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.
Deep reinforcement learning for de novo drug design.Science advances, 4(7):eaap7885
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2roles
background 1polarities
background 1representative citing papers
SGRPO is a GRPO-style framework that constructs set-level diversity rewards via supergroup sampling and leave-one-out redistribution to expand the utility-diversity Pareto frontier in biomolecular design tasks.
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.
-
Pushing Biomolecular Utility-Diversity Frontiers with Supergroup Relative Policy Optimization
SGRPO is a GRPO-style framework that constructs set-level diversity rewards via supergroup sampling and leave-one-out redistribution to expand the utility-diversity Pareto frontier in biomolecular design tasks.