4 papers
Atomic Design Transformer: Scaffold-Conditioned 3D Molecule Generation via xTB-Reward Reinforcement Learning
Takao Kotani
We present an SE(3)-invariant transformer for 3D-molecule generation, the Atomic Design Transformer (ADT). ADT places atoms one at a time, autoregressively. SE(3) invariance is ach…
Atomic Design Transformer: xTB-Validated 3D Molecule Generation from Scaffolds
Takao Kotani
We present an SE(3)-invariant transformer for 3D-molecule generation, the Atomic Design Transformer (ADT). ADT places atoms one at a time, autoregressively. The SE(3) invariance is…
Machine Learning Band Gap Predictions: Linking Quasiparticle Self-Consistent GW and LDA-Derived Partial Density of States
Shota Tankano, Takao Kotani, Masao Obata +3
Accurately calculating band gaps for given crystal structures is highly desirable. However, conventional first-principles calculations based on density functional theory (DFT) with…
Efficient implementation of the quasiparticle self-consistent method on GPU
Masao Obata, Takao Kotani, Tatsuki Oda
We have developed a multi-GPU version of the quasiparticle self-consistent (QSGW), a cutting-edge method for describing electronic excitations in a first-principles approach.…