We are significantly expanding to accelerate our ambitious plans for AI-driven materials discovery at @msftresearch.bsky.social AI for Science. Looking for a Data Engineer, ML Engineer and Applied Scientist (UK/NL/DE). ⬇️ See job postings below ⬇️
Robert Pinsler
@rpinsler.bsky.social
AI for materials design at Microsoft Research AI for Science | Prev. University of Cambridge. Views are my own.
Skala is now available to everyone! Why are we releasing it? Because we’re not just aiming to publish a cool paper — we’re on a mission to bring DFT to chemical accuracy using deep learning. And to make real progress, we need the community’s feedback. #compchem
Microsoft Research@msftresearch.bsky.social · 10mo agoThe wait is over! Microsoft Research is sharing Skala, the new exchange-correlation functional, marking a major milestone in the accuracy/cost trade-off in DFT. Help us learn from your testing so we can improve. Available on Azure AI Foundry and GitHub. msft.it/6016sFDLY
Job alert! Check out our open roles (Senior Researcher, Senior Applied Scientist, Senior Data Engineer) for AI for materials discovery.
Tian Xie@xie-tian.bsky.social · 10mo ago🚨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.bsky.social AI for Science. Location can be Cambridge UK or Amsterdam NL or Berlin DE.
Incredibly excited to see that Aardvark-Weather is finally out in Nature!! An amazing project with a truly fantastic team. The lead authors Anna Allen and Stratis Markou have worked really really hard to make this project happen. www.nature.com/articles/s41...
End-to-end data-driven weather prediction - Nature
Nature - End-to-end data-driven weather prediction
nature.com
Today we have published BioEmu-Benchmarks (MIT license): a code to evaluate the multi-conformation sampling benchmarks, MD free energy landscape benchmarks, and folding free energy benchmarks shown in the BioEmu-1 paper with BioEmu or your own model. Some details below 🧵 github.com/microsoft/bi...
GitHub - microsoft/bioemu-benchmarks: Benchmarking code accompanying the release of `bioemu`
Benchmarking code accompanying the release of `bioemu` - microsoft/bioemu-benchmarks
github.com
Nature published Microsoft research detailing our WHAM, an AI model that generates video game visuals & controller actions. We're releasing the model weights, sample data & WHAM Demonstrator on Azure AI Foundry to enable researchers to build on this work. www.microsoft.com/en-us/resear...
Check out this great BioEmu talk by @jjimenezluna.bsky.social and @yuxie.bsky.social in the VantAI lecture series. Thank you for hosting @mmbronstein.bsky.social @lucanaef.bsky.social www.youtube.com/watch?v=8vsT...
Emulation of protein equilibrium ensembles with generative deep learning | José Jiménez Luna, Yu Xie
YouTube video by VantAI
youtube.com
⭐️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)
Excited to share the news that MatterGen is published on Nature today. Since the publication of our preprint, we have bee busy improving our evaluation; we have also shown successful exp synthesis! Grateful for the team members for their hard work and perseverance, and #MSR colleagues for support!
Microsoft Research@msftresearch.bsky.social · 2y agoMicrosoft researchers introduce MatterGen, a model that can discover new materials tailored to specific needs—like efficient solar cells or CO2 recycling—advancing progress beyond trial-and-error experiments. www.microsoft.com/en-us/resear...
Super excited to share that MatterGen is published in Nature!
Microsoft Research@msftresearch.bsky.social · 2y agoMicrosoft researchers introduce MatterGen, a model that can discover new materials tailored to specific needs—like efficient solar cells or CO2 recycling—advancing progress beyond trial-and-error experiments. www.microsoft.com/en-us/resear...
MatterGen now published in Nature 🔥 Very strong work from the materials team at MSR AI for Science!
Microsoft Research@msftresearch.bsky.social · 2y agoMicrosoft researchers introduce MatterGen, a model that can discover new materials tailored to specific needs—like efficient solar cells or CO2 recycling—advancing progress beyond trial-and-error experiments. www.microsoft.com/en-us/resear...
Super excited to share that the MatterGen code is now public on GitHub! github.com/microsoft/ma...
GitHub - microsoft/mattergen: Official implementation of MatterGen -- a generative model for inorganic materials design across the periodic table that can be fine-tuned to steer the generation towards...
Official implementation of MatterGen -- a generative model for inorganic materials design across the periodic table that can be fine-tuned to steer the generation towards a wide range of property c...
github.com
Microsoft Research@msftresearch.bsky.social · 2y agoMicrosoft researchers introduce MatterGen, a model that can discover new materials tailored to specific needs—like efficient solar cells or CO2 recycling—advancing progress beyond trial-and-error experiments. www.microsoft.com/en-us/resear...
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.
Microsoft Research@msftresearch.bsky.social · 2y agoMicrosoft researchers introduce MatterGen, a model that can discover new materials tailored to specific needs—like efficient solar cells or CO2 recycling—advancing progress beyond trial-and-error experiments. www.microsoft.com/en-us/resear...
A new diffusion-driven model called MatterGen generates stable inorganic crystals by refining random atom placements. Zeni et al. show it can be steered toward specific properties, opening efficient pathways for materials design. www.nature.com/articles/s41...
📢 Paper + code release 📃💻 After 2 years of work, I'm excited to announce our newest paper, MatterGen, has been published in Nature! www.nature.com/articles/s41... We are also releasing all the training data, model weights, model code, and evaluation code on GitHub! github.com/microsoft/ma...
