Benchmarking Compositional Generalisation for Machine Learning Interatomic Potentials
NeurIPS 2026
Benchmarking Compositional Generalisation for Machine Learning Interatomic Potentials
NeurIPS 2026
For chemists: Knowing the parts, missing the whole
Seminar version. Leads with the chemistry (functional groups, molecular dynamics, DFT) and keeps machine learning jargon light.
Seminar version. Leads with compositional generalisation and out-of-distribution evaluation, and explains the chemistry from scratch.
Explainable Graph Neural Network for Computational Chemistry
First-year review · Cardiff University · 2025