2 papers
astro-ph.GA2025
Dark Matter profiles of "in silico" galaxies: deep learning inference
Martín de los Rios, Serafina Di Gioia, Fabio Iocco +1
Machine learning has the potential to improve the reconstruction of the dark matter profile of galaxies with respect to traditional methods, like rotation curves. We demonstrate on…
cs.LG2025
Rotary Masked Autoencoders are Versatile Learners
Uros Zivanovic, Serafina Di Gioia, Andre Scaffidi +3
Applying Transformers to irregular time-series typically requires specializations to their baseline architecture, which can result in additional computational overhead and increase…