Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
A Later Test Set Is Not a New Domain: Pretraining Familiarity Survives a Contamination-Free Hold-Out
Mahdi Naser Moghadasi, Faezeh Ghaderi
Time-series foundation models are evaluated almost exclusively on public archives that predate them, so a strong score cannot be separated from having seen the test set during pret…
cs.LG2026
Transformer Scalability Crisis: The First Comprehensive Empirical Analysis of Performance Walls in Modern Language Models
Mahdi Naser Moghadasi, Faezeh Ghaderi
Despite the remarkable success of transformer architectures in natural language processing, their scalability limitations remain poorly understood through systematic empirical anal…