Kernels from pretrained MLIP latent spaces outperform standard acquisition methods in active learning for reactive chemistry, reducing required labels by 38% for energy error and 28% for force error.
Mixed citations
Uberuaga, and Hannes Jónsson
Mixed citation behavior. Most common role is background (60%).
12
Pith papers citing it
20k
external citations · Crossref
Background
60% of classified citations
citation-role summary
background 4
method 1
citation-polarity summary
years
2026 12representative citing papers
Drift-React produces full minimum energy pathways for reactions in a single step via SE(3) drifting fields, matching TS accuracy of iterative models with orders-of-magnitude speedup on Transition1x and Halo8 datasets.
TSAgent automates transition state searches at DFT accuracy via an agentic loop, reaching 83% success on 100 OC20NEB examples and 70% on 10 held-out cases versus 73% for human experts.
Force-aware Neural Tangent Kernels combined with chunked acquisition provide scalable and distribution-robust active learning for MLIPs, outperforming baselines on OC20 and remaining competitive on other benchmarks.
Molecular dynamics simulations find that both I and MA defects in MAPbI3 diffuse rapidly at room temperature with barriers of 0.15-0.20 eV, with MA interstitials moving via concerted mechanisms and no MA vacancy migration observed.
Polarization-resolved high-harmonic generation spectra in bilayer Td-WTe2 exhibit robust signatures of mirror-symmetry breaking from sliding ferroelectricity, enabling all-optical identification of the polarization state.
An open-source Snakemake workflow fully automates NEB reaction path calculations with ML potentials and recovers the known HCN-HNC energy profile without manual steps.
Fine-tuned MACE MLIPs achieve lower mean absolute errors on catalytic reaction energies and barriers than from-scratch models, with a large fine-tuned model performing best on both metallic and oxide systems including out-of-distribution cases.
mlip v2 is a new software release that integrates API redesign, e3j backend, eSEN model, improved charge modeling, and expanded simulation capabilities to support larger-scale molecular modeling.
NO2 adsorption on alpha-Fe2O3 transfers 0.72 electrons and quenches surface small polarons, suppressing polaronic conductivity and explaining sensor resistance increase.
HSE06 calculations of Cu defects in silicon propose a Cu_i4V complex to resolve discrepancies in the Cu_PL defect's transition levels and formation mechanism.
Bayesian optimization with Gaussian processes unifies minimization, single-point saddle searches, and double-ended path searches on potential energy surfaces through a shared six-step surrogate loop using derivative observations and inverse-distance kernels.
citing papers explorer
-
Pretrained Model Representations as Acquisition Signals for Active Learning of MLIPs
Kernels from pretrained MLIP latent spaces outperform standard acquisition methods in active learning for reactive chemistry, reducing required labels by 38% for energy error and 28% for force error.
-
Drift-React: One-step Generation of Reaction Pathways via SE(3) Drifting Fields
Drift-React produces full minimum energy pathways for reactions in a single step via SE(3) drifting fields, matching TS accuracy of iterative models with orders-of-magnitude speedup on Transition1x and Halo8 datasets.
-
TSAgent: An Agentic Workflow for Autonomous Transition State Search
TSAgent automates transition state searches at DFT accuracy via an agentic loop, reaching 83% success on 100 OC20NEB examples and 70% on 10 held-out cases versus 73% for human experts.
-
Force-Aware Neural Tangent Kernels for Scalable and Robust Active Learning of MLIPs
Force-aware Neural Tangent Kernels combined with chunked acquisition provide scalable and distribution-robust active learning for MLIPs, outperforming baselines on OC20 and remaining competitive on other benchmarks.
-
A Unified microscopic picture of cation and anion migration in MAPbI$_3$
Molecular dynamics simulations find that both I and MA defects in MAPbI3 diffuse rapidly at room temperature with barriers of 0.15-0.20 eV, with MA interstitials moving via concerted mechanisms and no MA vacancy migration observed.
-
Probing sliding ferroelectricity in bilayer T$_\mathrm{d}$-WTe$_2$ with high-harmonic generation
Polarization-resolved high-harmonic generation spectra in bilayer Td-WTe2 exhibit robust signatures of mirror-symmetry breaking from sliding ferroelectricity, enabling all-optical identification of the polarization state.
-
Reproducible Orchestration of Best Practices for Reaction Path Optimization with the Nudged Elastic Band
An open-source Snakemake workflow fully automates NEB reaction path calculations with ML potentials and recovers the known HCN-HNC energy profile without manual steps.
-
Systematic Fine-Tuning of MACE Interatomic Potentials for Catalysis
Fine-tuned MACE MLIPs achieve lower mean absolute errors on catalytic reaction energies and barriers than from-scratch models, with a large fine-tuned model performing best on both metallic and oxide systems including out-of-distribution cases.
-
Machine Learning Interatomic Potentials: Advancing Open-Source Software for Efficient and Scalable Molecular Simulation
mlip v2 is a new software release that integrates API redesign, e3j backend, eSEN model, improved charge modeling, and expanded simulation capabilities to support larger-scale molecular modeling.
-
Polaron Conductivity in $\alpha$-Fe2O3 Quenched by Adsorbed NO2
NO2 adsorption on alpha-Fe2O3 transfers 0.72 electrons and quenches surface small polarons, suppressing polaronic conductivity and explaining sensor resistance increase.
-
Hybrid functional calculation of electrical activity and complexing mechanism of Cu-related defects
HSE06 calculations of Cu defects in silicon propose a Cu_i4V complex to resolve discrepancies in the Cu_PL defect's transition levels and formation mechanism.
-
A Tutorial Review of Bayesian Optimization with Gaussian Processes to Accelerate Stationary Point Searches
Bayesian optimization with Gaussian processes unifies minimization, single-point saddle searches, and double-ended path searches on potential energy surfaces through a shared six-step surrogate loop using derivative observations and inverse-distance kernels.