AI2Pot is presented, a scalable and unified MLIP framework that seamlessly integrates model training, evaluation, and large-scale MD simulations with PyTorch-compatible ecosystem, and offers an user-friendly end-to-end framework for the developing, training, and deploying MLIPs for large scale MD.
Abstract
Machine-learning interatomic potentials (MLIPs) bridge the accuracy of first-principles calculations and the efficiency required for large-scale molecular dynamics (MD) simulations. However, existing MLIP software remains fragmented across different model architectures, making it difficult to establish unified workflows that support flexible model development, efficient training, and scalable MD deployment. Here, we present AI2Pot, a scalable and unified MLIP framework that seamlessly integrates model training, evaluation, and large-scale MD simulations with PyTorch-compatible ecosystem. Instead of relying on generic automatic differentiation for expensive atomistic operators, AI2Pot re-engineers the core computations of Moment tensor potential (MTP) and Neuroevolution potential (NEP) for both training and inference using hand-crafted C++/CUDA code. These specialized operators constitute a unified computational backend shared by training and inference, improving training-inference consistency and reducing memory usage by avoiding large intermediate caches. As a result, AI2Pot enables fast inference for large-scale atomic systems containing millions of atoms on a single GPU, while retaining the flexibility of PyTorch for model construction, training, and evaluation. Trained models can be deployed in ASE and LAMMPS for MD simulations. Furthermore, AI2Pot provides a companion command-line toolkit (AI2Pot-cli) and Python APIs to facilitate practical MLIP workflows. By unifying high-performance atomistic computing with modern machine-learning ecosystems, AI2Pot offers an user-friendly end-to-end framework for the developing, training, and deploying MLIPs for large scale MD.
The Active Learning Framework (ALF), an open-source Python package designed to streamline the design and deployment of MLIP training datasets on High Performance Computing resources, is introduced, illustrating ALF’s effectiveness in compiling datasets that capture essential chemical and structural regimes.
V. Grizzi, P. Lohr, Nikita Fedik et al.· Journal of Chemical Theory a...· 0 citations
This work introduces MLIP Studio, an open and free platform that brings more than 60 universal MLIPs into a unified interactive interface for molecules and materials, and demonstrates that MLIP-based pre-optimization can reduce subsequent DFT optimization effort by ~33$\times$.
Manas Sharma, Sudeep N. Punnathanam, A. Rajan· 1 citation
The limits of equivariant MLIPs are examined, and a family of foundation potentials in the NequIP and Allegro equivariant MLIP architectures are presented which achieve leading inference speeds and strong scalability as well as excellent accuracies across a range of community benchmarks.
Seán R. Kavanagh, Chuin Wei Tan, Menghang Wang et al.· 0 citations
Pretrained machine-learning interatomic potentials, so-called universal or foundation models offer an appealing starting point for atomistic simulations, but their accuracy for material-specific observables often remains limited without additional reference data (fine-tuning). Here, we systematically quantify how much first-principles data are required to convert universal models into ab initio-accurate material-specific potentials, and ask whether fine-tuning is necessarily preferable to training from scratch. We compare five universal MLIP frameworks, MACE-MP-0, SevenNet-0, GRACE-1L-OAM, MatterSim-v1-5M and ORB-v2, across seven chemically diverse systems incorporating rare and reactive events. Fine-tuning on only 10 AIMD-derived configurations is insufficient for the investigated systems; 200 configurations succeed in favorable cases, but the outcome remains strongly system-dependent. By contrast, 2000 AIMD configurations constitute a robust default, yielding low force and energy errors and reproducing the target material-specific observables. Moderately dense sub-sampling of the AIMD trajectory reduces the required trajectory length tenfold with little loss in model quality. Training from scratch on the same datasets is competitive with, and often slightly more accurate than, naive fine-tuning for MACE and SevenNet, whereas GRACE requires more data. The energy profile for a sulfur-vacancy jump in MoS$_2$ reveals that low trajectory-level errors do not guarantee a correct reaction profile, highlighting the need for observable-level validation. Finally, we show that averaging independently trained models improves predictions in scarce-data regimes at no additional first-principles cost. Together, these results provide practical guidelines for converting limited AIMD reference data into reliable material-specific MLIPs for nanosecond-timescale simulations at near-DFT accuracy.
This work introduces implicit machine learning force fields, which replace explicit stacks of neural network layers with self-consistent fixed-point equations, and demonstrates this across three major classes of graph neural networks: invariant, equivariant Cartesian tensor, and SO(3)-equivariant spherical-tensor architectures.
J. Maess, Leon Werner, J. Frank et al.· 0 citations
Foundation machine learning interatomic potentials (MLIPs) deliver near-ab-initio accuracy at a fraction of the computational cost, yet their promise for Metal-organic Frameworks (MOFs) remains largely unrealized as large unit cells make first-principles training data expensive to generate, fine-tuned models are scarce, and experimentally grounded benchmarks are scarcer still. We introduce uMOF, a three-part contribution addressing this gap. First, we release the largest and most accurate density functional theory dataset for MOFs to date, computed at the r$^2$SCAN-D4 level of theory across 85524 configurations spanning 19950 unique frameworks and 79 elements, covering empty and gas-loaded structures, geometry optimizations, equations of state, and finite-temperature molecular dynamics. Second, we release a literature-mined benchmark of 3986 verified property values (3146 experimental) extracted from 626 papers by a seven-stage, checkpointed multi-pass large language model pipeline, linked to more than 650 crystallographic information files. Third, we release two universal MLIPs for MOFs, uMOF-MH and uMOF-POLAR, fine-tuned from two architecturally distinct MACE foundation models on the uMOF dataset. On near-equilibrium, ``Tier-1''properties (bulk modulus, phonon-derived heat capacity) the uMOF models perform comparably to existing foundation and fine-tuned baselines. On harder, dynamics-sensitive properties like gas adsorption enthalpies via Widom insertion and adsorption isotherms, the uMOF models outperform every baseline we test, including MOF-specialized gas-capture models trained on datasets up to three orders of magnitude larger, cutting error by more than 80% to within experimental uncertainty. We trace this advantage to the physical diversity of the training data and to level of theory where a small (1.7%) fraction of MD simulations is decisive for MLIP stability.
T. J. Inizan, Prathami Divakar Kamath, A. Elena et al.· 0 citations
