Score: 2

Equivariant Neural Diffusion for Molecule Generation

Published: June 12, 2025 | arXiv ID: 2506.10532v1

By: François Cornet , Grigory Bartosh , Mikkel N. Schmidt and more

Potential Business Impact:

Builds new molecules that fit perfectly.

Business Areas:
Nanotechnology Science and Engineering

We introduce Equivariant Neural Diffusion (END), a novel diffusion model for molecule generation in 3D that is equivariant to Euclidean transformations. Compared to current state-of-the-art equivariant diffusion models, the key innovation in END lies in its learnable forward process for enhanced generative modelling. Rather than pre-specified, the forward process is parameterized through a time- and data-dependent transformation that is equivariant to rigid transformations. Through a series of experiments on standard molecule generation benchmarks, we demonstrate the competitive performance of END compared to several strong baselines for both unconditional and conditional generation.

Country of Origin
🇳🇱 🇩🇰 Denmark, Netherlands

Page Count
26 pages

Category
Computer Science:
Machine Learning (CS)