Combining Theory and Benchmarks: Towards A Virtuous Cycle to Understand and Guarantee Foundation Model Performance
Embedded Files
ICML 2026
Seoul, South Korea
July 10 or 11, 2026
Keynote Speakers
Associate Professor
MIT
Topic
TBD
Bio
Tamara Broderick is an Associate Professor in Electrical Engineering and Computer Science at MIT, where she is a member of LIDS and IDSS. Her research focuses on the foundations of Bayesian inference, uncertainty quantification, and scalable, interpretable machine learning. She develops methods to rigorously characterize uncertainty and improve the reliability of data-driven decisions in complex models. Her contributions have been recognized with the NSF CAREER Award, the ONR Young Investigator Award, and the COPSS Emerging Leader Award. Tamara earned her Ph.D. in Statistics from UC Berkeley and her A.B. in Mathematics from Princeton University.
Program Manager, Information Innovation Office
DARPA
Topic
TBD
Bio
Dr. Patrick Shafto joined DARPA in September 2023 to develop, execute, and transition programs in artificial intelligence (AI), mathematics, machine learning, and human-machine symbiosis. He is a professor of mathematics and computer science at Rutgers University, and for the two years before joining DARPA, he was a member of the School of Mathematics at the Institute for Advanced Study in Princeton. His research focuses on the mathematical foundations of learning agents, bridging mathematics, machine learning, AI, and cognitive science. His work has been published in more than 100 papers related to mathematical, computational, and empirical perspectives on learning. He also co-founded and served as chief scientist for Redpoll, a startup focused on human-centered AI, from 2019-2023.
Assistant Professor
Stanford University
Topic
TBD
Bio
Tengyu Ma is an assistant professor of computer science at Stanford. His research interests broadly include topics in machine learning, algorithms and their theory, such as deep learning, (deep) reinforcement learning, pre-training / foundation models, robustness, non-convex optimization, distributed optimization, and high-dimensional statistics.
Staff Research Scientist
Google DeepMind
Topic
TBD
Bio
Hanie is a Staff Research Scientist at Google DeepMind where she leads the DeepPhenomena team. Her research addresses a pivotal challenge in AI: enabling robust planning and scientific reasoning in Foundational Models. Her approach is to systematically deconstruct their reasoning failures to uncover the underlying mechanisms and develop targeted interventions. This work builds upon her long-standing research in the science of deep learning for more than a decade, aiming to push the boundaries of what these models can achieve. Hanie was a workshop chair for NeurIPS 2022 as well as tutorial chair for ICML 2022 and 2023, a program chair for CoLLAs 2023 and has also been an area chair for NeurIPS, ICLR and ICML and a member of JMLR Editorial board.
Page updated
Google Sites
Report abuse