I am an assistant professor in Natural Language Processing at the University of Edinburgh and a visiting professor at NVIDIA.
If you are a prospective student please visit the FAQ page for more information.
My research focuses on:
-
efficient architectures (see my NeurIPS 2024 tutorial on dynamic sparsity): I aim to redefine the units of computation of foundation models by adaptively compressing their intermediate representations and memory. This breaks models free from tokenizers and learn hierarchical abstractions over raw data.
-
modular deep learning: I am interested in designing neural architectures that route information to specialised modules (e.g., sparse subnetworks). This facilitates systematic generalisation and conditional computation.
-
computational typology: I wish to understand how languages vary, across the world and its cultures, within a computational and mathematical framework. Multimodal models in particular give us an powerful tool to study how form depends on grounded, embodied representations of meaning and function.
Previously, I was a visiting postdoctoral scholar at Stanford University and a postdoctoral fellow in computer science at Mila - Quebec AI Institute in Montreal. In 2021, I obtained a PhD from the University of Cambridge, St John’s College. Once upon a time I studied typological and historical linguistics at the University of Pavia (deep in my heart, I am still a humanist).
My research has been featured on the Economist and Scientific American, among others. I received a Google Research Faculty Award and 2 Best Paper Awards at EMNLP 2021 and RepL4NLP 2019. I am a board member of SIGTYP, the ACL special interest group for computational typology, a Scholar of the European Lab for Learning and Intelligent Systems (ELLIS), and part of the TACL journal editorial team.
