🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

1/ How do we weigh the contributions of different spectra when probing local structure + chemistry? In our new paper (npj Computational Materials), we used interpretable ML to study XANES and PDF spectra for property inversion in TM oxides. 🔗 nature.com/articles/s4152… 🧵

Our work on the intrinsic & extrinsic (dopant) defect chemistry of trigonal Selenium, for indoor and tandem PV solar cells, is now published. Check out the thread below for a quick summary and the article link!

TorchSim makes optimal use of GPUs—go check out the new features in v0.2!

We have released an eSEN model that is the current SOTA on Matbench-Discovery. Code/checkpoints are available for both non-commercial and commercial use: code: github.com/facebookresear… checkpoint: huggingface.co/facebook/OMAT24 paper (updated): arxiv.org/abs/2502.12147

Excited for the release of our EGIP model! Pushing the boundaries of efficiency and accuracy 🚀

ML-first materials are here: we demonstrate that machine learning approaches to materials prediction achieves state-of-the-art accuracy and best-in-class efficiency and performance. Adeesh Kolluru is leading the charge Radical AI

The momentum we have Radical AI right now is incredible…if you are looking to build technology that impacts the entire human race, we are hiring. Please reach out .

Cool feature! Great to see that Matbench Discovery is pushing the community to improve the accuracy of machine learning force fields 🔥

One of the research works I'm most proud of, fantastic teamwork! Anders Johansson Chuin Wei Tan Cameron J. Owen Boris Kozinsky

Excited to see our AI model for electric fields featured by Harvard Harvard SEAS ! 🚀 Link to paper 👉 nature.com/articles/s4146… seas.harvard.edu/news/2025/06/m…

Very proud of this work — pushing the boundaries of AI for materials modelling! 🔥

doped (3.1.0) and ShakeNBreak (3.4.2) have had new releases! - Streamlined chemical potential handling - Auto-compatibility checks w/competing phases calculation settings (as for defects) – common pitfall - Directly parse spin magnetisation (incl SOC) ... github.com/SMTG-Bham/dope…

Matbench Discovery is out in Nature Machine Intelligence @ Paper: rdcu.be/esRFB Leaderboard: …tbench-discovery.materialsproject.org No better time to thank all my co-authors Rhys Goodall, Philipp Benner, Yuan Chiang Yuan (Cyrus) Chiang, Bowen Deng, Mark Asta, Gerbrand Ceder Ceder Group,