Roberto Trotta — accepted AI-conference papers

2025

Human-LLM Coevolution: Evidence from Academic Writing

ACL 2025finding

With a statistical analysis of arXiv paper abstracts, we report a marked drop in the frequency of several words previously identified as overused by ChatGPT, such as “delve”, starting soon after they were pointed out in early 2024. The frequency of certain other words favored by ChatGPT, such as “si…

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Rotary Masked Autoencoders are Versatile Learners

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

NeurIPS 2025poster

Applying Transformers to irregular time-series typically requires specializations to their baseline architecture, which can result in additional computational overhead and increased method complexity. We present the Rotary Masked Autoencoder (RoMAE), which utilizes the popular Rotary Positional Embe…

Cited by 0 Source ↗Scholar ↗