| Accelerating Molecular Graph Neural Networks via Knowledge Distillation F Ekström Kelvinius, D Georgiev, A Toshev, J Gasteiger Advances in Neural Information Processing Systems 36, 2023 | 36 | 2023 |
| Graph-based machine learning beyond stable materials and relaxed crystal structures F Ekström Kelvinius, R Armiento, F Lindsten Physical Review Materials 6 (3), 033801, 2022 | 13 | 2022 |
| WyckoffDiff-A Generative Diffusion Model for Crystal Symmetry F Ekström Kelvinius, OB Andersson, AS Parackal, D Qian, R Armiento, ... ICML 2025, 2025 | 12* | 2025 |
| Discriminator Guidance for Autoregressive Diffusion Models F Ekström Kelvinius, F Lindsten International Conference on Artificial Intelligence and Statistics, 3403-3411, 2024 | 7 | 2024 |
| Solving Linear-Gaussian Bayesian Inverse Problems with Decoupled Diffusion Sequential Monte Carlo F Ekström Kelvinius, Z Zhao, F Lindsten ICML 2025, 2025 | 6* | 2025 |
| Autoregressive Diffusion Models with non-Uniform Generation Order F Ekström Kelvinius, F Lindsten ICML 2023 Workshop on Structured Probabilistic Inference {\&} Generative …, 2023 | 2 | 2023 |
| Deep Learning for the Atomic Scale: Graph Neural Networks and Deep Generative Models with Some Applications to Materials and Molecules F Ekström Kelvinius Linköping University Electronic Press, 2025 | | 2025 |
| Graph neural networks for prediction of formation energies of crystals F Ekström | | 2020 |
Fredrik LindstenAssociate Professor, Linköping UniversityVerified email at liu.se
