Bálint Máté — accepted AI-conference papers

2026

Enhancing Diffusion-Based Sampling with Molecular Collective Variables

Juno Nam, Bálint Máté, Artur P. Toshev, Manasa Kaniselvan, Rafael Gomez-Bombarelli, Ricky T. Q. Chen +3

ICLR 2026poster

Diffusion-based samplers learn to sample complex, high-dimensional distributions using energies or log densities alone, without training data. Yet, they remain impractical for molecular sampling because they are often slower than molecular dynamics and miss thermodynamically relevant modes. Inspired…

Cited by 0 Source ↗code ↗Scholar ↗

2023

SUPA: A Lightweight Diagnostic Simulator for Machine Learning in Particle Physics

Atul Kumar Sinha, Daniele Paliotta, Bálint Máté, John Andrew Raine, Tobias Golling, François Fleuret

NeurIPS 2023poster

Deep learning methods have gained popularity in high energy physics for fast modeling of particle showers in detectors. Detailed simulation frameworks such as the gold standard \textsc{Geant4} are computationally intensive, and current deep generative architectures work on discretized, lower resolut…

Cited by 3 Source ↗PDF ↗Scholar ↗

2022

Flowification: Everything is a normalizing flow

Bálint Máté, Samuel Klein, Tobias Golling, François Fleuret

NeurIPS 2022accept

The two key characteristics of a normalizing flow is that it is invertible (in particular, dimension preserving) and that it monitors the amount by which it changes the likelihood of data points as samples are propagated along the network. Recently, multiple generalizations of normalizing flows have…

Cited by 4 Source ↗PDF ↗code ↗Scholar ↗