AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Learning Discrete Diffusion on Graphs via Free-Energy Gradient Flows

Dario Rancati, Jan Maas, Francesco Locatello

ICML 2026 · Image generation › Fast diffusion sampling · approach: Diffusion theory and learned samplers

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 learned free-energy gradient flow (W_K JKO) instead of pretrained OpenFIMdiscrete diffusion forecasting · Synthetic graphs, beta=0.01Hellinger distance: 0.142 -> 0.066Improved
use learned free-energy gradient flow instead of OpenFIMdiscrete diffusion forecasting · Synthetic graphs, beta=0.10Hellinger distance: 0.150 -> 0.059Improved
use learned free-energy gradient flow instead of OpenFIMdiscrete diffusion forecasting · Synthetic graphs, beta=0.20Hellinger distance: 0.159 -> 0.069Improved
increase graph size N from 10 to 50 (ablation)free-energy learner · Synthetic graphsHellinger distance: approximately linear growth in N over N in {10, 20, 30, 40, 50}Hurt
reduce number of samples to 500 (from 10000) (ablation)free-energy learner · Synthetic graphs, N=10Hellinger distance: slight degradation at 500 samplesHurt
vary samples among 1000, 2000, 5000, 10000 (ablation)free-energy learner · Synthetic graphs, N=10Hellinger distanceNo 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