Samy-Melwan Vilhes
Ph.D student @ LITIS Lab, INSA Rouen
anomaly detection · time series forecasting · foundation models · zero-shot forecasting
About
I am currently pursuing a Ph.D at the LITIS Lab, INSA Rouen, with a research focus on time series anomaly detection, forecasting, and the development of foundation models for zero-shot forecasting.
I have a strong background in Mathematics, with a Bachelor's degree in Mathematics from Paris-Saclay University and a Master's degree in Mathematics and Artificial Intelligence from the same institution.
News
-
Does Normalization Choice Matter for Causal Large Time-Series Models? accepted at the ICLR 2026 Workshop “Time Series in the Age of Large Models” — selected as a spotlight paper.
-
Completed the Deep Learning Optimisé sur Jean Zay program — multi-GPU / multi-node training, from DDP to 4-D parallelism, mixed precision, large-batch strategies and performance profiling on HPC.
-
Poster session at the Hi! Paris Summer School 2025 presenting PatchTrAD (poster).
Research & Writing
Sports
The main sport I pursued as a teenager was cycling, competing in numerous national races. I won several departmental and regional races, including being crowned Department Champion once and Regional Team Champion once.
After stepping away from cycling, I transitioned to streetlifting — a strength sport focused on muscle-ups, pull-ups, dips, and squats. I have competed twice in the French Dips Championship and was crowned First Step French Champion of Streetlifting in 2024 in the −80 kg category. I have also worked as a trainer, helping athletes reach higher levels through tailored programs and weekly progress tracking.
Contact
- Emailsamy-melwan.vilhes@insa-rouen.fr
- GitHub
@vilhess - LinkedInSamy-Melwan Vilhes
- ScholarGoogle Scholar