ReactionAtlas is an iterative ML framework that proposes candidate reactions from seed molecules, filters them with an ML force field for valid transition states, and grows a network of ~47,000 reactions among ~12,000 compounds up to C4 in pre-biotic chemistry.
and Poltavsky, Igor and Schütt, Kristof T
7 Pith papers cite this work, alongside 1,223 external citations. Polarity classification is still indexing.
7
Pith papers citing it
1,223
external citations · OpenAlex
representative citing papers
DeepPolaron ML-MD simulations show rutile electrons form Ti-localized polarons hopping along [001] with 39 meV barrier and 4.4e-2 cm2/Vs mobility, while anatase holes form O-localized polarons hopping to second neighbors with 139 meV barrier and 1.4e-3 cm2/Vs mobility.
Proposes generative pseudo-force fields trained on quadratic pseudo-potentials from noisy equilibria as a time-step-agnostic diffusion variant for efficient molecular conformation generation with high validity on QM9.
Non-autoregressive ionic transport predictor learns dynamics from auxiliary trajectory data during training only, achieving over 200x speedup versus autoregressive models and lower error than non-autoregressive baselines on both dataset types.
Benchmarks of 15 MLIPs show parameter count and training set size correlate with accuracy, architecture drives speed and memory, and explicit Coulomb terms provide no benefit.
Machine-learned force fields trained on coupled-cluster potential energy surfaces produce phonon dispersions and vibrational densities of states for solids that agree better with experiment than DFT-based models.
The paper claims current graph condensation approaches are flawed due to full-dataset training requirements, high overhead, poor generalization, and misleading evaluation metrics, calling for a reset toward lightweight and architecture-agnostic methods.
citing papers explorer
-
ReactionAtlas: Ab origine exploration of chemical reaction networks with machine learning
ReactionAtlas is an iterative ML framework that proposes candidate reactions from seed molecules, filters them with an ML force field for valid transition states, and grows a network of ~47,000 reactions among ~12,000 compounds up to C4 in pre-biotic chemistry.
-
Polaron Transport in TiO$_{2}$ from Machine Learning Molecular Dynamics
DeepPolaron ML-MD simulations show rutile electrons form Ti-localized polarons hopping along [001] with 39 meV barrier and 4.4e-2 cm2/Vs mobility, while anatase holes form O-localized polarons hopping to second neighbors with 139 meV barrier and 1.4e-3 cm2/Vs mobility.
-
Generative Pseudo-Force Fields for Molecular Generation
Proposes generative pseudo-force fields trained on quadratic pseudo-potentials from noisy equilibria as a time-step-agnostic diffusion variant for efficient molecular conformation generation with high validity on QM9.
-
Teaching Molecular Dynamics to a Non-Autoregressive Ionic Transport Predictor
Non-autoregressive ionic transport predictor learns dynamics from auxiliary trajectory data during training only, achieving over 200x speedup versus autoregressive models and lower error than non-autoregressive baselines on both dataset types.
-
Accuracy and Efficiency Benchmarks of Pretrained Machine Learning Potentials for Molecular Simulations
Benchmarks of 15 MLIPs show parameter count and training set size correlate with accuracy, architecture drives speed and memory, and explicit Coulomb terms provide no benefit.
-
Machine-Learned Force Fields for Lattice Dynamics at Coupled-Cluster Level Accuracy
Machine-learned force fields trained on coupled-cluster potential energy surfaces produce phonon dispersions and vibrational densities of states for solids that agree better with experiment than DFT-based models.
-
Position: Graph Condensation Needs a Reset -- Move Beyond Full-dataset Training and Model-Dependence
The paper claims current graph condensation approaches are flawed due to full-dataset training requirements, high overhead, poor generalization, and misleading evaluation metrics, calling for a reset toward lightweight and architecture-agnostic methods.