1 citations · 1 across the 5 of their papers we have counts for
5 papers
The Curved Spacetime of Transformer Architectures
Riccardo Di Sipio, Jairo Diaz-Rodriguez, Luis Serrano
We present a geometric framework for understanding Transformer-based language models, drawing an explicit analogy to General Relativity. Queries and keys induce an effective metric…
Rethinking LLM Training through Information Geometry and Quantum Metrics
Riccardo Di Sipio
Optimization in large language models (LLMs) unfolds over high-dimensional parameter spaces with non-Euclidean structure. Information geometry frames this landscape using the Fishe…
Bidirectional Long Short-Term Memory (BLSTM) neural networks for reconstruction of top-quark pair decay kinematics
Fardin Syed, Riccardo Di Sipio, Pekka Sinervo
A probabilistic reconstruction using machine-learning of the decay kinematics of top-quark pairs produced in high-energy proton-proton collisions is presented. A deep neural networ…
Eikos: a Bayesian unfolding method for differential cross-section measurements
Riccardo Di Sipio
A likelihood-based unfolding method based on Bayes' theorem is presented, with a particular emphasis on the application to differential cross-section measurements in high-energy pa…
GPGPU for track finding in High Energy Physics
Lorenzo Rinaldi, Mauro Belgiovine, Riccardo Di Sipio +6
The LHC experiments are designed to detect large amount of physics events produced with a very high rate. Considering the future upgrades, the data acquisition rate will become eve…