🌍 What’s next?
Many applications:
- Expanding the Alexandria database 🏛️
- Designing materials with tailored properties 🔬
- Accelerating breakthroughs in energy storage & semiconductors
We’re just getting started!
🏆 Results we’re proud of:
- 8x more likely to generate stable structures than baselines (e.g., PyXtal with charge compensation)
- Fast: 1,000 novel structures/min ⚡
- Control over space group, composition, and stability
- Releasing 3 million compounds generated by the model 📥
Did you know that only 11 convex uniform tilings can perfectly cover a flat surface using regular polygons—where every vertex has the same surroundings?
🖨️ What we printed:
✅ 3 Regular (Platonic) Tilings – Made from a single polygon type: triangle, square, or hexagon.
🚀 Big News!
We’re thrilled to share our latest work: “A Generative Material Transformer using Wyckoff Representation” 🌌
Discover Matra-Genoa – where AI meets Materials Science.
📄 Check out the pre-print: arxiv.org/abs/2501.16051
#AIforScience #GenerativeAI #MaterialsScience
The Maximum Tc of Conventional Superconductors at Ambient Pressure
Through analysis of electron-phonon calculations for over
20000 metals, we critically examine this question.
arxiv.org/abs/2502.18281
Video
Botti-Marques research group
Botti-Marques research group
Botti-Marques research group
Botti-Marques research group
Antonio Sanna
🧪 Why this matters:
Materials are the foundation of modern technology—fueling everything from batteries to semiconductors.
However, generating stable 3D structures near the convex hull is challenging:
- Efficiency ⚡
- Symmetry ⚖️
- Stability 🏔️
Matra-Genoa adresses these challenges.
💡 What makes it unique?
- Fully leverages Wyckoff positions (discrete + continuous parameters)
- Trained across the periodic table & 230 space groups
- Condition on critical properties like stability
✅ 8 Semiregular (Archimedean) Tilings – Combining two or more polygons while maintaining uniformity—each vertex has the same surroundings!
These patterns are key to geometry, architecture, and—most importantly for us—materials science! 🏗️🔬
#3DPrinting #MaterialsScience
