Equivariant Neural Diffusion (END) combines a learnable, equivariant forward process with diffusion for 3D molecule generation, improving conditional controllability on QM9 and GEOM-Drugs.
u ller, and Kristof T Sch \
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Equivariant Neural Diffusion for Molecule Generation
Equivariant Neural Diffusion (END) combines a learnable, equivariant forward process with diffusion for 3D molecule generation, improving conditional controllability on QM9 and GEOM-Drugs.