Roberto Trotta

Full Professor, SISSA/ISAS

1 paper at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 1

Wednesday, December 3, 2025 · 11:00 AM → 2:00 PM

Rotary Masked Autoencoders are Versatile Learners

#2300 · Uros Zivanovic, Serafina Di Gioia, Andre Scaffidi, Martín Emilio de los Rios, Gabriella Contardo, Roberto Trotta

RoMAE is a single, drop-in masked autoencoder that utilizes continuous (axial) RoPE to excel in interpolation and representation learning across modalities.