Published multiple papers, including a paper on transferrable surrogates at AutoML 2025 and einspace at NeurIPS 2024. Co-organized the NAS Unseen-Data competition as part of AutoML 2024. Received a best paper award at AutoML 2023.
Research Experience
Postdoctoral researcher at the University of Edinburgh, working with Elliot J. Crowley on AutoML and efficient neural network architectures. Interned at Samsung AI Centre Cambridge with Tim Hospedales & Da Li. Interned at Huawei Noah’s Ark Lab with Steven McDonagh & Ales Leonardis.
Education
PhD from the University of Edinburgh, thesis titled 'Self-Supervised Learning for Transferable Representations', supervised by Tim Hospedales, and supported in part by the EPSRC.
Background
Lecturer (Assistant Professor) in AI/ML at the University of Glasgow. Research interests include representation learning, multi-modal learning, robustness, and automated machine learning (AutoML). Focuses on using AI/ML methods to learn transferable data representations, building efficient neural networks, and adapting these models across data shifts to help people solve problems reliably across different scenarios.