2 papers
cs.LG2026
A Geometric Perspective on Next-Token Prediction in Large Language Models: Three Emerging Phases
Gianfranco Lombardo, Giuseppe Trimigno, Stefano Cagnoni
We investigate the geometry of predictive information across the layers of large language models (LLMs). We repurpose representation lenses-learned affine maps trained to predict t…
cs.LG2022
Anomaly detection in laser-guided vehicles' batteries: a case study
Gianfranco Lombardo, Stefano Cagnoni, Stefano Cavalli +4
Detecting anomalous data within time series is a very relevant task in pattern recognition and machine learning, with many possible applications that range from disease prevention…