Tian Xie

It is a rare opportunity to join a highly talented, collaborative team and build the next frontier model for materials design.

Senior Researcher: jobs.careers.microsoft.com/global/en/jo...
Senior Research Engineer: jobs.careers.microsoft.com/global/en/jo...

Want to join our efforts @msftresearch.bsky.social AI for Science to push the frontier of AI for materials? We are the team behind MatterGen & MatterSim and we have 2 job openings! Each can be in Amsterdam, NL, Berlin, DE, or Cambridge, UK.

Today in the journal Science: BioEmu from Microsoft Research AI for Science. This generative deep learning method emulates protein equilibrium ensembles – key for understanding protein function at scale. www.science.org/doi/10.1126/...

Very excited and proud of this incredible team effort!

🚀 After two+ years of intense research, we’re thrilled to introduce Skala — a scalable deep learning density functional that hits chemical accuracy on atomization energies and matches hybrid-level accuracy on main group chemistry — all at the cost of semi-local DFT ⚛️🔥🧪🧬

Huge congrats to our DFT team in achieving the first big milestone towards a universal XC functional. It is a key step towards bridging the gap between computation and experiments for the computational design of molecules and materials.

Illustrated image of Hongxia Hao and Bing Lv. "Abstracts: A Microsoft Research Podcast” runs along the bottom.

Thermal conductivity is critical in modern electronics, but in a post-Moore’s Law world, the need for novel structures that surpass the heat transfer properties of silicon is essential. Learn how AI is helping scientists discover these next-gen materials. msft.it/6013SnPAN

⭐️MatterGen has reached 1K stars on GitHub⭐️

Thanks for giving it a try, we look forward to seeing what you can discover with it!

This is what we discovered so far 🙃 (audio on)

Adding a link to the PDF: rdcu.be/d6qIe

Here is a list of links to read more:

Paper: www.nature.com/articles/s41...
GitHub: github.com/microsoft/ma...
Blog: www.microsoft.com/en-us/resear...
Podcast: www.microsoft.com/en-us/resear...
Story: www.microsoft.com/en-us/resear...

We are working with more partners to bring these AI tools into real-world impact. We also look forward to hearing feedback from you when you try out our tools.

MatterGen is the first demonstration on how generative AI begins to impact how we design novel materials. It will have profound influence on broad domains, including energy storage, carbon capture, and medical imaging.

This introduces an improved approach to evaluate generative model for materials. We have updated all evaluation in the paper and make the whole evaluation pipeline available in our GitHub repo.

Compositional disorder has raised extensive discussion in the community past year. We introduce a new structure matching algorithm that accounts for disorder, and use it redefine novelty and stability.

Compared to our announcement 1 year ago (see copied post), we successfully synthesized a novel material generated by MatterGen and show the experimentally measured property is within 20% of the target -- quite close from an experimental point of view.

x.com/xie_tian/sta...

Excited to finally announce the publication of MatterGen on Nature. MatterGen represents a new paradigm of materials design with generative AI. We are releasing the code of MatterGen under MIT license. Look forward to seeing how the community will use the tool and build on top of it.