Archive Block
This is example content. Double-click here and select a page to create an index of your own content. Learn more
Filter by name
Filter by tag
Projects in progress
Learning to structure the world
mechanistic interpretability, representation learning, methodology
Learning to structure the world
mechanistic interpretability, representation learning, methodology

This project aims not only to learn representations, but also to develop generative models that use learning‑to‑structure to improve efficiency, generalisation, and the ability to express and estimate uncertainty.

Read more →
mechanistic interpretability, representation learning, methodology
One Step Generation
probabilistic modelling, variational inference, approximate inference, methodology
One Step Generation
probabilistic modelling, variational inference, approximate inference, methodology

This two-stage training process, whilst pragmatic, raises some deep questions: why can't we train a one-step generator directly, without needing to first train a diffusion model?

Read more →
probabilistic modelling, variational inference, approximate inference, methodology
Generative and Explainable Modelling of Single-Cell and Spatial Omics Data
Generative and Explainable Modelling of Single-Cell and Spatial Omics Data

It All Begins Here

Read more →
Memory System for Long-Context LLMs
Memory System for Long-Context LLMs

This project develops a novel flexible memory system that enables AI assistants to maintain truly coherent, long-term conversations by preserving raw conversational data and supporting multi-resolution retrieval without information loss.It All Begins Here

Read more →