Antonio Vitale

It's exciting that LLMs can describe code for us, but now the problem is knowing if that output is any good. This paper makes great observations, to which I would add that in my experience models get saturated after a million examples or so. @vitaleantonio7 , @AntonioMastro2 , @RoccoOliveto , @mdipenta , @SimonScalabrino arxiv.org/abs/2502.07611

Good news today: "Using Deep Learning to Automatically Improve Code Readability" by @vitaleantonio7 @SimonScalabrino @RoccoOliveto yt has been accepted at @ASE_conf! 😎