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

Quantum Machine Intelligence

Quantum latent diffusion model for high-dimensional state generation

Guangxi Li, Mingrui Jing, Chenghong Zhu, Xin Wang

Published Feb 4, 2026• 0 citations
Publisher
DOI
10.1007/s42484-026-00352-1

Related papers

Quantum latent diffusion models

Francesca De Falco, Andrea Ceschini, Alessandro Sebastianelli +2 more

arXiv:2501.11174•Quantum Machine Intelligence•Nov 27, 2024•22 citations

An Hybrid Quantum-Classical Diffusion Model for Image Generation

Qipeng Qian, Keli Deng, Yuntao Qian

Quantum diffusion models provide a physics-consistent route to generative learning by formulating noising and denoising directly on quantum states. However, applying such models to classical high-dimensional data is constrained by the qubit cost of state encoding and the computational burden of simulating large density operators. We propose a scalable hybrid generative pipeline that combines a classical autoencoder for dimensionality reduction with a mixed-state quantum denoising diffusion probabilistic model (MSQuDDPM) operating in the learned latent space. The autoencoder compresses data into compact latent codes that can be embedded into a small-qubit Hilbert space, after which the quantum diffusion model learns a generative distribution over latent density operators and decodes samples back to the original domain. Algorithmically, we simplify the reverse dynamics by predicting an estimate of the clean state $ρ_0$ at timestep $t$ and computing the one-step reverse update via an analytic backward propagation rule, rather than learning an explicit predictor for $ρ_{t-1}$. We demonstrate the proposed approach on MNIST image generation and discuss how mixed-state quantum diffusion can serve as a practical backbone for hybrid quantum--classical generative modeling under realistic qubit budgets.

arXiv:2607.07072•Jul 8, 2026•0 citations

Quantum-state diffusion: Application to Bayesian hierarchical modeling

Zakarya Zarezadeh, Giovanni Costantini

Physica A Statistical Mechanics and its Applications•Aug 28, 2021•0 citations

Understanding of the Diffusion Noise in Quantum Latent Diffusion Model

Jeihee Cho, Junyong Lee, Shiho Kim

Generative models have gained attention for their proven effectiveness in various domains, from generating images to producing text. Diffusion models (DMs) have demonstrated superior performance compared to alternative techniques like generative adversarial networks (GANs) or autoencoders (AE). The research about DMs has advanced further with the proposition of latent diffusion models (LDMs), which employ DMs within the latent space to mitigate computational complexity while preserving high quality and flexibility. Quantum computing with its intrinsic characteristics of entanglement and superposition which enable high representational power, arises with the possibility of offering computational advantages over classical generative models. Inspired by current trends of classical generative models, we propose quantum latent diffusion models (QLDMs) to enable computationally efficient DMs with the guidance of conditions on classical data. QLDMs offer solutions to the challenges faced by classical generative models due to their large number of parameters, while still achieving comparable results on datasets.

IEEE International Conference on Quantum Computing and Engineering (QCE)•Sep 1, 2024•0 citations

Leveraging Quantum Latent Diffusion Models for Data Augmentation on The Eurosat Dataset

Francesca De Falco, Francesco Mauro, Andrea Ceschini +4 more

Generative models are transforming earth observation, enabling high-quality image generation for applications like data augmentation, cloud removal or image inpainting. This study investigates quantum latent diffusion models, integrating quantum variational circuits within latent diffusion processes. Using three ansatzes Rx-Rz-Rx, universal, and matchgate, we compare those models with classical latent diffusion models and generative adversarial networks. The quantum latent diffusion models with the universal ansatz achieved a 21.5% improvement in Fréchet inception distance and a 29.9% improvement in kernel inception distance compared to the best classical counterpart, while maintaining competitive diversity with an inception score of 1.3152. These results demonstrate the efficiency of quantum-enhanced generative models in the specific case of data augmentation for earth observation applications, expecting similar improvements also in other related earth observation tasks.

IEEE International Geoscience and Remote Sensing Symposium (IGARSS)•Aug 3, 2025•1 citation

Quantum Diffusion Monte Carlo Method

Shinil Cho

Synthesis lectures on mathematics and statistics•Jan 1, 2023•0 citations
Quantum diffusion models provide a physics-consistent route to generative learning by formulating noising and denoising directly on quantum states. However, applying such models to classical high-dimensional data is constrained by the qubit cost of state encoding and the computational burden of simulating large density operators. We propose a scalable hybrid generative pipeline that combines a classical autoencoder for dimensionality reduction with a mixed-state quantum denoising diffusion probabilistic model (MSQuDDPM) operating in the learned latent space. The autoencoder compresses data into compact latent codes that can be embedded into a small-qubit Hilbert space, after which the quantum diffusion model learns a generative distribution over latent density operators and decodes samples back to the original domain. Algorithmically, we simplify the reverse dynamics by predicting an estimate of the clean state ρ0ρ_0ρ0​ at timestep ttt and computing the one-step reverse update via an analytic backward propagation rule, rather than learning an explicit predictor for ρt−1ρ_{t-1}ρt−1​. We demonstrate the proposed approach on MNIST image generation and discuss how mixed-state quantum diffusion can serve as a practical backbone for hybrid quantum--classical generative modeling under realistic qubit budgets.
Generative models have gained attention for their proven effectiveness in various domains, from generating images to producing text. Diffusion models (DMs) have demonstrated superior performance compared to alternative techniques like generative adversarial networks (GANs) or autoencoders (AE). The research about DMs has advanced further with the proposition of latent diffusion models (LDMs), which employ DMs within the latent space to mitigate computational complexity while preserving high quality and flexibility. Quantum computing with its intrinsic characteristics of entanglement and superposition which enable high representational power, arises with the possibility of offering computational advantages over classical generative models. Inspired by current trends of classical generative models, we propose quantum latent diffusion models (QLDMs) to enable computationally efficient DMs with the guidance of conditions on classical data. QLDMs offer solutions to the challenges faced by classical generative models due to their large number of parameters, while still achieving comparable results on datasets.
Generative models are transforming earth observation, enabling high-quality image generation for applications like data augmentation, cloud removal or image inpainting. This study investigates quantum latent diffusion models, integrating quantum variational circuits within latent diffusion processes. Using three ansatzes Rx-Rz-Rx, universal, and matchgate, we compare those models with classical latent diffusion models and generative adversarial networks. The quantum latent diffusion models with the universal ansatz achieved a 21.5% improvement in Fréchet inception distance and a 29.9% improvement in kernel inception distance compared to the best classical counterpart, while maintaining competitive diversity with an inception score of 1.3152. These results demonstrate the efficiency of quantum-enhanced generative models in the specific case of data augmentation for earth observation applications, expecting similar improvements also in other related earth observation tasks.