The research on controlled thermonuclear fusion aims at providing stable, baseload electric power by creating “a star on earth”. It is a long-term collaboration of specialists with various areas of experience. Graphical representations (plots, images, …) play a key role in communications regarding machine operation and physics studies, but uncovering specific information from the vast repositories that have been accumulated over many years, can be a considerable challenge. Recent advances in large language models (LLMs) have shown an impressive capacity to generate acceptable responses to queries based on newly provided (in-context) information. A further step is the understanding of image data. The goal of the internship is to create an expert system that can understand figures produced in fusion science, by applying existing image captioning techniques on a curated dataset. The end user will be able to prompt the chatbot to look for a figure, understand its context, or answer questions about it. Depending on the student’s background (emphasis on physics or computer science), the internship can focus on correct interpretation by the chatbot of physics results, or on the technical aspects of the tool.

Master of Science in Engineering Physics, Master of Science in Physics and Astronomy, European Master of Science in Nuclear Fusion and Engineering Physics, Master of Science in Computer Science Engineering, Master of Science in Information Engineering Technology