AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Distributional Priors Guided Diffusion for Generating 3D Molecules in Low Data Regimes

Haokai Hong, Wanyu Lin, Ming Yang, Kay Chen Tan

AAAI 2026 · Image generation › Autoregressive and latent generation · approach: Equivariant diffusion for 3D molecules · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (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 asymmetric autoencoder (reconstruct full molecule from substructure) instead of symmetric (ablation)GODD · QM9 OOD-II scaffoldsvalidity (%): 35.0 -> 83.3Improved
use asymmetric autoencoder (ablation)GODD · QM9 OOD-I scaffoldsvalidity (%): 58.3 -> 80.0Improved
use asymmetric autoencoder (ablation)GODD · QM9 OOD-I scaffoldsmolecule stability (%): 12.8 -> 45.6Improved
use asymmetric autoencoder (ablation)GODD · QM9 OOD-II scaffoldssuccess rate (%): 31.0 -> 65.8Improved
use asymmetric autoencoder (ablation)GODD · QM9 in-distribution scaffoldsscaffold coverage (%): 98.5 -> 92.5Hurt
use asymmetric autoencoder (ablation)GODD · QM9 in-distribution scaffoldssuccess rate (%): 52.1 -> 52.4No clear effect
add structural priors vs scalar ring-count conditioning (C-EDM etc.)GODD · QM9 OOD ring-structuresuccess rate (%): 25.0 -> 40.5Improved
use GODD instead of fragment-based LinkerNetGODD · QM9 OOD-II scaffoldssuccess rate (%): 53.2 -> 65.8Improved
use GODD instead of LinkerNetGODD · GEOM-LINKER OOD linker designvalidity (%): 48.5 -> 65.2Improved
use unconditional diffusion models (EDM, GeoLDM) for rare scaffoldsEDM/GeoLDM · QM9 OOD-II scaffoldssuccess rate (%): 1.5 vs 65.8 (GODD)Hurt

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