Han Yang 杨涵

Senior Researcher at Microsoft Research AI4Science. Ph.D. in Chemistry from the University of Chicago.

[Han Yang 杨涵 @HanYangChicago]

Excited to share our latest development, MatterSim: A Deep Learning Atomistic Model Across Elements, Temperatures and Pressures. Check it out 👉https://t.co/g6dOMMDtVN https://t.co/B0BKPcA8n0 #MicrosoftResearch #AI #DeepLearning #MaterialScience
@luzihen

[Kairos Materials @KairosMaterials]

Kairos Materials releases ELEMENTA, a large-scale materials dataset featuring 210M DFT-labeled configurations, 9.7M+ polymorphs, 1.9M chemical compositions and 4.7M+ spin samples.
https://t.co/rOpFMAyjYa
https://t.co/vv1MQqxFJb
https://t.co/v7f0TfkhIm

#AI4Science #AI4Materials

[Robert Pinsler @rpinsler]

We are significantly expanding to accelerate our ambitious plans for AI-driven materials discovery at @MSFTResearch AI for Science. Looking for a Data Engineer, ML Engineer and Applied Scientist (UK/NL/DE).

⬇️See job postings below ⬇️

[Gregor Simm @gncsimm]

MLFFs 🤝 Polymers — SimPoly works!

Our team at @MSFTResearch AI for Science is proud to present SimPoly (SIM-puh-lee) — a deep learning solution for polymer simulation.

Polymeric materials are foundational to modern life—found in everything from the clothes we wear and the food we consume to high-performance materials in aerospace, electronics, and medicine. Today, we introduce a new way to simulate them.

We built a machine learning force field (MLFF) to predict macroscopic properties across a broad range of polymers—trained only on quantum-chemical data, with no experimental fitting. Specifically, we accurately compute polymer densities via large-scale MD simulations, achieving higher accuracy than classical force fields. We also capture second-order phase transitions, enabling prediction of glass transition temperatures. These two properties are fundamental to processing and application design. Finally, we created a benchmark based on experimental data for 130 polymers plus an accompanying quantum-chemical dataset—laying the foundation for a fully in silico design pipeline for next-generation polymeric materials.

The incredible team: Jean Helie, @temporaer, Yicheng Chen, Guillem Simeon, @a_kzna, @ErnestoCheco, @erunzzz, Gabriele Tocci, @chc273, @yatao_li, @SherryLixueC, @zunwang_msr, Bichlien H. Nguyen, Jake A. Smith, and Lixin Sun.

📄 Preprint: https://t.co/CfFTJJA0nk
⚙️ Data and code release: in progress⏳

#MLFFs #Polymers #AIforScience #DeepLearning #SimPoly #ScientificML #Microsoft #MicrosoftResearch #MicrosoftQuantum

[Tian Xie @xie_tian]

🚨We are hiring! 🚨 Want to join a highly talented, collaborative team and build the next frontier model for materials design? Apply to the following roles and join our materials team at @MSFTResearch AI for Science. Location can be Cambridge UK or Amsterdam NL or Berlin DE.

Senior Researcher in Deep Learning: https://t.co/WzwWJNpRFq
Senior Applied Scientist: https://t.co/RdTyynFsOE
Senior Research Engineer on Data: https://t.co/bBvvRA2Phc
Senior Research Software Development Engineer(w/ our engineering team): https://t.co/ywcGBrGANB

[Tian Xie @xie_tian]

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 training and inference code of MatterGen under MIT license. Look forward to seeing how the community will use the tool and build on top of it.

[Tian Xie @xie_tian]

Great to be back to Boston for @Materials_MRS MRS Fall 2024. I will give a talk at symposium MT04 on Wednesday 1:30pm about our efforts to build foundational AI capabilities for materials design at @MSFTResearch AI for Science. Look forward to meeting old and new friends in the coming week! #F24MRS

[Han Yang 杨涵 @HanYangChicago]

We are glad to announce that we are releasing MatterSim-V1 for public use today. We look forward to hearing your feedback after trying out our models.
We are actively working on developing more pre-trained models for MatterSim. Please stay tuned for updates.

[Microsoft Research @MSFTResearch]

We're thrilled to announce the release of MatterSimV1-1M and MatterSimV1-5M on GitHub. These cutting-edge models are now available for researchers, developers, and innovators to explore, customize and build upon. https://t.co/AiImSAWDGV

[Han Yang 杨涵 @HanYangChicago]

@FrankNoeBerlin Congrats, Frank! Well deserved!

[Han Yang 杨涵 @HanYangChicago]

@luzihen @MSFTResearch Thank you @jrib_, for developing this invaluable benchmark leaderboard that has significantly contributed to our community. Your assistance in integrating MatterSim's results into the leaderboard is also greatly appreciated.

[Han Yang 杨涵 @HanYangChicago]

Exciting news! MatterSim has officially claimed the #1 spot on the #MatBench Discovery leaderboard https://t.co/DeL32uUB3a.
MatterSim is a SOTA #machinelearning force field for materials simulation, discovery and more https://t.co/g6dOMMDtVN. @luzihen
#AI4Science @MSFTResearch

[Han Yang 杨涵 @HanYangChicago]

@_YunyangLI @iclr_conf Congrats! Well deserved!

[Tian Xie @xie_tian]

[1/N] Generative AI has revolutionized how we create text and images. How about designing novel materials? We at @MSFTResearch #AI4Science are thrilled to announce MatterGen: our generative model that enables broad property-guided materials design.
👇
https://t.co/wDExZ3zWcd

[Claudio Zeni @ICML @zany_cloud]

New 📰 alert
At @MSFTResearch AI4Science and @MSFTQuantum we explored #GPT4 's ability to tackle scientific discovery tasks, with interesting results.

Link 👇
https://t.co/OIpeA33xB9

#LLM #AI4SCIENCE #Materials #Science #Chemistry #PDE #Biology

[Han Yang 杨涵 @HanYangChicago]

@nanophononics Congratulations!!

[Arpan Kundu @Arpan__Kundu]

Checkout our latest work on organic molecular crystals @jctc_papers . @GalliGroup We tested the state-of-the art first principles methods for electron-phonon interactions using https://t.co/fvdeTcgkj3, https://t.co/fgh6VeLkpa, https://t.co/9nIEJoSik0.
https://t.co/Bj4XXczzPw

[Chi Chen @chc273]

Happy to share a free copilot in the chemistry and materials science space.

It’s been a great journey building on Microsoft’s copilot stack, and turning a simple demo to a public web service

https://t.co/EBFm8zNoui

[Han Yang 杨涵 @HanYangChicago]

@jlischner597 2) Train on diverse, large datasets and apply to new systems. I'm eager to see the model's performance in the second scenario, as it could result in a surrogate for linear response calculations if successful.

[Han Yang 杨涵 @HanYangChicago]

@jlischner597 Thanks Johannes for your reply. I'm discussing two transferability scenarios: 1) Train affordably on small systems, then apply to costly large systems. However, the model accumulates errors as system size grows, as mentioned in the paper. I guess further optimization might help.