PD detection. Traditional methods have shown good results through the use of Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), BiLSTM, Random Forest, and the Quantum Generative Adversarial Networks (QGAN). Nevertheless, these models are usually said to be limited by being computationally expensive, relying on large labeled datasets, the inability to deal with high-dimensional sequential data, limited ability to learn long-range temporal interactions, and the vanishing gradient problem. In order to cope with these issues, this paper presents a new Quantum Transformer-based system of Parkinson’s disease detection. The suggested model encodes voice features into quantum states and uses quantum self-attention mechanisms to effectively express the long-range dependencies and subtle interactions of feature. The hybrid quantum-classical learning architecture is applied to merge the benefits of quantum computation and the benefits of efficient classical optimization methods. According to experimental findings, the proposed Quantum Transformer is always more accurate, precise, and has a higher recall and $\mathrm{F1}$-score than the existing models. Also, the model has lower value of losses, consistent convergence, and it has minimized overfitting. These results demonstrate that quantum-enhanced transformer-based architectures can be a reliable scalable solution to the clinical decision-support systems of the future that can be used to detect Parkinson’s disease early and accurately.

International Conference on Next Generation Electronics (NELEX)•May 8, 2026•0 citations

MedQViT: A Lightweight Hybrid Quantum Vision Transformer for Medical Image Analysis

Amandeep Singh Bhatia, Mandeep Kaur Saggi

Classical Vision Transformers (CViTs) have demonstrated strong performance in medical image analysis, supporting a wide range of digital health applications. However, their self-attention mechanisms can require substantial computational resources and model parameters. In parallel, quantum machine learning (QML) has attracted increasing interest in healthcare and other scientific domains, particularly because quantum-enhanced models may provide expressive representations for small datasets. In this paper, we propose MedQViT, a robust and parameter-efficient Quantum Vision Transformer for medical image classification. To reduce the computational cost of global self-attention, MedQViT combines a shared four-qubit parameterized quantum circuit with a quantum-feature state memory and trainable landmark tokens. This hybrid architecture encodes image patches into compact quantum-enhanced representations while using classical layers for feature aggregation and classification. Experiments on established medical image datasets evaluate the effectiveness and feasibility of MedQViT against classical and quantum baselines. MedQViT achieves competitive performance with substantially fewer parameters than conventional vision models and outperforms several classical and quantum methods in terms of test accuracy (ACC) and area under the receiver operating characteristic curve (AUC).

Proceedings of the AAAI Symposium Series•Nov 6, 2026•0 citations

Quantum computing in image recognition: A comparative analysis with classical models

Aakanshi Gupta, Yash Sing, Harshit Agrawal +4 more

This research explores quantum machine learning for image classification, comparing classical and quantum models. A classical convolutional neural network (CNN), based on the LeNet architecture, achieved 99.12% accuracy on MNIST, outperforming a quantum CNN, which attained 93.30%. Quantum encoders applied to Fashion-MNIST reached 85.60%, while quantum support vector machine (SVM), implemented for binary classification, obtained 71.34%. The study integrates hybrid quantum-classical models, leveraging quantum circuits for feature extraction. A quantum autoencoder-based classifier was introduced, demonstrating efficient data compression and classification without additional qubits. Feature encoding using RX gates mapped classical data into quantum states, and the impact of parameterized quantum circuit structures on classification accuracy was analyzed. Results indicate that specific ansatz structures yield superior accuracy, highlighting the significance of quantum circuit design. While classical models currently outperform quantum counterparts, quantum approaches reduce trainable parameters and computational complexity. Limitations in current quantum hardware, including noise and scalability, restrict performance. However, advancements in error mitigation, quantum gate efficiency, and scalable quantum architecture could bridge the gap with classical methods. These quantum techniques hold potential in aerospace applications, such as satellite image classification, anomaly detection in remote sensing, and real-time processing of high-dimensional image data. This study underscores the growing role of quantum circuits in machine learning, particularly in feature extraction and classification, suggesting that future quantum hardware could unlock new capabilities in end-to-end learning beyond hybrid approaches.

