Research map / Image generation / Autoregressive and latent generation
MDM: Molecular Diffusion Model for 3D Molecule Generation
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Use dual equivariant encoders for local and global interatomic relations | MDM versus EDM · QM9 | validity (%): 91.7 -> 98.6 | Helped |
| Use dual equivariant encoders for local and global interatomic relations | MDM versus EDM · GEOM | validity (%): 68.6 -> 99.5 | Helped |
| Add the variational controlling variable and its loss (ablation) | MDM · QM9 | uniqueness (%): 91.6 -> 94.6 | Helped |
| Add the variational controlling variable and its loss (ablation) | MDM · QM9 | novelty (%): 80.1 -> 90.0 | Helped |
| Add the variational controlling variable and its loss (ablation) | MDM · GEOM | uniqueness (%): 99.5 -> 99.0 | Hurt |
| Add the variational controlling variable and its loss (ablation) | MDM · GEOM | stability (%): 42.3 -> 62.2 | Helped |
| Condition generation on target properties with MDM rather than EDM | MDM · QM9 conditional generation | MAE (ε_gap): 0.655 -> 0.044 | Helped |
| Condition generation on target properties with MDM rather than EDM | MDM · QM9 conditional generation | MAE (μ): 1.111 -> 1.177 | Hurt |
| Condition generation on target properties with MDM rather than EDM | MDM · QM9 conditional generation | MAE (C_v): 1.101 -> 1.647 | Hurt |
Closest papers by meaning
- Geometric-Facilitated Denoising Diffusion Model for 3D Molecule Generation (AAAI 2024 · similarity 0.92)
- Navigating the Design Space of Equivariant Diffusion-Based Generative Models for De Novo 3D Molecule Generation (ICLR 2024 · similarity 0.91)
- NExT-Mol: 3D Diffusion Meets 1D Language Modeling for 3D Molecule Generation (ICLR 2025 · similarity 0.90)
- Enhancing Generalizability in Molecular Conformation Generation with METRIZATION-Informed Geometric Diffusion Pretraining (AAAI 2025 · similarity 0.90)
- Towards Unified and Lossless Latent Space for 3D Molecular Latent Diffusion Modeling (NeurIPS 2025 · similarity 0.90)
- Straight-Line Diffusion Model for Efficient 3D Molecular Generation (NeurIPS 2025 · similarity 0.89)
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.