ÂÜÀòÂÒÂ×

Alex Spies is a JSPS Fellow at the National Institute of Informatics, engaged in full-time research focusing on enhancing reasoning in large language models through the integration of symbolic methods and mechanistic reverse-engineering. Currently a doctoral student at Imperial College London, Alex works on Neuro-symbolic Learning and Reinforcement Learning under the supervision of Professor A. Previous research experiences include a summer internship at DESY, where Alex investigated Higgs-based Stau production channels, and an undergraduate research assistantship at Berkeley Lab, where work involved a novel technique for improving pixel sensor readouts. Alex holds a Master of Science in Computer Science specializing in Artificial Intelligence and Machine Learning from Imperial College London and an MPhys in Physics with Theoretical Physics from The University of Manchester.