Ben Erichson

Biography

Ben Erichson, PhD, is a Senior Research Scientist, Group Lead for Deep Learning, and a Research Mentor at ICSI. He also serves as Research Scientist at Lawrence Berkeley National Laboratory. 

Dr. Erichson’s research interests focus on the intersection of deep learning, dynamical systems, and robustness, addressing the question of how we can build robust and intelligent dynamical systems that are computationally efficient and expressive. His research interests focus on the intersection of deep learning, dynamical systems, and robustness, addressing the question of how we can build robust and intelligent dynamical systems that are computationally efficient and expressive. His recent work centers on building large-scale generative diffusion models for spatio-temporal forecasting, with a focus on scientific domains such as weather systems, seismic wave propagation, and fluid dynamics. He is particularly interested in how such models can be integrated with reasoning and large multimodal systems to enhance forecasting through the fusion of numeric, textual, and contextual metadata, enabling richer, more adaptable decision-making systems. He is also actively exploring AI safety, including backdoor and jailbreaking attacks, and the development of reliable LLM-based judges. 

Before coming to ICSI, Dr. Erichson was a tenure-track assistant professor of data-driven modeling and artificial intelligence in the Department of Mechanical Engineering and Materials Science at the University of Pittsburgh. He also previously served as a postdoctoral researcher in the Department of Statistics at UC Berkeley, in the RISELab in the Department of Electrical Engineering and Computer Sciences (EECS) at UC Berkeley, and in the Department of Applied Mathematics at the University of Washington. He earned his PhD in Statistics at the University of St Andrews.

Publications

Areas of Expertise

• Artificial Intelligence
• Machine Learning (Supervised, Unsupervised, Reinforcement Learning)
• Deep Learning and Neural Networks
• Generative AI and Foundation Models
• Planning, Decision-Making, and Intelligent Agents
• Adversarial AI and Robust Machine Learning
• AI Safety, Alignment, and Trustworthiness
• Agentic AI (Autonomous AI Agents)
• AI for National Security, Defense, and Critical Infrastructure

ICSI Activity