Equivariant Neural Diffusion for Molecule Generation

François Cornet, Grigory Bartosh, Mikkel N Schmidt, C. A. Naesseth
2/10/2026

No official code found. Best implementation: frcnt/equivariant-neural-diffusion (9 stars, MIT, last commit 2025-04-21).

Abstract

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.

View on arXivView PDF

Code Implementations(1)

frcnt/equivariant-neural-diffusionCommunity100%
MIT

[NeurIPS 2024] Equivariant Neural Diffusion for Molecule Generation

90PythonOct 30, 20241 years agoMIT
diffusion-modelsmolecule-generation

Similar Papers

NExT-Mol: 3D Diffusion Meets 1D Language Modeling for 3D Molecule Generation

87% match1 repo932026

Frame-based Equivariant Diffusion Models for 3D Molecular Generation

86% match2025

Navigating the Design Space of Equivariant Diffusion-Based Generative Models for De Novo 3D Molecule Generation

86% match1 repo142026

Straight-Line Diffusion Model for Efficient 3D Molecular Generation

85% match1 repo22025

D3MES: Diffusion Transformer with multihead equivariant self-attention for 3D molecule generation

85% match1 repo122025

LDMol: A Text-to-Molecule Diffusion Model with Structurally Informative Latent Space Surpasses AR Models

85% match1 repo252026

Cite this paper

@article{cornet2026equivariant,
  title  = {Equivariant Neural Diffusion for Molecule Generation},
  author = {François Cornet and Grigory Bartosh and Mikkel N Schmidt and C. A. Naesseth},
  year   = {2026},
  eprint = {2506.10532},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/2506.10532},
  journal = {NEURIPS 2025 2025}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2506.10532.svg)](https://codeofpaper.com/paper/2506.10532)

Discussion