←
Gregor Simm45 posts
Gregor Simm avatar

Gregor Simm

@gncsimm

I’m a Senior Researcher and Project Lead at Microsoft Research, working within the AI for Science initiative. My research focuses on geometric deep learning and

◷ Joined March 2017▧ 3 Photos and videos
Gregor Simm avatar
Gregor Simm@gncsimm·17 Oct 2025

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: arxiv.org/abs/2510.13696 ⚙️ Data and code release: in progress⏳ #MLFFs #Polymers #AIforScience #DeepLearning #SimPoly #ScientificML #Microsoft #MicrosoftResearch #MicrosoftQuantum

Post attachment
Paris Perdikaris avatar
⟳ Gregor Simm retweeted
Paris Perdikaris@ParisPerdikaris·22 May 2024

Excited to introduce Aurora: a foundation model of the atmosphere.  In <1min, Aurora produces 5-day global air pollution predictions and 10-day high-resolution weather forecasts that outperform SOTA classical simulation tools and the best specialized deep learning models… 1/n

Post attachment
Tian Xie avatar
⟳ Gregor Simm retweeted
Tian Xie@xie_tian·7 Dec 2023

[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. 👇 arxiv.org/abs/2312.03687

Rianne van den Berg avatar
⟳ Gregor Simm retweeted
Rianne van den Berg@vdbergrianne·30 Nov 2023

📢New internship opening at AI4Science in Amsterdam or Berlin!📢 For our interdisciplinary team working on electronic structure and deep learning, we are looking for someone to join us and work on synthetic data generation and curation. Please apply here! jobs.careers.microsoft.com/g…

Austin Tripp avatar
⟳ Gregor Simm retweeted
Austin Tripp@austinjtripp·3 Sep 2023

For those of you interested in molecular design, our docking package "dockstring" is now easier to install than ever! Just type "conda install -c conda-forge dockstring" or "pip install dockstring" to start calculating docking scores! @gncsimm @jmhernandez233

Johannes Brandstetter avatar
⟳ Gregor Simm retweeted
Johannes Brandstetter@jo_brandstetter·8 Mar 2023

Happy that we can finally share our codebase. Thanks to @rejuvyesh and @djjruhe :) Geometric layers will be included soon. microsoft.github.io/clifford…

Post attachment

New work on how to construct neural network layers on composite objects of scalars, vectors, bivectors, … --> multivectors! Via Clifford algebras, we generalize convolution and Fourier transforms to multivectors, especially relevant for PDE modeling: arxiv.org/abs/2209.04934

Gregor Simm avatar
Gregor Simm@gncsimm·16 Jun 2022

Efficient higher order message passing is all you need! With @IlyesBatatia, @davkovacs10, Christoph Ortner, and Gabor Csanyi.

⚡️MACE: Efficient Higher Order Equivariant Force Fields⚡️ Is equivariance necessary for creating SOTA force fields? With @IlyesBatatia and @gncsimm we introduce a new model MACE matching / exceeding the SOTA on standard benchmarks rMD17, 3BPA arxiv.org/abs/2206.07697 Thread👇👇