Research map / Probabilistic and scientific modeling / Molecules and proteins
Crystal Diffusion Variational Autoencoder for Periodic Material 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 CDVAE instead of FTCP for reconstruction | Crystal reconstruction · Perov-5 | RMSE: 0.0259 -> 0.0156 | Helped |
| Use CDVAE instead of FTCP for reconstruction | Crystal reconstruction · Carbon-24 | RMSE: 0.2563 -> 0.1251 | Helped |
| Use CDVAE instead of FTCP for reconstruction | Crystal reconstruction · MP-20 | RMSE: 0.1593 -> 0.0356 | Helped |
| Use CDVAE instead of FTCP for reconstruction | Crystal reconstruction · Perov-5 | match rate (%): 99.34 -> 97.52 | Hurt |
| Use CDVAE instead of FTCP for reconstruction | Crystal reconstruction · Carbon-24 | match rate (%): 62.28 -> 55.22 | Hurt |
| Use CDVAE instead of FTCP for reconstruction | Crystal reconstruction · MP-20 | match rate (%): 69.89 -> 45.43 | Hurt |
| Use CDVAE instead of the strongest reported baseline | Crystal generation · Perov-5 | COV-R (%): 73.92 -> 99.45 | Helped |
| Use CDVAE instead of the strongest reported baseline | Crystal generation · Carbon-24 | COV-R (%): 0.00 -> 99.80 | Helped |
| Use CDVAE instead of the strongest reported baseline | Crystal generation · MP-20 | COV-R (%): 41.93 -> 99.15 | Helped |
| Use CDVAE instead of the strongest reported baseline | Crystal generation · MP-20 | COV-P (%): 99.74 -> 99.49 | No clear effect |
| Use CDVAE instead of FTCP | Property optimization · MP-20 | SR5: 0.02 -> 0.78 | Helped |
| Use CDVAE instead of FTCP | Property optimization · MP-20 | SR10: 0.04 -> 0.86 | Helped |
Closest papers by meaning
- LLM Meets Diffusion: A Hybrid Framework for Crystal Material Generation (NeurIPS 2025 · similarity 0.91)
- All-atom Diffusion Transformers: Unified generative modelling of molecules and materials (ICML 2025 · similarity 0.91)
- WyckoffDiff -- A Generative Diffusion Model for Crystal Symmetry (ICML 2025 · similarity 0.90)
- Periodic Materials Generation using Text-Guided Joint Diffusion Model (ICLR 2025 · similarity 0.90)
- Scalable Diffusion for Materials Generation (ICLR 2024 · similarity 0.90)
- Crystalformer: Infinitely Connected Attention for Periodic Structure Encoding (ICLR 2024 · 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.