QT-Net predicts atomic electron populations and multipoles via a new SOAP-cluster held-out test, improving molecular property prediction and recovering QM9 dipole moments from per-atom outputs.
BOOM: Benchmarking out-of-distribution molecular property predictions of machine learning models
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
fields
cs.LG 3years
2026 3verdicts
UNVERDICTED 3roles
background 2representative citing papers
FORGE reformulates molecular optimization as context-aware fragment ranking and replacement using mined low-to-high edit pairs, outperforming larger language models and graph methods on standard benchmarks.
A new benchmark finds that state-of-the-art ML interatomic potentials struggle with compositional generalization, producing errors an order of magnitude higher on unseen molecular combinations than on training-like cases.
citing papers explorer
-
QT-Net: Rethinking Evaluation of AI Models in Atomic Chemical Space
QT-Net predicts atomic electron populations and multipoles via a new SOAP-cluster held-out test, improving molecular property prediction and recovering QM9 dipole moments from per-atom outputs.
-
FORGE: Fragment-Oriented Ranking and Generation for Context-Aware Molecular Optimization
FORGE reformulates molecular optimization as context-aware fragment ranking and replacement using mined low-to-high edit pairs, outperforming larger language models and graph methods on standard benchmarks.
-
Benchmarking Compositional Generalisation for Machine Learning Interatomic Potentials
A new benchmark finds that state-of-the-art ML interatomic potentials struggle with compositional generalization, producing errors an order of magnitude higher on unseen molecular combinations than on training-like cases.