mlsanityData to 14 Oct 2026

Orb: A Fast, Scalable Neural Network Potential

arXiv 2410.22570 ↗First posted 29 Oct 2024cond-mat.mtrl-sci cs.LGcited by 66

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 66 papers in the map (data through 14 Oct 2026). Builds on 35 of its 61 references that are in the map. First posted on arXiv 29 Oct 2024.

Builds on

35 of 61 references.

References · 35

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2017Graph Attention Networkscited by 8,923
  5. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  6. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  7. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  8. 2020Point Transformercited by 1,470
  9. 2021Variational Diffusion Modelscited by 1,153
  10. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,102
  11. 2020Learning to Simulate Complex Physics with Graph Networkscited by 880
  12. 2021E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentialscited by 708
23 more
  1. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 657
  2. 2022MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fieldscited by 474
  3. 2022Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphscited by 264
  4. 2023EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representationscited by 204
  5. 2022Pre-training via Denoising for Molecular Property Predictioncited by 124
  6. 2022Equivariance with Learned Canonicalization Functionscited by 109
  7. 2022The Design Space of E(3)-Equivariant Atom-Centered Interatomic Potentialscited by 101
  8. 2022Forces are not Enough: Benchmark and Critical Evaluation for Machine Learning Force Fields with Molecular Simulationscited by 95
  9. 2018Less is more: sampling chemical space with active learningcited by 82
  10. 2023Swallowing the Bitter Pill: Simplified Scalable Conformer Generationcited by 56
  11. 2022The Lie Derivative for Measuring Learned Equivariancecited by 54
  12. 2020Learning Invariances in Neural Networkscited by 52
  13. 2021Simple GNN Regularisation for 3D Molecular Property Prediction & Beyondcited by 44
  14. 2023Smooth, exact rotational symmetrization for deep learning on point cloudscited by 39
  15. 2023From Molecules to Materials: Pre-training Large Generalizable Models for Atomic Property Predictioncited by 39
  16. 2023Matbench Discovery -- A framework to evaluate machine learning crystal stability predictionscited by 35
  17. 2024Emergent Equivariance in Deep Ensemblescited by 18
  18. 2024Generalizing Denoising to Non-Equilibrium Structures Improves Equivariant Force Fieldscited by 18
  19. 2023Uncertainty-biased molecular dynamics for learning uniformly accurate interatomic potentialscited by 16
  20. 2023CHGNet: Pretrained universal neural network potential for charge-informed atomistic modelingcited by 13
  21. 2024Probing the effects of broken symmetries in machine learningcited by 13
  22. 2023Denoise Pretraining on Nonequilibrium Molecules for Accurate and Transferable Neural Potentialscited by 11
  23. 2024Stability-Aware Training of Machine Learning Force Fields with Differentiable Boltzmann Estimatorscited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 34; 2026: 31.

66 papers.

Sort:

By area:

