Summary
I am doing a PhD in the Department of Applied Mathematics and Theoretical Physics (DAMTP) as part of Machine Learning and AI for Medicine group led by Prof. Mihaela van der Schaar. To date, I have published four papers in top-tier ML conferences (NeurIps, ICML [long oral], ICLR and AISTATS).
Research areas: Large Language Models (LLMs), Transformer Architectures, Reinforcement Learning (model-free and model-based), Generative Models, Control, Time Series Forecasting, Symbolic Regression (discovery), Continuous-time models (ODEs, Laplace transforms), and applications to healthcare and scientific discovery.
Background
- 2021 - Now : PhD in Machine Learning at DAMTP
- 2013 - 2017 : MEng in Engineering Science (High 1st class)
Selected publications
- S Holt, M Ruiz Luyten, M van der Schaar: L2MAC: Large Language Model Automatic Computer for Unbounded Code Generation, (Preprint 2023)
- S Holt, A Hüyük, M van der Schaar: Active Observing in Continuous-time Control, (NeurIps 2023)
- S Holt, Z Qian, M van der Schaar: Deep Generative Symbolic Regression, (ICLR 2023) [Code]
- S Holt, A Hüyük, Z Qian, H Sun, M van der Schaar: Neural Laplace Control for Continuous-time Delayed Systems, (AISTATS 2023) [Video] [Code]
- S Holt, Z Qian, M van der Schaar: Neural Laplace: Learning diverse classes of differential equations in the Laplace domain, (ICML 2022) [Long Oral, top 2% of papers] [Video] [Code]