PhD student in Computer Science at the University of Cambridge working on NLP and Machine Learning.
energizer. An active learning library for Pytorch based on Lightning-Fabric.
79memorisation-profiles. This is the official implementation for our ACL 2024 paper: "Causal Estimation of Memorisation Profiles".
25anchoral. This is the official PyTorch implementation for our NAACL 2024 paper: "AnchorAL: Computationally Efficient Active Learning for Large and Imbalanced Datasets".
22tokenisation-bias. Jupyter Notebook
8whisper-bot. A Telegram bot that converts audio to text
5bayesian-statistics-in-julia. This repo contains the code that I produced while studying Julia and Turing, roughly following the Bayesian Data Analysis (BDA3) curriculum
2