About
I am a machine learning researcher. I recently finished my DPhil at the University of Oxford, supervised by Xiaowen Dong and Michael Bronstein, as a member of the Autonomous Intelligent Machines and Systems Centre for Doctoral Training (AIMS CDT).
My research is on learning from relational and structured data (graphs, molecules, sequences, documents), with a focus on long-range interactions, and on long-context reasoning in LLMs. In particular:
- Message-passing neural networks, graph Transformers and graph foundation models
- Long-range interactions, and measuring range in GNNs
- LLMs, particularly for long contexts
- AI for document processing, including handwriting transcription with multi-modal LLMs
Earlier, I worked on the HumBug project, which detects and classifies mosquito species from phone recordings, and completed my MEng in Engineering Science at Oxford.
Find my CV here.
In my spare time I enjoy reading books, watching films, playing and GMing D&D and other TTRPGs, and exploring new pubs, especially those with real ale. I maintain a table of ratings and useful information about every pub in Oxford here.
11/09/2026: Passed my viva (DPhil defence) with minor corrections! 🎉
09/07/2026: Judge a Book by Its Cover: Investigating Multi-Modal LLMs for Multi-Page Handwritten Document Transcription accepted to COLM (the Conference On Language Modeling) 2026 in San Francisco!
26/04/2026: Presented my paper “Can Graph Foundation Models Generalize Over Architecture?” as a poster at the ICLR-26 Workshop on Geometry-grounded Representation Learning and Generative Modeling (GRaM) in Rio de Janeiro 🇧🇷. Check out the poster and the paper!
24/04/2026: Submitted my thesis! 🎉🎉🎉
02/03/2026: “Can Graph Foundation Models Generalize Over Architecture?” accepted to the ICLR-26 Workshop on Geometry-grounded Representation Learning and Generative Modeling (GRaM) in Rio de Janeiro as a full-length PMLR proceedings paper.
28/12/2025: Best Books of 2025
02/07/2025: Started return internship in the Deep Learning team at QuantCo.
01/05/2025: “On Measuring Long-Range Interactions in Graph Neural Networks”, a co-first-authored paper with Jacob Bamberger and Scott le Roux, accepted to ICML 2025.
31/12/2024: Best Books of 2024
17/12/2024: Judge a Book by Its Cover: Investigating Multi-Modal LLMs for Multi-Page Handwritten Document Transcription accepted to the AAAI-25 Workshop on Document Understanding and Intelligence (DocUI@AAAI-25) in Philadelphia.
10/06/2024: Started internship in the Deep Learning team at QuantCo working on DocAI and LLM long-context reasoning.
03/03/2024: Started Visiting Data Scientist internship at BCG X, working on the ‘Pathfinder’ flight schedule optimiser at British Airways.
06/08/2023: DRew covered in round-up blog post by @michael_galkin: Graph Machine Learning @ ICML 2023.
28/07/2023: DRew discussed in keynote talk by @mmbronstein at TAG-ML workshop at ICML 2023.
19/06/2023: Presented DRew to Learning on Graphs and Geometry (LoGG) reading group (recording here). Blog post based on DRew published on Towards Data Science.
23/04/2023: First-author paper, “DRew: Dynamically Rewired Message Passing with Delay”, accepted to ICML 2023.