Quantum Machine Intelligence· 2026Q1
Physics-inspired Generative AI models via real hardware-based noisy quantum diffusion
- 3citations
- Q1SCImago
- 2026year
Short summary
A new physics-inspired quantum diffusion model (QDM) using quantum stochastic walks achieved lower Fréchet Inception Distance (FID) on MNIST image generation compared to classical dynamics, and another QDM exploited IBM quantum hardware noise to generate images with only four qubits.
AI-generated from the title and abstract; the full text is not read.
Key points
- A quantum diffusion model using quantum stochastic walks achieved lower FID scores on MNIST image generation than classical dynamics.
- A second QDM exploited the intrinsic noise of real IBM quantum hardware with four qubits to generate images.
- The hybrid quantum-classical forward process in QDMs can produce more robust generative models.
- Quantum noise can be utilized as a resource in quantum Generative AI, rather than solely mitigated.
AI-generated from the title and abstract; the full text is not read.
Abstract
Abstract Quantum Diffusion Models (QDMs) are an emerging paradigm in Generative AI that aims to use quantum properties to improve the performances of their classical counterparts. However, existing algorithms are not easily scalable due to the limitations of near-term quantum devices. Following our previous work on QDMs, here we propose and implement two physics-inspired protocols. In the first, we use the formalism of quantum stochastic walks, showing that a specific interplay of quantum and classical dynamics in the forward process produces statistically more robust models generating sets of MNIST images with lower Fréchet Inception Distance (FID) than using totally classical dynamics. In the second approach, we realize an algorithm to generate images by exploiting the intrinsic noise of real IBM quantum hardware with only four qubits. Our work could be a starting point to pave the way for new scenarios for large-scale algorithms in quantum Generative AI, where quantum noise is neither mitigated nor corrected, but instead exploited as a useful resource.
The authors' abstract, as published at the source. Quantum Machine Intelligence, 2026 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Artificial Intelligence
Artificial IntelligenceComputer Science