Built on

“Self-Consistent Equations Including Exchange and Correlation Effects”
W. Kohn and L.. Sham · 1965
Earlier work this paper cites.
“Generalized Gradient Approximation Made Simple.”
John. Perdew, Kieron Burke and Matthias Ernzerhof · 1996
Earlier work this paper cites.
“Assessment of Gaussian-2 and density functional theories for the computation of enthalpies of formation”
Larry. Curtiss, Krishnan Raghavachari, Paul. Redfern and John. Pople · 1997
Earlier work this paper cites.
“Analysis of approximate nearest neighbor searching with clustered point sets”
Songrit Maneewongvatana and David. Mount · 1999
Earlier work this paper cites.
“Commentary: The Materials Project: A materials genome approach to accelerating materials innovation”
Anubhav Jain et al · 2013
Earlier work this paper cites.
“The atomic simulation environment—a Python library for working with atoms”
Ask Hjorth et al · 2017
Earlier work this paper cites.
“Pytorch: An imperative style, high-performance deep learning library”
Original
A Paszke · 2019
Earlier work this paper cites.
“Machine Learning in Python: Main developments and technology trends in data science, machine learning, and artificial intelligence”
Original
Sebastian Raschka, Joshua Patterson and Corey Nolet · 2020
Earlier work this paper cites.
“Learning to Simulate Complex Physics with Graph Networks”
Original
Alvaro Sanchez-Gonzalez et al · 2020
Earlier work this paper cites.
“Highly accurate protein structure prediction with AlphaFold”
John Jumper et al · 2021
Earlier work this paper cites.
“MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fields”, 2023
Original
Ilyes Batatia et al · 2023
Earlier work this paper cites.
“CHGNet: Pretrained universal neural network potential for charge-informed atomistic modeling”, 2023
Original
Bowen Deng et al · 2023
Earlier work this paper cites.
“Stress and heat flux via automatic differentiation”
Marcel Langer, J Frank and Florian Knoop · 2023
Earlier work this paper cites.
“Equiformerv2: Improved equivariant transformer for scaling to higher-degree representations”
Original
Yi-Lun Liao, Brandon Wood, Abhishek Das and Tess Smidt · 2023
Earlier work this paper cites.
“Machine learning coarse-grained potentials of protein thermodynamics”
Maciej Majewski et al · 2023
Earlier work this paper cites.
“Machine-Learning-Assisted Determination of the Global Zero-Temperature Phase Diagram of Materials”
Jonathan Schmidt et al · 2023
Earlier work this paper cites.

Similar

“Single-model uncertainty quantification in neural network potentials does not consistently outperform model ensembles”
Aik Tan et al · 2023
Cited alongside, same era.
“MDR phonon calculation database”
Atsushi Togo · 2023
Cited alongside, same era.
“Neural potentials of proteins extrapolate beyond training data”
Geemi. Wellawatte, Glen. Hocky and Andrew. White · 2023
Cited alongside, same era.
“Open Materials 2024 (OMat24) Inorganic Materials Dataset and Models”, 2024
Original
Luis Barroso-Luque et al · 2024
Cited alongside, same era.
“A foundation model for atomistic materials chemistry”, 2024
Original
Ilyes Batatia et al · 2024
Cited alongside, same era.

Then

“CHIPS-FF: Evaluating Universal Machine Learning Force Fields for Material Properties”
Original
Daniel Wines and Kamal Choudhary · 2024
Later among the works it cites.
“MatterSim: A Deep Learning Atomistic Model Across Elements, Temperatures and Pressures”, arXiv, 2024
Han Yang et al · 2024
Later among the works it cites.
“Accelerating CALPHAD-based Phase Diagram Predictions in Complex Alloys Using Universal Machine Learning Potentials: Opportunities and Challenges”
Original
S Zhu, R Arróyave and D Sarıtürk · 2024
Later among the works it cites.
“Towards Fast, Specialized Machine Learning Force Fields: Distilling Foundation Models via Energy Hessians”, 2025
Original
Ishan Amin, Sanjeev Raja and Aditi Krishnapriyan · 2025
Closest in time.
“Towards Fast, Specialized Machine Learning Force Fields: Distilling Foundation Models via Energy Hessians”

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…

2025

Orb-v3: atomistic simulation at scale

Rhodes, Benjamin, Vandenhaute, Sander, Šimkus, Vaidotas et al.

Understand

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.

