Pith. sign in

REVIEW 4 cited by

Quantum Diffusion Models

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2311.15444 v1 pith:LXB3ZHPE submitted 2023-11-26 quant-ph

Andrea Cacioppo , Lorenzo Colantonio , Simone Bordoni , Stefano Giagu This is my paper · ORCID
classification quant-ph
keywords quantumversionalgorithmmodelsbeendiffusionartificialassessments
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We propose a quantum version of a generative diffusion model. In this algorithm, artificial neural networks are replaced with parameterized quantum circuits, in order to directly generate quantum states. We present both a full quantum and a latent quantum version of the algorithm; we also present a conditioned version of these models. The models' performances have been evaluated using quantitative metrics complemented by qualitative assessments. An implementation of a simplified version of the algorithm has been executed on real NISQ quantum hardware.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. SQGen: Structured Quantum Image Generation with Latent-Modulated Quantized Tensor Trains

    quant-ph 2026-07 unverdicted novelty 7.0 of 10

    SQGen maps a quantized tensor-train image model with latent-modulated re-uploading rotations onto a shallow native quantum circuit that generates images without a classical decoder.

  2. Quantum Reversibility Meets Classical Reverse Diffusion

    quant-ph 2025-10 conditional novelty 4.0 of 10

    The semiclassical limit of the Petz-reversed Lindblad equation reproduces the Bayes-rule reverse-time diffusion equation, with the reference state's Wigner function playing the role of the classical score distribution.

  3. Mixed-State Quantum Denoising Diffusion Probabilistic Model

    quant-ph 2024-11 conditional novelty 4.0 of 10

    MSQuDDPM generates quantum state ensembles by diffusing depolarizing noise and learning to denoise with parameterized circuits, reaching 4-qubit test cases without scrambling unitaries.

  4. Enhancing Quantum Diffusion Models with Pairwise Bell State Entanglement

    quant-ph 2024-11 reject novelty 4.0 of 10

    A pairwise Bell-state entanglement trick reduces the trainable parameter count in a quantum diffusion model, but the reported image quality scores are too low to support the claimed advances.

Pith tools