Pehuén Moure

I am a PhD candidate at ETH Zurich’s Institute of Neuroinformatics, working at the intersection of machine learning and neuroscience. My research focuses on developing robust AI systems that can generalize across domains, from neuroprosthetic control to reinforcement learning for robotics and personalized speech recognition.

Currently, I’m developing deep learning approaches for controlling neural activity in visual prostheses and building methods for improving generalization in reinforcement learning using Bayesian neural networks. I also lead the development of personalized speech recognition tools for people with impaired speech, and I use neuroscience-inspired approaches to understand how large language models perform on complex reasoning tasks. If you’re interested in a master’s or bachelor’s project or thesis, you can browse the open student projects or just contact me directly!

My work aims to bridge the gap between theoretical advances in machine learning and practical applications, particularly in healthcare and robotics. I’m passionate about developing AI systems that can adapt to diverse needs and serve specific individuals rather than just average use cases.

A list of my publications can be found on my publications page, and short explainers on some of the work are on my videos page.