CRC Press eBooks•Mar 19, 2026•0 citations
Gravitational Wave (GW) detection is a pivotal field in astrophysics, gaining prominence for its role in deciphering cosmic phenomena. Traditional machine learning algorithms in GW detection, while effective, grapple with challenges in parallelism, scalability, efficiency in handling high-dimensional data and noise interference. To mitigate these limitations, this paper proposes the Quantum-Gravitational Transformer (QGFormer), a novel quantum-classical hybrid transformer for gravitational wave detection. The QGFormer consists of a vision transformer encoder and a quantum classifier following the autoencoder architecture, which first segments the original input signal into small patches and maps them to higher dimensions, and then inputs the higher-dimensional feature map into the quantum classifier for prediction. The excellent parallelism inherent in the multi-head self-attention mechanism and quantum computing makes QGFormer expected to achieve high computational efficiency and scalability on quantum computing devices. Additionally, the super-density coding and quantum state compression techniques that could be used in these devices help mitigate the effects of noise. In experiments on the Gravitational Spy dataset, which utilizes data collected by the LIGO telescope, our results show that QGFormer outperforms the comparison models in accuracy and F1-score, demonstrating the promising future of quantum machine learning approaches in this field.
Reliable flood detection is critical for disaster management, yet classical deep learning models often struggle with the high-dimensional, nonlinear complexities inherent in remote sensing data. To mitigate these limitations, we introduced a novel Quantum-Enhanced Vision Transformer (ViT) that synergizes the global context-awareness of transformers with the expressive feature extraction capabilities of quantum computing. Using remote sensing imagery, we developed a hybrid architecture that processes inputs through parallel pathways, a ViT backbone and a quantum branch utilizing a 4-qubit parameterized quantum circuit for localized feature mapping. These distinct representations were fused to optimize binary classification. Results showed that the proposed hybrid model significantly outperformed a classical ViT baseline, increased overall accuracy from 84.48 % to 94.47 % and the F1-score from 0.841 to 0.944. Notably, the quantum integration substantially improved discriminative power in complex terrains for both class. These findings validate the potential of quantum-classical hybrid models to enhance precision in hydrological monitoring and earth observation applications.
Machine learning (ML) techniques are increasingly explored to analyse gravitational wave (GW) data expected from the Laser Interferometer Space Antenna (LISA). At the same time, advances in quantum computing have stimulated interest in quantum machine learning as a potential alternative to conventional approaches. We investigate the applicability of quantum, hybrid quantum-classical, and classical ML models to two tasks relevant for LISA observations of massive black hole binaries: GW signal detection and merger prediction. Using the Sangria dataset from the LISA Data Challenge, we benchmark several quantum architectures, including variational quantum classifiers (VQCs), post VQC hybrid models, quantum kernel methods, data reuploading classifiers, and quantum long short-term memory (QLSTM) networks, against classical support vector machines, multilayer perceptrons, recurrent neural networks, and LSTM networks. The models are trained on labelled data derived from the Sangria training dataset and evaluated on the corresponding blind dataset. For signal detection, several quantum models match or outperform classical baselines. In particular, the best performing hybrid post VQC architecture correctly identifies all signal samples in the blind dataset, while the standard VQC and data reuploading classifier achieve competitive detection rates. For merger detection and coalescence time estimation, however, the standard VQC emerges as the most reliable model, successfully localising all detected merger events with the lowest localisation errors. We further analyse the trade-offs between predictive performance, model complexity, and quantum circuit resources. Our results indicate that, although no universal quantum advantage is observed, selected quantum models can provide practical benefits for specific GW analysis tasks and represent promising candidates for future LISA data analysis pipelines.
Abstract Gravitational waves carry information about far away phenomena which astronomers can use to form a better picture of the universe. Over the past few years, numerous gravitational waves have been detected using a method called matched filtering; however, this approach has two main drawbacks. First, it requires knowledge of the sought-after waveform beforehand. Second, it is infeasible for gravitational wave searches which are precise or cover a long time span. While attempts have been made to use classical machine learning to overcome these difficulties, the usage of quantum machine learning in this context is relatively unexplored. Quantum variational rewinding is a hybrid quantum-classical machine learning algorithm for time series anomaly detection. This work makes the first steps in investigating its potential for gravitational wave detection. Training and testing the algorithm was done without depending on synthetic data. In a noiseless simulated environment, quantum variational rewinding was able to pick out all confirmed gravitational wave signals from the background noise of a detector with perfect accuracy when filtering was applied before hand and was able to do so to a high degree of success without filtering. Anomaly detection with this algorithm was performed with two signals on quantum hardware as a proof of concept. Using Fisher information, both the capacity and the trainability of quantum variational rewinding are described so that future approaches can be compared in these regards. With new gravitational wave detectors under development, even more data will be generated for analysis in the future, compounding the existing bottlenecks in the search pipeline. As such, approaches which help tackle issues with the current approach to gravitational wave analysis are in demand, and the empirical results from this work assert that quantum computing should not be overlooked in this process.
