Keynote Speakers

Kostya Novoselov

Nobel Prize in Physics 2010, inter alia. Director of the Institute of Functional Intelligent Materials at the National University of Singapore, where he leads the multiscale endeavor to develop a new class of smart materials that actively respond to external stimulus – and can't be simulated with the existing methods.

Daniel Polani

Professor of Artificial Intelligence at the Department of Computer Science, Director of the Centre for Artificial Intelligence and Robotics Research (CAIRR) and Head of the Adaptive Systems Research Group at the University of Hertfordshire. His research interests concentrate on the understanding and modeling of collective complex systems and intelligent decision-making, especially in the context of cognition in artificial and biological agents. His research ranges from fundamental questions, such as the role of embodiment, intrinsic motivations, taskless utilities, self-organization and Artificial Life, to questions from cognitive science, psychology, social science, and biology.

Sergei Gukov

Title Math + AI = AGI

Abstract In this talk, we explore the transformative potential of custom reinforcement learning (RL) algorithms in accelerating solutions to complex, research-level mathematical challenges. We begin by illustrating how these algorithms have achieved a 10X improvement in areas where previous advances of the same magnitude required many decades. A comparative analysis of different network architectures is presented to highlight their performance in this context. We then delve into the application of RL algorithms to exceptionally demanding tasks, such as those posed by the Millennium Prize problems and the smooth Poincaré conjecture in four dimensions. Drawing on our experiences, we discuss the prerequisites for developing new RL algorithms and architectures that are tailored to these high-level challenges. Based on a recent work: What makes math problems hard for reinforcement learning: a case study

Biography Director of Merkin Center for Pure and Applied Mathematics; Consulting Director of American Institute of Mathematics; John D. MacArthur Professor of Theoretical Physics and Mathematics at California Institute of Technology. Sergei is a member of the Scientific Board of the American Institute of Mathematics (AIM) and a member of the International Advisory Board of the Centre for Quantum Mathematics (QM). He has served on numerous other scientific committees and advisory boards. He is editor of the journal Communications in Mathematical Physics, Journal of Knot Theory and Its Ramifications, and Letters in Mathematical Physics. Known for Gukov–Vafa–Witten superpotential, Gukov–Witten surface operators, and Gukov–Pei–Putrov–Vafa (GPPV) invariants. Sergei's expertise is uniquely positioned at the intersection of theoretical physics, mathematics and machine learning.

Charlotte Bunne

Title Virtual Cells and Digital Twins: Multi-Scale and Multi-Modal AI for Biomedicine

Abstract The complexity of cancer demands understanding biological processes across scales, from molecular interactions to tissue architecture. This talk explores how artificial intelligence enables the creation of digital twins at both cellular and tissue levels, with the aim to predict cellular phenotypes, function and their responses to perturbations such as cancer therapies. Concretely, I will introduce the Virtual Tissues (VirTues) platform, a foundation model framework that transforms how we analyze multiplexed tissue data and seamlessly integrates molecular, cellular, and tissue-scale information to increase diagnostic precision and biological understanding in personalized oncology. VirTues employs a multi-modal vision transformer architecture designed to learn from heterogeneous, high-dimensional datasets spanning different biological markers, measurement characteristics, and variable clinical annotations. While existing approaches often focus on H&E-stained slides, our framework incorporates highly multiplexed imaging techniques that capture hundreds of proteins within single tissue sections. Through unsupervised learning and a multi-scale neural network architecture, VirTues unifies these diverse data sources into a coherent virtual tissue space. As a result, new patient biopsy samples can be automatically mapped into this common representation. This enables integrative analyses of morphological, molecular and spatial complexity while facilitating clinically relevant predictions. To bridge insights from the analysis of patient samples with personalized treatment, we employ generative models trained on large biomedical datasets. These models predict treatment responses of biopsied cells from metastatic melanoma patients by revealing patterns of signaling pathway modulation associated with driver mutations and metastasis sites. Together, these approaches enable a multi-scale understanding of cancer biology and treatment response, advancing the development of personalized therapies guided by comprehensive digital twins of patients.

Biography Assistant professor at EPFL in the School of Computer and Communication Sciences (IC) and School of Life Sciences (SV) and a member of the Swiss Institute for Experimental Cancer Research (ISREC). Before, she was a PostDoc at Genentech and Stanford with Aviv Regev and Jure Leskovec and in 2023 completed a PhD in Computer Science at ETH Zurich working with Andreas Krause and Marco Cuturi. During her graduate studies, she was a visiting researcher at the Broad Institute of MIT and Harvard hosted by Anne Carpenter and Shantanu Singh and worked with Stefanie Jegelka at MIT. Her research aims to advance personalized medicine by utilizing machine learning and large-scale biomedical data. Charlotte Bunne’s interdisciplinary research has won several (best paper) awards. Charlotte has been a Fellow of the German National Academic Foundation and is a recipient of the ETH Medal.

Qianxiao Li

Title Constructing macroscopic dynamics using deep learning

Abstract We discuss some recent work on constructing stable and interpretable macroscopic dynamics from trajectory data using deep learning. We adopt a modelling approach: instead of generic neural networks as functional approximators, we use a model-based ansatz for the dynamics following a suitable generalisation of the classical Onsager principle for non-equilibrium systems. This allows the construction of macroscopic dynamics that are physically motivated and can be readily used for subsequent analysis and control. We discuss applications in the analysis of polymer stretching in elongational flow. Moreover, we will also discuss some algorithmic challenges associated with learning (macroscopic) dynamics for scientific applications.

Biography Assistant professor in the Department of Mathematics, National University of Singapore. He graduated with a BA in mathematics from the University of Cambridge and a PhD in applied mathematics from Princeton University in 2016. His research interests include the interplay of machine learning and dynamical systems, control theory, stochastic optimization algorithms and data-driven methods for science and engineering. He is a recipient of the PSTA Young Scientist Award, National Research Foundation Singapore. Qianxiao has published in top material science and machine learning venues, such as Journal of Machine Learning Research, International Conference on Machine Learning, and Matter.