A plain causal transformer that tokenizes atom positions in local frames generates 3D molecules directly; RL against an xTB relaxation reward lifts topology-preserving valid yield from ~50% to ~95%.
hub
Pre- diction of physicochemical parameters by atomic contributions.Journal of Chemical Informa- tion and Computer Sciences, 39(5):868–873, 1999
1 Pith paper cite this work, alongside 1,497 external citations. Polarity classification is still indexing.
1
Pith paper citing it
1,497
external citations · OpenAlex
hub tools
fields
physics.comp-ph 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Atomic Design Transformer: Scaffold-Conditioned 3D Molecule Generation via xTB-Reward Reinforcement Learning
A plain causal transformer that tokenizes atom positions in local frames generates 3D molecules directly; RL against an xTB relaxation reward lifts topology-preserving valid yield from ~50% to ~95%.