activity
20242026
collaborators

8 papers

cs.LG2026

Learning Generation Orders for Masked Discrete Diffusion Models via Variational Inference

David Fox, Sam Bowyer, Song Liu +3

Masked discrete diffusion models (MDMs) are a promising new approach to generative modelling, offering the ability for parallel token generation and therefore greater efficiency th…

physics.ao-ph2026

Machine learning emulation of precipitation from km-scale UK regional climate simulations using a diffusion model

Henry Addison, Elizabeth Kendon, Suman Ravuri +2

High-resolution climate simulations are valuable for understanding climate change impacts. This has motivated use of regional convection-permitting climate models (CPMs), but these…

cs.CL2025

Scale-invariant Attention

Ben Anson, Xi Wang, Laurence Aitchison

One persistent challenge in LLM research is the development of attention mechanisms that are able to generalise from training on shorter contexts to inference on longer contexts. W…

cs.LG2025

Controlling changes to attention logits

Ben Anson, Laurence Aitchison

Stability of neural network weights is critical when training transformer models. The query and key weights are particularly problematic, as they tend to grow large without any int…

stat.ML2025

Flexible Infinite-Width Graph Convolutional Neural Networks

Ben Anson, Edward Milsom, Laurence Aitchison

A common theoretical approach to understanding neural networks is to take an infinite-width limit, at which point the outputs become Gaussian process (GP) distributed. This is know…

stat.ML2025

Function-Space Learning Rates

Edward Milsom, Ben Anson, Laurence Aitchison

We consider layerwise function-space learning rates, which measure the magnitude of the change in a neural network's output function in response to an update to a parameter tensor.…