AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

Quantum latent distributions in deep generative models

Omar Bacarreza, Thorin Farnsworth, Alexander Makarovskiy, Hugo Wallner, Tessa Hicks, Santiago Sempere-Llagostera, John J Price, Robert J. A. Francis-Jones, William R. Clements

ICML 2026 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Score-based generative modeling analysis

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use quantum instead of distinguishable-photon latent (ablation)GAN · Quantum dataset (synthetic)L1 distance: 0.041 -> 0.036Improved
use quantum instead of Gaussian latentGAN · Quantum dataset (synthetic)L1 distance: 0.061 -> 0.036Improved
use quantum latent instead of GaussianGAN · Bernoulli dataset (synthetic)L1 distance: 0.012 -> 0.015No clear effect
use quantum instead of distinguishable-photon latent (ablation)MolGAN-based GAN · QM9 d_z=16FCD: 1.333 -> 1.160Improved
use quantum instead of Gaussian latentMolGAN-based GAN · QM9 d_z=16# valid and unique: 1814 -> 2522Improved
use quantum instead of distinguishable-photon latent (ablation)MolGAN-based GAN · QM9 d_z=32FCD: 1.533 -> 1.536No clear effect
use quantum instead of distinguishable-photon latent (ablation)MolGAN-based GAN · QM9 d_z=48# valid and unique: 1307 -> 1528Improved
use quantum instead of Bernoulli latentMolGAN-based GAN · QM9 d_z=48FCD: 1.671 -> 1.696No clear effect
increase latent size from 16 to 48 with quantum latentMolGAN-based GAN · QM9FCD: 1.160 -> 1.696Hurt
use quantum 1-1 circuit instead of distinguishable photons (ablation)MolGAN-based GAN · QM9 d_z=16 (1-1)FCD: 1.291 -> 1.245Improved
use quantum instead of distinguishable photons in 1-3-9 circuit (ablation)MolGAN-based GAN · QM9 d_z=16FCD: 1.376 -> 1.187Improved
use real quantum processor instead of simulationMolGAN-based GAN · QM9 d_z=32FCD: 1.414 -> 1.410No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy