Research map / Image generation / Autoregressive and latent generation
Towards Symmetry-Aware Generation of Periodic Materials
Youzhi Luo, Chengkai Liu, Shuiwang Ji
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use distance score matching instead of coordinate score matching (ablation) | SyMat · Perov-5 | COV-R: 97.46 -> 99.68 | Improved |
| use distance score matching instead of coordinate score matching (ablation) | SyMat · Perov-5 | COV-P: 95.32 -> 98.64 | Improved |
| use distance score matching instead of coordinate score matching (ablation) | SyMat · Carbon-24 | COV-R: 96.72 -> 100.00 | Improved |
| use distance score matching instead of coordinate score matching (ablation) | SyMat · Carbon-24 | COV-P: 93.44 -> 97.59 | Improved |
| use distance score matching instead of coordinate score matching (ablation) | SyMat · MP-20 | COV-R: 94.25 -> 98.97 | Improved |
| use distance score matching instead of coordinate score matching (ablation) | SyMat · MP-20 | COV-P: 95.61 -> 99.97 | Improved |
| SyMat vs CDVAE: symmetry-aware generation | SyMat · Perov-5 random generation | COV-P: 98.93 -> 98.64 | Hurt |
| SyMat vs CDVAE: symmetry-aware generation | SyMat · Perov-5 random generation | energy EMD: 0.0264 -> 0.2364 | Hurt |
| SyMat vs CDVAE: symmetry-aware generation | SyMat · MP-20 random generation | element-count EMD: 1.432 -> 0.5067 | Improved |
| SyMat vs CDVAE: symmetry-aware generation | SyMat · Perov-5 property optimization | SR5: 0.52 -> 0.73 | Improved |
| SyMat vs CDVAE: symmetry-aware generation | SyMat · MP-20 property optimization | SR5: 0.78 -> 0.92 | Improved |
| SyMat vs CDVAE: symmetry-aware generation | SyMat · MP-20 reconstruction | atom type match rate: 68.32 -> 72.10 | Improved |
Closest papers by meaning
- Generating Symmetric Materials using Latent Flow Matching (NeurIPS 2026 · similarity 0.93)
- SymmCD: Symmetry-Preserving Crystal Generation with Diffusion Models (ICLR 2025 · similarity 0.92)
- WyckoffDiff -- A Generative Diffusion Model for Crystal Symmetry (ICML 2025 · similarity 0.90)
- LLM Meets Diffusion: A Hybrid Framework for Crystal Material Generation (NeurIPS 2025 · similarity 0.89)
- Wyckoff Transformer: Generation of Symmetric Crystals (ICML 2025 · similarity 0.88)
- Periodic Materials Generation using Text-Guided Joint Diffusion Model (ICLR 2025 · 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.
