Program

Plenary speakers

Jonathan Citrin, Google Deepmind, UK – TORAX: A Fast and Differentiable Tokamak Transport Simulator in JAX
Lu Lu, Yale University, USA – Learning operators and diffusion models over function spaces
Stefano Markidis, KTH Royal Institute of Technology, Sweden – Earth’s Magnetosphere as a Distribution: Learning a Generative Atlas of Plasma Environments
Peter Messmer, Nvidia, USA – Harnessing AI compute power for data-driven plasma science
Siddhartha Mishra, ETH Zurich, Switzerland – AI for data-driven simulations in Physics

Invited speakers

Stefan Dasbach, Dutch Institute for Fundamental Energy Research, The Netherlands – Deep learning for estimation and control of power plant scale exhaust
Chuanfei Dong, Boston University, USA – Toward Data-Driven Kinetic Plasma Modeling: From Landau Damping to Turbulence
David Garrido González, Aix Marseille University, France – Geometry-Aware Reduced Order Modelling of Parameter-Dependent Nonlinear Partial Differential Equations
Kentaro Hara, Stanford University, USA – State and parameter estimation of partially ionized gases using data assimilation
Doohyun Kim, Samsung Electronics, Republic of Korea – How does data-driven AI transform the semiconductor processing and manufacturing technologies
Manuel Kirchen, Deutsches Elektronen Synchroton (DESY), Germany – Data-Driven Modelling and Control of Laser-Plasma Accelerators
Bogdan Kustowski, Lawrence Livermore National Laboratory, USA – Automating the search for robustly igniting ICF designs using ML-augmented optimization on the exascale computer El Capitan
Hae June Lee, Pusan National University, Republic of Korea – Prediction of spatiotemporal distributions of RF capacitively coupled plasmas using neural networks
Kookjin Lee, Arizona State University, USA – Neural Operators and Physics-Informed Approaches for Parameterized 1D Capacitively Coupled Plasma Systems
Joe Lu, Lam Research, USA – Data‑Driven Plasma Process Development via Human–Machine Collaboration and Virtual Twins Under Extreme Data Scarcity
Shinya Maeyama, National Institute for Fusion Science, Japan – Turbulent transport modeling in magnetic fusion plasma using a multi-fidelity data fusion approach
George Miloshevich, KU Leuven, Belgium
Hironori Moki, Tokyo Electron Limited, Japan – Surrogate Modeling for Plasma Simulation
Kelly Moran, Los Alamos National Laboratory, USA – From diagnostics to discovery through Bayesian reconstruction of plasma temperature profiles
Motoki Nakata, Komazawa University, Japan – Quantum-information-theoretic measures for turbulence and transport
Takashi Nishizawa, Kyushu University, Japan – Physics-Informed Multidimensional Nonparametric Inference Using Gaussian Processes
Sanghoo Park, Korea Advanced Institute of Science & Technology, Republic of Korea – Deep Spectral Deconvolution for Image-Based Spectral Plasma Data Analysis
Seolhye Park, Seoul National University, Republic of Korea – Designing and Setting up the New OLED Display Mass-Producing Fab Referring to Plasma Information-based Virtual Metrology (PI-VM)
Dirk Reiser, Forschungszentrum Jülich, Germany – Machine Learning for Surface Morphology Studies and Erosion Physics
Alexander Scheinker, Los Alamos National Laboratory, USA – Autoregressive Latent Diffusion for Magnetohydrodynamics
Cristina Venturini, Swiss Plasma Center – EPFL, Switzerland – Data-driven surrogate diagnostic for kinetic profile reconstruction on tokamaks
Qiang Wang, Tokyo Electron America, USA – Deep Neutral Network (DNN) based Surrogate Modeling for Electron Energy Distribution Function (EEDF) Simulation in High Density Plasma

Draft program (subject to change)

Book of abstracts

TBA

Program

TBA

Poster session

TBA

Welcome reception

TBA

Conference dinner

TBA