Fabian Ruehle

Fabian Ruehle is an Assistant Professor of Physics and Mathematics at Northeastern University and a Senior Investigator at the NSF Institute for Artificial Intelligence and Fundamental Interactions (IAIFI). His research focuses on theoretical physics, particularly string theory, and its intersections with mathematics and artificial intelligence. He holds a PhD in Physics from the University of Bonn (2013) and a Diplom in Physics and a B.Sc. in Computer Science from the University of Heidelberg. Ruehle’s work applies machine learning techniques—such as transformers, neural networks, and genetic algorithms—to problems in knot theory, algebraic geometry, and Calabi-Yau manifolds. He has also explored applications of AI in studying multi-omic blood data for COVID-19.

Education

• PhD in Physics (summa cum laude), University of Bonn (2010–2013)
• Diplom in Physics (highest distinction), University of Heidelberg (2003–2009)
• B.Sc. in Computer Science (highest distinction), University of Heidelberg (2006–2009)

Research Interests

Ruehle’s research bridges theoretical physics and computational methods. Key areas include:

• String Theory: Exploring dualities, compactifications, and connections to particle physics and cosmology.
• Machine Learning: Applying neural networks, reinforcement learning, and symbolic regression to problems in topology, algebraic geometry, and physics-informed models.
• Mathematics: Investigating algebraic geometry, knot theory, and Calabi-Yau metrics through computational tools.

Publications

Ruehle’s recent work emphasizes AI-driven approaches to theoretical physics, including studies on neural tangent kernels, ribbon knots, and Calabi-Yau manifold metrics. His articles often highlight interdisciplinary methods, such as combining genetic algorithms with string theory landscapes.

Awards & Grants

• NSF IAIFI Grant (2021–2025)
• NSF Investigator-Initiated Research Project (2022–2026)
• Otto-Haxel Prize for Best Theoretical Physics Degree (2009)

Teaching & Outreach

Ruehle teaches graduate and undergraduate courses on quantum field theory, general relativity, and machine learning applications in physics. He has also organized seminars and workshops on topics like machine learning for mathematicians and string phenomenology.

Labs & Collaborations

He leads projects at the IAIFI and collaborates on initiatives like the String Pheno seminar series. His work often involves computational tools, such as the ribbon Python package for studying ribbon knots.