7 papers
Fast Inference on Astronomical Time Series with Trans-Dimensional Flow Matching Posterior Estimation
Nina van der Meulen, Tin Hadži VeljkoviÄ, Daniela Huppenkothen +2
The analysis of time series plays an important part in the study of (fast) transient events, including gamma-ray bursts, magnetar bursts, fast radio bursts, and solar flares. A com…
Emulation of non-linear 1D spectral models: relativistic X-ray reflection
Benjamin J. Ricketts, Tin Hadži VeljkoviÄ, Daniela Huppenkothen +4
The use of machine learning techniques to approximate computationally expensive models has become increasingly prevalent in a wide variety of fields within astronomy. We discuss th…
Crystalite: A Lightweight Transformer for Efficient Crystal Modeling
Tin Hadži VeljkoviÄ, Joshua Rosenthal, Ivor LonÄariÄ +1
Generative models for crystalline materials often rely on equivariant graph neural networks, which capture geometric structure well but are costly to train and slow to sample. We p…
CORDS: Continuous Representations of Discrete Structures
Tin Hadži VeljkoviÄ, Erik Bekkers, Michael Tiemann +1
Many learning problems require predicting sets of objects when the number of objects is not known beforehand. Examples include object detection, molecular modeling, and scientific…
Dynamic Training Enhances Machine Learning Potentials for Long-Lasting Molecular Dynamics
Ivan Žugec, Tin Hadži VeljkoviÄ, Maite Alducin +1
Molecular Dynamics (MD) simulations are vital for exploring complex systems in computational physics and chemistry. While machine learning methods dramatically reduce computational…
DuoDiff: Accelerating Diffusion Models with a Dual-Backbone Approach
Daniel Gallo Fernández, RÄzvan-Andrei MatiÅan, Alejandro Monroy Muñoz +4
Diffusion models have achieved unprecedented performance in image generation, yet they suffer from slow inference due to their iterative sampling process. To address this, early-ex…