Scientific intelligence / MAGICS Lab
NORTHWESTERN UNIVERSITYWe build AI that reasons about scientific problems, models complex worlds, and learns through experimentation. From the foundations of intelligence to discovery in the physical world.
The research agenda
AI that can turn scientific experience into better models, better decisions, and new discoveries.
How can AI become a better scientist through experience? We study memory, reasoning, adaptation, and tool use—and build agents that turn evidence into the next research question.
Explore the foundations →From genomes and cells to the changing universe. We learn representations of scientific objects and processes that support prediction and reasoning about interventions.
Explore the models →Connect scientific agents with simulation, robotics, and automated experiments. Build systems that choose what to test, execute a plan, and learn from what happens.
Explore the systems →From ideas to scientific infrastructure
Directed by Han Liu, Northwestern’s CFMG connects foundational advances in machine intelligence with science and engineering, bringing researchers together around models, reasoning, and discovery.
Explore the center ↗An NSF-supported programmable laboratory connecting protein design, AI, robotics, and automated experimentation. Han Liu serves as Co-PI and AI lead.
Inside the initiative ↗Han Liu co-leads a scientific foundation-model project within the NSF–Simons SkAI Institute, learning from astronomical time-series data.
Explore the project ↗Explore our open software, meet the researchers, or start a conversation about the next scientific challenge.
GitHub
Google Scholar
LinkedIn
CFMG