GitHub - microsoft/mattergen: Official implementation of MatterGen -- a generative model for inorganic materials design across the periodic table that can be fine-tuned to steer the generation towards...
Official implementation of MatterGen -- a generative model for inorganic materials design across the periodic table that can be fine-tuned to steer the generation towards a wide range of property c...
github.com
Microsoft Research@msftresearch.bsky.social · 2y agoMicrosoft researchers introduce MatterGen, a model that can discover new materials tailored to specific needs—like efficient solar cells or CO2 recycling—advancing progress beyond trial-and-error experiments. www.microsoft.com/en-us/resear...
MatterGen is out in Nature! MatterGen is a SOTA generative model for materials design. We also raise the bar for evaluation by considering compositional disorder and experimentally validating model capabilities. Code is open-source! www.nature.com/articles/s41... github.com/microsoft/ma...
GitHub - microsoft/mattergen: Official implementation of MatterGen -- a generative model for inorganic materials design across the periodic table that can be fine-tuned to steer the generation towards...
Official implementation of MatterGen -- a generative model for inorganic materials design across the periodic table that can be fine-tuned to steer the generation towards a wide range of property c...
github.com
Microsoft Research@msftresearch.bsky.social · 2y agoMicrosoft researchers introduce MatterGen, a model that can discover new materials tailored to specific needs—like efficient solar cells or CO2 recycling—advancing progress beyond trial-and-error experiments. www.microsoft.com/en-us/resear...
Excited to talk about MatterGen and MatterSim (now on GitHub!) today at the @cecamevents.bsky.social l workshop at CECAM-HQ in EPFL Lausanne. If you're interested, drop by at 11.15, or let's chat afterwards. 💻 github.com/microsoft/ma... 📄 arxiv.org/abs/2312.03687 📄📄 arxiv.org/abs/2405.04967
GitHub - microsoft/mattersim: MatterSim: A deep learning atomistic model across elements, temperatures and pressures.
MatterSim: A deep learning atomistic model across elements, temperatures and pressures. - microsoft/mattersim
github.com
Another great model from @msftresearch.bsky.social AI for Science - CHIMERA, an accurate retrosynthesis prediction model by @marwinsegler @MaziarzKris and team!
Marwin Segler@marwinsegler.bsky.social · 2y agonew preprint on chemical synthesis ML models - showing how to combine multiple models in a principled way - modern Transformers + GNN to featurize chemical reaction: - new insights in where the models shine + bonus: find the quirky named reaction! Feedback welcome! arxiv.org/abs/2412.05269
new preprint on chemical synthesis ML models - showing how to combine multiple models in a principled way - modern Transformers + GNN to featurize chemical reaction: - new insights in where the models shine + bonus: find the quirky named reaction! Feedback welcome! arxiv.org/abs/2412.05269
Chimera: Accurate retrosynthesis prediction by ensembling models with diverse inductive biases
Planning and conducting chemical syntheses remains a major bottleneck in the discovery of functional small molecules, and prevents fully leveraging generative AI for molecular inverse design. While ea...
arxiv.org
Exciting stuff! will be interesting to test this on our own favourite protein ensembles!
Frank Noe@franknoe.bsky.social · 2y agoSuper excited to preprint our work on developing a Biomolecular Emulator (BioEmu): Scalable emulation of protein equilibrium ensembles with generative deep learning from @msftresearch.bsky.social ch AI for Science. www.biorxiv.org/content/10.1...
Excited to present what we've been up to the last couple years. Introducing BioEmu, a Biomolecular Emulator of protein dynamics: www.biorxiv.org/content/10.1...
Scalable emulation of protein equilibrium ensembles with generative deep learning
Following the sequence and structure revolutions, predicting the dynamical mechanisms of proteins that implement biological function remains an outstanding scientific challenge. Several experimental t...
biorxiv.org
Great progress from @franknoe.bsky.social and collaborators on the protein conformational sampling problem using AI!
Frank Noe@franknoe.bsky.social · 2y agoSuper excited to preprint our work on developing a Biomolecular Emulator (BioEmu): Scalable emulation of protein equilibrium ensembles with generative deep learning from @msftresearch.bsky.social ch AI for Science. www.biorxiv.org/content/10.1...
Super excited to preprint our work on developing a Biomolecular Emulator (BioEmu): Scalable emulation of protein equilibrium ensembles with generative deep learning from @msftresearch.bsky.social ch AI for Science. www.biorxiv.org/content/10.1...
If you are at #F24MRS in Boston today, check out Tian's talk at symposium MT04 at 1:30pm. He will present our efforts to build AI tools for materials design at @msftresearch.bsky.social AI for Science. #materialsscience #machinelearning #mattergen #mattersim
Major announcement from Microsoft, their machine learning matter simulator is now available
Claudio Zeni@claudiozeni.bsky.social · 2y ago🚨Our Machine Learning Force Field Mattersim is now available! 🚨 Check it out here 👇 msft.it/6013oBZLt The force field is designed to be used on a vast range of temperatures and pressures, try it yourself :) Feedback and suggestions are very welcome!
🚨Our Machine Learning Force Field Mattersim is now available! 🚨 Check it out here 👇 msft.it/6013oBZLt The force field is designed to be used on a vast range of temperatures and pressures, try it yourself :) Feedback and suggestions are very welcome!
GitHub - microsoft/mattersim: MatterSim: A deep learning atomistic model across elements, temperatures and pressures.
MatterSim: A deep learning atomistic model across elements, temperatures and pressures. - microsoft/mattersim
msft.it