University of Geneva
Faculty of MedecineDepartment of Basic Neurosciences

Théo Desbordes

Function: Post-doctoral position — “Sleep & Cognition ” Lab (Pr. SOPHIE Schwartz) & “NeuroLingo” lab (pr. Nina Kazanina)

Affiliation: Faculty of Medicine, Department of Basic Neurosciences (UniGE)

Keywords: language, memory, magnetoencephalography, artificial intelligence

Short Biography

Dr. Desbordes received his master’s degree in Cognitive Neuroscience from École Normale Supérieure, then got a PhD from Sorbonne University with Stanislas Dehaene (Neurospin) and Jean-Rémi King (Meta AI Research). His doctoral work explored compositionality in language processing — the capacity to combine words into meaningful sentences — in both human neuroimaging data and neural language models. Using magnetoencephalography, intracranial electroencephalography and computational methods, his current research extends to the format of storage of linguistic constructions in memory across timescales. Dr. Desbordes is particularly interested in neural replays, compression mechanisms, and the application of Artificial Intelligence tools to Neuroscience.

If this sounds interesting to you, feel free to get in touch!

Key Publications

For a full list of publications, see his Google Scholar.

  • Desbordes, T., King, J.-R., & Dehaene, S. (2024). Tracking the neural codes for words and phrases during semantic composition, working-memory storage, and retrieval. Cell Reports. https://doi.org/10.1016/j.celrep.2024.113847.
  • Desbordes, T., Lakretz, Y., Chanoine, V., Oquab, M., Badier, J.-M., Trébuchon, A., Carron, R., Bénar, C.-G., Dehaene, S., & King, J.-R. (2023). Dimensionality and Ramping: Signatures of Sentence Integration in the Dynamics of Brains and Deep Language Models. The Journal of Neuroscience. https://doi.org/10.1523/JNEUROSCI.1163-22.2023.
  • Lakretz, Y., Desbordes, T., Hupkes, D., & Dehaene, S. (2022). Can Transformers Process Recursive Nested Constructions, Like Humans? Proceedings of the 29th International Conference on Computational Linguistics. https://aclanthology.org/2022.coling-1.285.
  • Lakretz, Y., Kruszewski, G., Desbordes, T., Hupkes, D., Dehaene, S., & Baroni, M. (2019). The emergence of number and syntax units in LSTM language models. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. https://doi.org/10.18653/v1/N19-1002.
  • Zacharopoulos, C., Desbordes, T., & Sablé-Meyer, M. (2023). Assessing the influence of attractor-verb distance on grammatical agreement in humans and language models. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics. https://doi.org/10.18653/v1/2023.emnlp-main.998.

Contact

Mail: theo.desbordes@unige.ch