SCOPE-BENCH shows state-of-the-art molecular models suffer up to 8x higher errors under extreme OOD, while POMA reduces mean absolute error by up to 11.2% via target-aware source selection and dual-scale adaptation.
E (n) equivariant graph neural networks
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
PIEGraph augments a spring-mass particle model with an equivariant GNN and novel action representation to predict accurate object dynamics for robotic manipulation from few interactions.
Equivariant mesh networks with anatomical priors and augmented message passing deliver stable segmentation across edge, vertex, and face supervision while resisting geometric perturbations.
citing papers explorer
-
Rethinking Molecular OOD Generalization via Target-Aware Source Selection
SCOPE-BENCH shows state-of-the-art molecular models suffer up to 8x higher errors under extreme OOD, while POMA reduces mean absolute error by up to 11.2% via target-aware source selection and dual-scale adaptation.
-
Learning Equivariant Neural-Augmented Object Dynamics From Few Interactions
PIEGraph augments a spring-mass particle model with an equivariant GNN and novel action representation to predict accurate object dynamics for robotic manipulation from few interactions.
-
Augmented Equivariant Mesh Networks for Anatomical Segmentation
Equivariant mesh networks with anatomical priors and augmented message passing deliver stable segmentation across edge, vertex, and face supervision while resisting geometric perturbations.