Harvard School of Engineering and Applied Sciences seeks junior faculty applicants for tenure-track materials scientists - both computations and experiments. Applications will be reviewed starting on Nov 15. Please spread the word!
academicpositions.harvard.ed…
Wide-ranging dinner discussions on science, policy, and ice cream with engineering grandmasters: Gang Chen, @zhigangsuo , John Hutchinson, Venky Narayanamurti, and Joost Vlassak. It's a great pleasure to host Gang as colloquium speaker at Harvard SEAS today!
Beyond happy and very honored to receive my tenure promotion at Harvard @hseas. Most grateful to all my colleagues and collaborators, especially the amazing members of our @Materials_Intel group, whose work made this possible. Now the fun begins😀
Boris Kozinsky retweeted
NequIP architecture from @Materials_Intel + compute, data & brains @Google = another leap in accuracy, this time in the universe of all known materials.
Replying to @simonbatzner
When evaluated on @jrib_'s MatBenchDiscovery, the model again does well (note that we only eval'ed on this long after the potential was trained, we never explicitly tried to optimize for this).
Boris Kozinsky retweeted
NequIP potentials trained at scale @GoogleDeepMind: GNoME models discover 2.2M (380,000 stable) crystals, expanding the space of materials known to humanity (OQMD+MaterialsProject+WBM) by x10! Already 736 of these materials synthesized by LBNL and others.
dpmd.ai/GNoME-AI
Boris Kozinsky retweeted
Today in @Nature, our team at @GoogleDeepMind is excited to share GNoME, a deep learning system that increases the number of stable crystal materials known to humanity by an order of magnitude.
From the data, we train a ML force-field with unprecedented capabilities at scale👇
Introducing GNoME: an AI tool that helped discover 2.2 million new crystals. 💎
Crystals are found in everything from the chips powering our phones to solar cells creating clean energy.
The model also better predicts the stability of new materials. 🧵 dpmd.ai/GNoME-AI
Boris Kozinsky retweeted
Fantastic presentation on Allegro to an overfilled hall at the ACM Gordon Bell Prize session at SuperComputing ‘23. Monumental achievement by PhD students Alby Musaelian, Anders Johansson & Simon Batzner, who were nominated for the top prize in the field of scientific computing!
Very honored to be elected an APS Fellow and very grateful to students and collaborators for their work and support! @APSphysics #physics buff.ly/46AmQVb
Boris Kozinsky retweeted
Looking forward to a week of chemistry at #ACSFall2023. Check out our three invited and four contributed presentations on accelerated MD for catalysis, surface reconstructions, battery solvents, coarse graining, and ML DFT functionals.
Boris Kozinsky retweeted
We are thrilled that Allegro was selected as one of the finalists for this year's "Nobel Prize for Supercomputing", the ACM Gordon Bell Prize. Congratulations to the team, pictured here happily finalizing the submission. arxiv.org/abs/2304.10061
Boris Kozinsky retweeted
FLARE is powering simulation AI on Microsoft Azure Quantum, with AiiDA... Hope we get new materials faster! Thanks to amazing developers at MIR: Jon Vandermause, Yu Xie, Anders Johansson, Steven Torrisi, Lixin Sun, Andrea Cepellotti, Simon Batzner, Cameron Owen, David Lim.
I was just dreaming of this when designing and prototyping the AiiDA framework at Bosch Research back in 2009, and in collaboration with EPFL from 2012... It's now here, congrats to the AiiDA team! #Bosch #EPFL #MicrosoftAzure quantum.microsoft.com/en-us/…
Boris Kozinsky retweeted
Ever wondered what 44 million atoms look like? This is a simulation of every single atom in an HIV protein, running on a supercomputer newscientist.com/article/237…
Boris Kozinsky retweeted
Congrats to Yu for passing her defense! 🍻 @YuuuXie
Boris Kozinsky retweeted
Check our new preprint on large-scale biomolecular dynamics! Our Allegro model demonstrates its potential of tackling the HIV capsid with 44 million atoms 🎉 Shout out to the Allegro team Albert Musaelian, Anders Johansson @ndrsjhnssn , and Simon Batzner @simonbatzner 🎉
This quoted post is unavailable.
Boris Kozinsky retweeted
Our new ML-driven CIDER exchange functional scales to hundreds of atoms and improves molecular properties and band gaps over semi-local DFT. See highlights below, and check out our talk at APS next week! 👇
arxiv.org/abs/2303.00682
meetings.aps.org/Meeting/MAR…
(1/3) #compchem
Boris Kozinsky retweeted
Check our new preprint on the benchmarking dataset of transition metals and performance comparison of machine learning force fields👇
🚨How well do machine-learned force fields perform across the transition metals?🚨 Today, we provide a preprint (arxiv.org/abs/2302.12993) discussing our TM23 benchmark dataset (to be released in the near future) and the accuracy of FLARE and NequIP models across this space. 🧵
Boris Kozinsky retweeted
Allegro was selected as an Editor's Highlight in Nature Communications: nature.com/collections/wtpqp…
Our Allegro work is now published in @NatureComms 🎉
Allegro is as a step towards simulations that are truly predictive of experiment - a new combination of scale, speed, and accuracy.
Paper: nature.com/articles/s41467-0…
Blog: go.nature.com/3wPcSPw
Code: github.com/mir-group/allegro

















