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.
Persson, and Gerbrand Ceder
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 2
method 2
citation-polarity summary
years
2026 4representative citing papers
DFT survey of H, He, B, C, N, O, P, S at six CSL grain boundaries in ferritic iron finds B and C strengthen cohesion while He, O, S act as powerful decohesives, with public data release.
AQVolt26 is a new high-temperature halide dataset that improves universal ML interatomic potentials for distorted configurations while showing that near-equilibrium relaxation data is not universally helpful.
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.
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.
-
Grain boundary segregation of light elements and their effects on cohesion in ferritic steels
DFT survey of H, He, B, C, N, O, P, S at six CSL grain boundaries in ferritic iron finds B and C strengthen cohesion while He, O, S act as powerful decohesives, with public data release.
-
AQVolt26: High-Temperature r$^2$SCAN Halide Dataset for Universal ML Potentials and Solid-State Batteries
AQVolt26 is a new high-temperature halide dataset that improves universal ML interatomic potentials for distorted configurations while showing that near-equilibrium relaxation data is not universally helpful.
-
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.