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.
Zhenqin Wu, Bharath Ramsundar, Evan N
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
Gradient matching empirically recovers implicit regularization effects such as l2 penalties from early stopping and dropout in neural networks.
Geo-Strat-RL applies RLVR in a synthetic geological generator-verifier setup to boost VLM stratigraphic reasoning scores and shows transfer to synthetic seismic data without domain-specific training.
A Latent NCDE-based continuous-time probabilistic corrector wrapped around deterministic physics propagators like GMAT improves forecast accuracy and produces sharp calibrated full-covariance uncertainty estimates on real CDDIS data for 2-4 day horizons.
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.
-
Estimating Implicit Regularization in Deep Learning
Gradient matching empirically recovers implicit regularization effects such as l2 penalties from early stopping and dropout in neural networks.
-
Geo-Strat-RL: Learning Geological Event Reasoning from Verifiable Tasks
Geo-Strat-RL applies RLVR in a synthetic geological generator-verifier setup to boost VLM stratigraphic reasoning scores and shows transfer to synthetic seismic data without domain-specific training.
-
Continuous-Time Probabilistic Correctors for Uncertainty-Aware Physics-Based Spacecraft Trajectory Forecasting
A Latent NCDE-based continuous-time probabilistic corrector wrapped around deterministic physics propagators like GMAT improves forecast accuracy and produces sharp calibrated full-covariance uncertainty estimates on real CDDIS data for 2-4 day horizons.