Parkinson disease (PD) is a neurological progressive disease that mainly impacts on speech, motor coordination and mobility, which causes a major reduction in the quality of life of patients. Timely and proper diagnosis is paramount to effective treatment, managing the symptoms, and monitoring the disease. As more biomedical data including voice signals and EEG recordings have become accessible, machine learning (ML) and artificial intelligence (AI) methods have been popular in automated PD detection. Traditional methods have shown good results through the use of Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), BiLSTM, Random Forest, and the Quantum Generative Adversarial Networks (QGAN). Nevertheless, these models are usually said to be limited by being computationally expensive, relying on large labeled datasets, the inability to deal with high-dimensional sequential data, limited ability to learn long-range temporal interactions, and the vanishing gradient problem. In order to cope with these issues, this paper presents a new Quantum Transformer-based system of Parkinson’s disease detection. The suggested model encodes voice features into quantum states and uses quantum self-attention mechanisms to effectively express the long-range dependencies and subtle interactions of feature. The hybrid quantum-classical learning architecture is applied to merge the benefits of quantum computation and the benefits of efficient classical optimization methods. According to experimental findings, the proposed Quantum Transformer is always more accurate, precise, and has a higher recall and F1\mathrm{F1}F1-score than the existing models. Also, the model has lower value of losses, consistent convergence, and it has minimized overfitting. These results demonstrate that quantum-enhanced transformer-based architectures can be a reliable scalable solution to the clinical decision-support systems of the future that can be used to detect Parkinson’s disease early and accurately.
Classical Vision Transformers (CViTs) have demonstrated strong performance in medical image analysis, supporting a wide range of digital health applications. However, their self-attention mechanisms can require substantial computational resources and model parameters. In parallel, quantum machine learning (QML) has attracted increasing interest in healthcare and other scientific domains, particularly because quantum-enhanced models may provide expressive representations for small datasets. In this paper, we propose MedQViT, a robust and parameter-efficient Quantum Vision Transformer for medical image classification. To reduce the computational cost of global self-attention, MedQViT combines a shared four-qubit parameterized quantum circuit with a quantum-feature state memory and trainable landmark tokens. This hybrid architecture encodes image patches into compact quantum-enhanced representations while using classical layers for feature aggregation and classification. Experiments on established medical image datasets evaluate the effectiveness and feasibility of MedQViT against classical and quantum baselines. MedQViT achieves competitive performance with substantially fewer parameters than conventional vision models and outperforms several classical and quantum methods in terms of test accuracy (ACC) and area under the receiver operating characteristic curve (AUC).
This research explores quantum machine learning for image classification, comparing classical and quantum models. A classical convolutional neural network (CNN), based on the LeNet architecture, achieved 99.12% accuracy on MNIST, outperforming a quantum CNN, which attained 93.30%. Quantum encoders applied to Fashion-MNIST reached 85.60%, while quantum support vector machine (SVM), implemented for binary classification, obtained 71.34%. The study integrates hybrid quantum-classical models, leveraging quantum circuits for feature extraction. A quantum autoencoder-based classifier was introduced, demonstrating efficient data compression and classification without additional qubits. Feature encoding using RX gates mapped classical data into quantum states, and the impact of parameterized quantum circuit structures on classification accuracy was analyzed. Results indicate that specific ansatz structures yield superior accuracy, highlighting the significance of quantum circuit design. While classical models currently outperform quantum counterparts, quantum approaches reduce trainable parameters and computational complexity. Limitations in current quantum hardware, including noise and scalability, restrict performance. However, advancements in error mitigation, quantum gate efficiency, and scalable quantum architecture could bridge the gap with classical methods. These quantum techniques hold potential in aerospace applications, such as satellite image classification, anomaly detection in remote sensing, and real-time processing of high-dimensional image data. This study underscores the growing role of quantum circuits in machine learning, particularly in feature extraction and classification, suggesting that future quantum hardware could unlock new capabilities in end-to-end learning beyond hybrid approaches.