Built on

“Self-Consistent Equations Including Exchange and Correlation Effects”
W. Kohn and L.. Sham · 1965
Earlier work this paper cites.
“Generalized Gradient Approximation Made Simple.”
John. Perdew, Kieron Burke and Matthias Ernzerhof · 1996
Earlier work this paper cites.
“Assessment of Gaussian-2 and density functional theories for the computation of enthalpies of formation”
Larry. Curtiss, Krishnan Raghavachari, Paul. Redfern and John. Pople · 1997
Earlier work this paper cites.
“Analysis of approximate nearest neighbor searching with clustered point sets”
Songrit Maneewongvatana and David. Mount · 1999
Earlier work this paper cites.
“Commentary: The Materials Project: A materials genome approach to accelerating materials innovation”
Anubhav Jain et al · 2013
Earlier work this paper cites.
“The atomic simulation environment—a Python library for working with atoms”
Ask Hjorth et al · 2017
Earlier work this paper cites.
“Pytorch: An imperative style, high-performance deep learning library”
Original
A Paszke · 2019
Earlier work this paper cites.
“Machine Learning in Python: Main developments and technology trends in data science, machine learning, and artificial intelligence”
Original
Sebastian Raschka, Joshua Patterson and Corey Nolet · 2020
Earlier work this paper cites.
“Learning to Simulate Complex Physics with Graph Networks”
Original
Alvaro Sanchez-Gonzalez et al · 2020
Earlier work this paper cites.
“Highly accurate protein structure prediction with AlphaFold”
John Jumper et al · 2021
Earlier work this paper cites.
“MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fields”, 2023
Original
Ilyes Batatia et al · 2023
Earlier work this paper cites.
“CHGNet: Pretrained universal neural network potential for charge-informed atomistic modeling”, 2023
Original
Bowen Deng et al · 2023
Earlier work this paper cites.
“Stress and heat flux via automatic differentiation”
Marcel Langer, J Frank and Florian Knoop · 2023
Earlier work this paper cites.
“Equiformerv2: Improved equivariant transformer for scaling to higher-degree representations”
Original
Yi-Lun Liao, Brandon Wood, Abhishek Das and Tess Smidt · 2023
Earlier work this paper cites.
“Machine learning coarse-grained potentials of protein thermodynamics”
Maciej Majewski et al · 2023
Earlier work this paper cites.
“Machine-Learning-Assisted Determination of the Global Zero-Temperature Phase Diagram of Materials”
Jonathan Schmidt et al · 2023
Earlier work this paper cites.

Similar

“Single-model uncertainty quantification in neural network potentials does not consistently outperform model ensembles”
Aik Tan et al · 2023
Cited alongside, same era.
“MDR phonon calculation database”
Atsushi Togo · 2023
Cited alongside, same era.
“Neural potentials of proteins extrapolate beyond training data”
Geemi. Wellawatte, Glen. Hocky and Andrew. White · 2023
Cited alongside, same era.
“Open Materials 2024 (OMat24) Inorganic Materials Dataset and Models”, 2024
Original
Luis Barroso-Luque et al · 2024
Cited alongside, same era.
“A foundation model for atomistic materials chemistry”, 2024
Original
Ilyes Batatia et al · 2024
Cited alongside, same era.

Then

“CHIPS-FF: Evaluating Universal Machine Learning Force Fields for Material Properties”
Original
Daniel Wines and Kamal Choudhary · 2024
Later among the works it cites.
“MatterSim: A Deep Learning Atomistic Model Across Elements, Temperatures and Pressures”, arXiv, 2024
Han Yang et al · 2024
Later among the works it cites.
“Accelerating CALPHAD-based Phase Diagram Predictions in Complex Alloys Using Universal Machine Learning Potentials: Opportunities and Challenges”
Original
S Zhu, R Arróyave and D Sarıtürk · 2024
Later among the works it cites.
“Towards Fast, Specialized Machine Learning Force Fields: Distilling Foundation Models via Energy Hessians”, 2025
Original
Ishan Amin, Sanjeev Raja and Aditi Krishnapriyan · 2025
Closest in time.
“Towards Fast, Specialized Machine Learning Force Fields: Distilling Foundation Models via Energy Hessians”

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

“The dark side of the forces: assessing non-conservative force models for atomistic machine learning”

Original

Filippo Bigi, Marcel Langer and Michele Ceriotti · 2024

Cited alongside, same era.

“Graph atomic cluster expansion for semilocal interactions beyond equivariant message passing”

Anton Bochkarev, Yury Lysogorskiy and Ralf Drautz · 2024

Cited alongside, same era.

“The Potential of Neural Network Potentials”

Timothy. Duignan · 2024

Cited alongside, same era.

“MatCalc”, 2024

Runze Liu et al · 2024

Cited alongside, same era.

“Universal Machine Learning Interatomic Potentials are Ready for Phonons”, 2024

Original

Antoine Loew et al · 2024

Cited alongside, same era.

“Universal Machine Learning Interatomic Potentials are Ready for Phonons”

Original

Antoine Loew et al · 2024

Cited alongside, same era.

“Orb: A fast, scalable neural network potential”

Original

Mark Neumann et al · 2024

Cited alongside, same era.

Ishan Amin, Sanjeev Raja and Aditi. Krishnapriyan · 2025

Closest in time.

“Carbonic anhydrase II simulated with a universal neural network potential”

Original

Timothy Duignan · 2025

Closest in time.

“Exploring foundational machine learned potentials for treating the high temperature dynamics of metal-organic frameworks” This content is a preprint and has not been peer-reviewed

C.. Edwards and J.. Evans · 2025

Closest in time.

“Learning Smooth and Expressive Interatomic Potentials for Physical Property Prediction”

Original

Xiang Fu et al · 2025

Closest in time.

“A Foundational Potential Energy Surface Dataset for Materials”, 2025

Original

Aaron. Kaplan et al · 2025

Closest in time.

“Materials Project PBE Elasticity Dataset”, 2025

Materials Virtual Lab · 2025