AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

GeoDiff: A Geometric Diffusion Model for Molecular Conformation Generation

ICLR 2022 · Probabilistic and scientific modeling › Molecules and proteins · approach: Diffusion for molecular conformations · 179 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use equivariant diffusion directly on atom coordinatesMolecular conformation generation · GEOM-DrugsCOV-R mean (%): 62.15 -> 89.13Helped
Use equivariant diffusion directly on atom coordinatesMolecular conformation generation · GEOM-QM9MAT-R mean (Å): 0.2673 -> 0.2090Helped
Use the chain-rule objective instead of the alignment objective (ablation)GeoDiff · GEOM-DrugsCOV-R mean (%): 88.36 -> 89.13Helped
Use the chain-rule objective instead of the alignment objective (ablation)GeoDiff · GEOM-QM9MAT-R mean (Å): 0.2104 -> 0.2090Helped
Reduce diffusion steps from 5000 to 1000 (ablation)GeoDiff · GEOM-DrugsCOV-R mean (%): 89.13 -> 82.96Hurt
Add force-field optimization (ablation)GeoDiff · GEOM-DrugsCOV-P mean (%)Helped
Add force-field optimization (ablation)GeoDiff · GEOM-DrugsCOV-R mean (%)Mixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy