Chem-GMNet uses sphere-native embeddings, DualSKA attention, and SH-FFN layers to match or beat ChemBERTa-2 on MoleculeNet tasks with fewer parameters and sometimes no pretraining.
Boris Bonev, Thorsten Kurth, Tom Kölbl, et al
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Low loadings of CeO2MnOx heterostructures on Vulcan XC-72 carbon achieve up to 90% selectivity for H2O2 via the 2e- ORR in RRDE tests.
citing papers explorer
-
Chem-GMNet: A Sphere-Native Geometric Transformer for Molecular Property Prediction
Chem-GMNet uses sphere-native embeddings, DualSKA attention, and SH-FFN layers to match or beat ChemBERTa-2 on MoleculeNet tasks with fewer parameters and sometimes no pretraining.
-
Influence of CeO$_2$MnO$_x$ heterostructure on Hydrogen Peroxide Electrogeneration on Carbon-Based Catalysts
Low loadings of CeO2MnOx heterostructures on Vulcan XC-72 carbon achieve up to 90% selectivity for H2O2 via the 2e- ORR in RRDE tests.