Weiwei Yang

Asemic.ai; formerly Microsoft Research

From GridSFM to Asemic-1: Foundation Models for Feasible Grid Decisions

Weiwei is the co-founder of Asemic.ai, where she builds foundation models for engineered systems to power civilization, starting with the electric grid. Previously, as a senior director at Microsoft Research, she led the development and open-source release of GridSFM, a foundation model that generalized across diverse power-grid topologies. That work reflects her broader focus at the intersection of AI, physics, and critical infrastructure: creating models that capture the structure and constraints of real engineering systems. At Asemic, she is turning this vision into practical technology that makes the infrastructure society depends on faster, more adaptive, and more resilient under pressure.

Bernardo Costa

School of Applied Mathematics, Getulio Vargas Foundation (FGV EMAp)

Can we detect multistage strategies in the Energy market?

Bernardo Costa is a professor of mathematics at the School of Applied Mathematics, Getulio Vargas Foundation (FGV), Brazil. His current research focuses on convex optimization, though he also worked with complex analysis and stochastic processes. He is particularly interested in multistage stochastic optimization and applications to the energy sector, having collaborated for 10 years with the Brazilian ISO in several research projects including modeling and algorithms for efficient operations planning.

Minghua Chen

The Chinese University of Hong Kong (Shenzhen) and City University of Hong Kong

Machine Learning for Optimal Power Flow: Beyond Soft Penalties to Hard Constraint Guarantees

Minghua received his B.Eng. and M.S. degrees from Tsinghua University and his Ph.D. in Electrical Engineering and Computer Sciences from UC Berkeley. He is currently a Presidential Chair Professor at the School of Data Science, The Chinese University of Hong Kong, Shenzhen. His research interests include machine learning for optimization, online algorithms, power system operation, intelligent transportation, and distributed optimization. He has received a number of awards and recognition, including the UC Berkeley Eli Jury Award, and best paper awards from IEEE Transactions on Multimedia, ACM Multimedia, ACM e-Energy, and Nature Communications Editors' Highlights. He currently serves as the Award Chair of ACM SIGEnergy, and TPC Area/Track Chair of ACM e-Energy, IEEE INFOCOM, and NeurIPS. He is a Fellow of the IEEE.

Pascal Van Hentenryck

Georgia Tech and Gurobi Optimization

Reliable AI for Power Systems Optimization

Pascal Van Hentenryck is the A. Russell Chandler III Chair and Professor in ISyE at Georgia Tech, the director of the US National Science Foundation (NSF) AI Institute for Advances in Optimization (AI4OPT), and the head of the AI Innovation lab at Gurobi Optimization. He was a professor of Computer Science at Brown University for over 20 years and led the optimization research group at National ICT Australia. Van Hentenryck is a pioneer of constraint programming, and designed several optimization systems that have been in commercial use for over 20 years. He has published 6 books and over 400 articles. He is a fellow of AAAI and INFORMS, and the recipient of two honorary degrees and numerous awards. His current research focuses on fusing AI and optimization for engineering with primary applications in energy systems, supply chains, manufacturing, and health care.

Nando Ochoa

University of Melbourne, Australia

Learning Where No Electrical Model Exists: Voltage Calculations from Real Smart Meter Data

Luis (Nando) Ochoa is a Professor of Smart Grids and Power Systems at The University of Melbourne. His research focuses on electricity distribution networks, particularly the integration of distributed energy resources and the use of data-driven and AI techniques in low voltage networks, where electrical models are often poor or missing altogether. Working with Australian distribution companies, his team has developed electrical model-free approaches that calculate voltages and operating envelopes directly from real smart meter measurements. He is an IEEE PES Distinguished Lecturer and previously held academic roles at the University of Manchester and the University of Edinburgh.

Jingrui He

University of Illinois Urbana-Champaign

Dr. Jingrui He is a Professor at the School of Information Sciences, University of Illinois Urbana-Champaign. She received her PhD from Carnegie Mellon University in 2010. Her research focuses on Agentic AI, heterogeneous machine learning, active learning, neural bandits, and self-supervised learning, with applications in sustainability, agriculture, social network analysis, healthcare, and finance. Dr. He is the recipient of the 2016 NSF CAREER Award, the 2020 OAT Award, the 2025 Amazon Research Award, three times recipient of the IBM Faculty Award, and was selected as IJCAI 2017 Early Career Spotlight. She has more than 250 publications at major conferences and journals, and is the author of two books. Dr. He is a Distinguished Member of ACM, a Senior Member of AAAI and IEEE, and a University Scholar at the U of I.

Priya Donti

MIT

Priya Donti is an Assistant Professor and the Silverman (1968) Family Career Development Professor at MIT EECS and LIDS. Her research focuses on safe and robust machine learning for high-renewables power grids. Priya is also a co-founder and Chair of Climate Change AI, a global nonprofit initiative to catalyze impactful work at the intersection of climate change and machine learning. She received her Ph.D. in Computer Science and Public Policy from Carnegie Mellon University. She was recognized in MIT Technology Review's 2021 list of 35 Innovators Under 35, Vox's 2023 Future Perfect 50, and the 2025 TIME100 AI list, and is a recipient of the Schmidt Sciences AI2050 Early Career Fellowship, the ACM SIGEnergy Doctoral Dissertation Award, and best paper honorable mentions at ICML and ACM e-Energy.

Arnaud Zinflou

Hydro-Québec

Arnaud Zinflou is a Principal Research Scientist at the Hydro-Québec Research Institute (IREQ), where he leads research and development activities in artificial intelligence for power systems and industrial applications. His work spans time-series forecasting, computer vision, representation learning, uncertainty quantification, and trustworthy AI. At Hydro-Québec, he contributes to the development and deployment of AI solutions supporting grid operations, asset management, infrastructure inspection, and decision support. His recent research focuses on foundation and world models for time series, self-supervised learning, and operationally reliable AI systems for critical infrastructure. He is the author or co-author of more than 50 scientific papers, 7 book chapters, and 3 patents, and has been an IEEE Senior Member since 2015.