Bipartite Cholesky Graph Networks from density-fitted ERI decomposition achieve 0.0296 Ha in-distribution MAE on six diatomic molecules under FCI reference, outperforming compressed-integral baselines, with generalization tied to orbital environment similarity.
A Universal Framework for Accurate and Efficient Geometric Deep Learning of Molecular Systems
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Fine-tuned LLaMA 3 achieves regression performance on QM9 molecular properties and 28 materials properties from composition strings that rivals random forests but is 5-10x worse than specialized models using atomic coordinates.
citing papers explorer
-
Bipartite Cholesky Graph Networks for Many-Body Quantum Chemistry
Bipartite Cholesky Graph Networks from density-fitted ERI decomposition achieve 0.0296 Ha in-distribution MAE on six diatomic molecules under FCI reference, outperforming compressed-integral baselines, with generalization tied to orbital environment similarity.
-
Regression with Large Language Models for Materials and Molecular Property Prediction
Fine-tuned LLaMA 3 achieves regression performance on QM9 molecular properties and 28 materials properties from composition strings that rivals random forests but is 5-10x worse than specialized models using atomic coordinates.