  1. 2025UMA: A Family of Universal Models for Atomscited by 105
  2. 2025Learning Smooth and Expressive Interatomic Potentials for Physical Property Predictioncited by 84
  3. 2025A practical guide to machine learning interatomic potentials -- Status and futurecited by 26
  4. 2024The dark side of the forces: assessing non-conservative force models for atomistic machine learningcited by 24
  5. 2025PET-MAD, a lightweight universal interatomic potential for advanced materials modelingcited by 23
  6. 2025Universally Converging Representations of Matter Across Scientific Foundation Modelscited by 14
  7. 2025Reinforcement Fine-Tuning for Materials Designcited by 13
  8. 2025FlashMD: long-stride, universal prediction of molecular dynamicscited by 12
  9. 2026Pushing the limits of unconstrained machine-learned interatomic potentialscited by 11
  10. 2026EquiformerV3: Scaling Efficient, Expressive, and General SE(3)-Equivariant Graph Attention Transformerscited by 11
  11. 2025How simple can you go? An off-the-shelf transformer approach to molecular dynamicscited by 10
  12. 2025Flexible MOF Generation with Torsion-Aware Flow Matchingcited by 10
38 more
  1. 2025Establishing baselines for generative discovery of inorganic crystalscited by 9
  2. 2025Retro-Rank-In: A Ranking-Based Approach for Inorganic Materials Synthesis Planningcited by 7
  3. 2025MOFSimBench: Evaluating Universal Machine Learning Interatomic Potentials In Metal--Organic Framework Molecular Modelingcited by 7
  4. 2025Transformers Discover Molecular Structure Without Graph Priorscited by 7
  5. 2025UniFFBench: Evaluating Universal Machine Learning Force Fields Against Experimental Measurementscited by 6
  6. 2025BLIPs: Bayesian Learned Interatomic Potentialscited by 6
  7. 2025Training a Foundation Model for Materials on a Budgetcited by 6
  8. 2026PFT: Phonon Fine-tuning for Machine Learned Interatomic Potentialscited by 6
  9. 2025MatterTune: An Integrated, User-Friendly Platform for Fine-Tuning Atomistic Foundation Models to Accelerate Materials Simulation and Discoverycited by 5
  10. 2025Mofasa: A Step Change in Metal-Organic Framework Generationcited by 5
  11. 2025AI-Driven Expansion and Application of the Alexandria Databasecited by 5
  12. 2026Zatom-1: Towards a Multimodal Foundation Model for 3D Molecules and Materialscited by 5
  13. 2025LeMat-Traj: A Scalable and Unified Dataset of Materials Trajectories for Atomistic Modelingcited by 4
  14. 2025Leveraging neural network interatomic potentials for a foundation model of chemistrycited by 3
  15. 2025AlphaNet: Scaling Up Local-frame-based Atomistic Interatomic Potentialcited by 2
  16. 2025Training speedups via batching for geometric learning: an analysis of static and dynamic algorithmscited by 2
  17. 2025Fast, Modular, and Differentiable Framework for Machine Learning-Enhanced Molecular Simulationscited by 2
  18. 2026Better without U: Impact of Selective Hubbard U Correction on Foundational MLIPscited by 2
  19. 2026CrystalREPA: Transferring Physical Priors from Universal MLIPs to Crystal Generative Modelscited by 2
  20. 2025Pre-training Graph Neural Networks with Structural Fingerprints for Materials Discoverycited by 1
  21. 2025Accelerating and enhancing thermodynamic simulations of electrochemical interfacescited by 1
  22. 2025Cross-functional transferability in universal machine learning interatomic potentialscited by 1
  23. 2025Molecular Learning Dynamicscited by 1
  24. 2025Gradient-based grand canonical optimization enabled by graph neural networks with fractional atomic existencecited by 1
  25. 2025ADAPT: Lightweight, Long-Range Machine Learning Force Fields Without Graphscited by 1
  26. 2026AceFF: A State-of-the-Art Machine Learning Potential for Small Moleculescited by 1
  27. 2026Faster Molecular Dynamics with Neural Network Potentials via Distilled Multiple Time-Stepping and Non-Conservative Forcescited by 1
  28. 2026How unconstrained machine-learning models learn physical symmetriescited by 1
  29. 2026Exact Symmetry as Algebra: Group-Structured Tensors that Enforce Physical Selection Rulescited by 1
  30. 2026TriForces: Augmenting Atomistic GNNs for Transferable Representationscited by 1
  31. 2026Surrogate-Gated Generation and Foundation-Model Embeddings for Bayesian Materials Designcited by 1
  32. 2026Implicit Machine Learning Force Fields Accelerate Molecular Dynamics Simulationscited by 1
  33. 2026OMatG-flash: An All-Atom Flow Map with Reinforce Adjoint Matching for Scalable Materials Discoverycited by 1
  34. 2025MoMa: A Modular Deep Learning Framework for Material Property Predictioncited by 0
  35. 2025Are Foundational Atomistic Models Reliable for Finite-Temperature Molecular Dynamics?cited by 0
  36. 2025On the Connection Between Diffusion Models and Molecular Dynamicscited by 0
  37. 2025Benchmarking Universal Interatomic Potentials on Zeolite Structurescited by 0
  38. 2026Enhancing Spatial Reasoning in Large Language Models for Metal-Organic Frameworks Structure Predictioncited by 0

50 most cited of 66 All 66 (JSON)