Dario Rancati — accepted AI-conference papers

2026

Learning Discrete Diffusion on Graphs via Free-Energy Gradient Flows

Dario Rancati, Jan Maas, Francesco Locatello

ICML 2026poster

Diffusion-based models on continuous spaces have seen substantial recent progress through the mathematical framework of gradient flows, leveraging the Wasserstein-2 (${W}_2$) metric via the Jordan-Kinderlehrer-Otto (JKO) scheme. Despite the increasing popularity of diffusion models on discrete space…

Cited by 0 Source ↗Scholar ↗

2025

Unifying Causal Representation Learning with the Invariance Principle

Dingling Yao, Dario Rancati, Riccardo Cadei, Marco Fumero, Francesco Locatello

ICLR 2025poster

Causal representation learning (CRL) aims at recovering latent causal variables from high-dimensional observations to solve causal downstream tasks, such as predicting the effect of new interventions or more robust classification. A plethora of methods have been developed, each tackling carefully…

Cited by 5 Source ↗PDF ↗Scholar ↗