Our guest speaker is Giuseppe Bruno from the Institute of Mathematical Statistics and Actuarial Science (IMSV) at the University of Bern.

You are all cordially invited to the CVG Seminar on November 7th, 2025 at 2:45 pm CEST

• in person at the Institute of Computer Science: room 302, Neubrückstrasse 10, 3012 Bern
• via Zoom (passcode is 459500).

Abstract

While transformers have revolutionized machine learning, a fundamental understanding of how they construct internal representations remains a central challenge. This talk will present a recent theoretical framework that models the evolution of tokens as a mean-field interacting particle system, with network depth interpreted as time. The resulting mathematical description of the token distribution shows that, under certain regimes, tokens self-organize into clusters across multiple timescales, creating structure from initially random states. This mechanism offers a potential explanation for how meaning emerges in these models, while uncovering links to classical mathematical equations and other machine learning paradigms, and raising several open problems.

Bio

Giuseppe Bruno is a PhD student at the Institute of Mathematical Statistics and Actuarial Science (IMSV) at the University of Bern, working in the research group of Prof. Andrea Agazzi. His research explores the mathematical foundations of machine learning, with a specific focus on interacting particle systems and the theory of transformer models. He holds a Master's Degree in Mathematics from the University of Pisa.