7-9 rue de l’Atlas - Paris, France

Lucy Zhang

Lucy Zhang

Lucy Zhang

PhD Candidate in Neuroscience & AI

Hi! I am Lucy Zhang, a Marie Skłodowska-Curie PhD candidate in Neuroscience and AI, co-affiliated with the École Normale Supérieure and Rothschild Foundation Hospital in Paris. Before my PhD, I completed my undergraduate degree in Experimental Psychology at the University of Oxford and my Master's degree in Brain and Cognitive Sciences, with a focus on computational neuroscience, at the University of Amsterdam.

My research centers on language decoding from diverse neural recordings. I specialize in using linear methods to address neuroscientific questions about language production, while applying deep learning frameworks to solve applied brain-computer interface (BCI) challenges. I am deeply fascinated by the intersection of science and engineering, and I want to further explore how we can leverage scientific insights to improve BCIs for clinical function restoration.

As I progress in my PhD, I have developed a growing interest in leveraging large-scale neural recordings. As the field shifts away from manual feature engineering on small, specific datasets toward large-scale data, methods like self-supervised or contrastive learning offer a powerful means to train foundation models within and across neural recording modalities to advance current approaches in brain decoding and encoding. These models could unlock exciting opportunities for both research and clinical applications.

Evanson, L., Zhang, M., Banville, H., Panchavati, S., Bourdillon, P., & King, J. R. (2025). From Minutes to Days: Scaling Intracranial Speech Decoding with Supervised Pretraining. arXiv preprint arXiv:2512.15830.
Gadonneix, J., Zhang, M., Rapin, J., Evanson, L., Bourdillon, P., & King, J. R. (2026). Temporal structure of the language hierarchy within small cortical patches. arXiv preprint arXiv:2604.03021.
Zhang, M., Lévy, J., d'Ascoli, S., Rapin, J., Alario, F., Bourdillon, P., ... & King, J. R. (2025). From thought to action: How a hierarchy of neural dynamics supports language production. arXiv preprint arXiv:2502.07429.