Research map / Image generation / Autoregressive and latent generation
Coarse-to-Fine: a Hierarchical Diffusion Model for Molecule Generation in 3D
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 coarse-to-fine fragment generation instead of atom-level EDM | 3D molecule generation · GEOM_DRUG conformations | COV (atom): 0.489 -> 0.546 | Helped |
| Use coarse-to-fine fragment generation instead of atom-level EDM | 3D molecule generation · GEOM_DRUG conformations | MAT (atom): 1.349 -> 1.121 | Helped |
| Use coarse-to-fine fragment generation instead of atom-level EDM | 3D molecule generation · GEOM_DRUG conformations | COV (frag): 0.097 -> 0.202 | Helped |
| Use property-based instead of element-based coarse features | HierDiff · GEOM_DRUG | QED: 0.632 -> 0.639 | Helped |
| Use property-based instead of element-based coarse features | HierDiff · CrossDocked2020 | RA: 0.574 -> 0.262 | Hurt |
| Remove iterative refinement (ablation) | HierDiff · GEOM_DRUG | QED | Hurt |
| Remove iterative refinement (ablation) | HierDiff · GEOM_DRUG | MCF | Hurt |
| Generate drug-size molecules with non-autoregressive HierDiff rather than autoregressive G-SphereNet | 3D molecule generation · GEOM_DRUG | Delta MW: 170.7 -> 13.33 | Helped |
Closest papers by meaning
- Equivariant Blurring Diffusion for Hierarchical Molecular Conformer Generation (NeurIPS 2024 · similarity 0.93)
- Navigating the Design Space of Equivariant Diffusion-Based Generative Models for De Novo 3D Molecule Generation (ICLR 2024 · similarity 0.90)
- Geometric-Facilitated Denoising Diffusion Model for 3D Molecule Generation (AAAI 2024 · similarity 0.89)
- Conditional Synthesis of 3D Molecules with Time Correction Sampler (NeurIPS 2024 · similarity 0.89)
- NExT-Mol: 3D Diffusion Meets 1D Language Modeling for 3D Molecule Generation (ICLR 2025 · similarity 0.88)
- Scalable Diffusion for Materials Generation (ICLR 2024 · similarity 0.88)
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.