INFORMED AI Summer School 2026
We are delighted to announce the INFORMED AI Summer School: 15-18 June 2026
The Summer School offers participants an opportunity to engage with cutting-edge research in the mathematics underpinning Artificial Intelligence (AI) and Machine Learning. Designed for both early-career and established researchers from academia and industry, the school provides a collaborative environment to explore foundational and emerging topics in AI.
INFORMED AI is a joint initiative between the Universities of Bristol, Cambridge, Durham, and Imperial College London, focusing on collective intelligence in distributed multi-agent systems. Please see our Research Blog for more information about our work and focus.
The program this year features short courses delivered by leading experts, complemented by opportunities for participants to present short talks and foster discussion.
Join us for an exciting week of learning, discussion, and collaboration at the intersection of mathematics and AI.
Registration opens soon.
Speakers:
Bruno Loureiro (École Normale Supérieure, Paris)
Wonders of high-dimensions: the maths and physics of machine learning: The past decade has witnessed a surge in the development and adoption of machine learning algorithms to solve day-a-day computational tasks. Yet, a solid theoretical understanding of even the most basic tools used in practice is still lacking, as traditional statistical learning methods are unfit to deal with the modern regime in which the number of model parameters are of the same order as the quantity of data – a problem known as the curse of dimensionality. Curiously, this is precisely the regime studied by Physicists since the mid 19th century in the context of interacting many-particle systems. This connection, which was first established in the seminal work of Elisabeth Gardner and Bernard Derrida in the 80s, is the basis of a long and fruitful marriage between these two fields.
The goal of this mini-course is to provide an in-depth overview of these connections and a good vision of the different tools available in the statistical physics toolbox, as well as their scope and limitations.
Note: No prior knowledge of statistical physics is expected.
Sanjay Shakkottai (The University of Texas at Austin)
Discrete Diffusion Models for Generative AI: This tutorial series will focus on discrete diffusion models, with applications to language and image generation. The first two lectures will provide a technical summary of the setting, model formulations, and algorithms. The third lecture will focus on recent research directions. 1. Discrete Diffusion Language Model (DLM) overview. 2. Flow representation (CTMC model) of DLM. 3. Anchoring for discrete diffusion models.
Gayane Vardoyan (University of Massachusetts, Amherst)
tbc