Publications

Orb-v3: atomistic simulation at scale

We introduce Orb-v3, the next generation of the Orb family of universal interatomic potentials. Models in this family expand the performance-speed-memory Pareto frontier, offering near SoTA performance across a range of evaluations with a >10x reduction in latency and > 8x reduction in memory. Our experiments systematically traverse this frontier, charting the trade-off induced by roto-equivariance, conservatism and graph sparsity. Contrary to recent literature, we find that non-equivariant, non-conservative architectures can accurately model physical properties, including those which require higher-order derivatives of the potential energy surface. This model release is guided by the principle that the most valuable foundation models for atomic simulation will excel on all fronts: accuracy, latency and system size scalability. The reward for doing so is a new era of computational chemistry driven by high-throughput and mesoscale all-atom simulations.

Recommended citation: Benjamin Rhodes, Sander Vandenhaute, Vaidotas Šimkus, James Gin, Jonathan Godwin, Tim Duignan and Mark Neumann. "Orb-v3: atomistic simulation at scale." arXiv preprint arXiv:2504.06231 (2025). https://arxiv.org/abs/2504.06231

Orb: A Fast, Scalable Neural Network Potential

We introduce Orb, a family of universal interatomic potentials for atomistic modelling of materials. Orb models are 3-6 times faster than existing universal potentials, stable under simulation for a range of out of distribution materials and, upon release, represented a 31% reduction in error over other methods on the Matbench Discovery benchmark. We explore several aspects of foundation model development for materials, with a focus on diffusion pretraining. We evaluate Orb as a model for geometry optimization, Monte Carlo and molecular dynamics simulations.

Recommended citation: Neumann, Mark, James Gin, Benjamin Rhodes, Steven Bennett, Zhiyi Li, Hitarth Choubisa, Arthur Hussey, and Jonathan Godwin. "Orb: A fast, scalable neural network potential." arXiv preprint arXiv:2410.22570 (2024). https://arxiv.org/abs/2410.22570

Enhanced gradient-based MCMC in discrete spaces

Published in Transactions on Machine Learning Research, 2022

We introduce several discrete Metropolis-Hastings samplers that are conceptually inspired by MALA, and demonstrate their strong empirical performance across a range of challenging sampling problems in Bayesian inference and energy-based modelling. Methodologically, we identify why discrete analogues to \emph{preconditioned} MALA are generally intractable, motivating us to introduce a new kind of preconditioning based on auxiliary variables and the “Gaussian integral trick”.

Recommended citation: Enhanced gradient-based MCMC in discrete spaces. Rhodes, B. and Gutmann, M. Transactions on Machine Learning Research (2022). http://benrhodes26.github.io/files/enhanced_mcmc.pdf

Telescoping Density-Ratio Estimation

Published in Advances in Neural Information Processing Systems - Spotlight (top 4% of submissions), 2020

We propose a new framework, Telescoping Density-ratio Estimation (TRE), that enables the estimation of ratios between highly dissimilar densities in high-dimensional spaces.

Recommended citation: Rhodes, B., Xu, K., and Gutmann, M. (2020). Telescoping Density-Ratio Estimation. In Advances in Neural Information Processing Systems http://benrhodes26.github.io/files/tre.pdf

Variational Noise-Contrastive Estimation

Published in The 22nd International Conference on Artificial Intelligence and Statistics (AISTATS), 2019

We propose a new method for estimating the parameters of energy-based, latent variable models. The core contribution is the derivation of a variational lower bound for the noise-contrastive estimation objective function.

Recommended citation: Rhodes, B. and Gutmann, M. U. (2019). Variational noise-contrastive estimation. InThe 22nd InternationalConference on Artificial Intelligence and Statistics, pages 2741–2750. http://benrhodes.github.io/files/vnce.pdf

Dimension Formulae for Iterated Function Systems

Unpublished MSci dissertation. The majority of the dissertation is an exposition of prior books and papers, but the final 10 pages contain original material, culminating in Theorem 7.19 which gives a lower bound on the Hausdorff dimension of a certain class of planar fractals.

Download here