iiinova — where your digital self keeps evolving

Joe Abbott

@jwasci.bsky.social

PhD Student at Lab COSMO, EPFL, working on surrogate models for DFT.

Joe Abbott @jwasci.bsky.social · 27/08/2025

And also Guillaume talking (very soon at 10:45) in Room 1 about all things metatensor and metatomic - making it easier to develop and use ML models for atomistic simulations 🔥 #psik2025

000

Reposted by Joe Abbott

COSMO Lab @labcosmo.bsky.social · 26/08/2025

If you are at the #psik2025 and want to know more about the #metatensor ecosystem, don't miss @luthaf.bsky.social talk tomorrow morning 9:45 in room 1

021

Joe Abbott @jwasci.bsky.social · 27/08/2025

Come and see my poster "On the importance of symmetry constraints for learning equivariant quantum mechanical properties" at Psi-k this lunchtime, poster B5.01!

010

Reposted by Joe Abbott

COSMO Lab @labcosmo.bsky.social · 27/08/2025

📢 Now out on @physrevx.bsky.social energy, journals.aps.org/prxenergy/ab... from 🧑‍🚀 @dtisi.bsky.social and Hanna Türk, our #PET -powered study of the dynamic reconstruction of LPS surfaces, and how it affects their structure, stability and reactivity.

A cartoon explaining how mild finite-temperature conditions induce disorder and dynamical reconstruction on the surfaces of lithium thiophosphates

194

Reposted by Joe Abbott

COSMO Lab @labcosmo.bsky.social · 22/08/2025

🚨 #machinelearning for #compchem goodies from our 🧑‍🚀 team incoming! After years of work it's time to share. Go check arxiv.org/abs/2508.15704 and/or metatensor.org to learn about #metatensor and #metatomic. What they are, what they do, why you should use them for all of your atomistic ML projects 🔍.

1148

Reposted by Joe Abbott

COSMO Lab @labcosmo.bsky.social · 27/05/2025

📢 Running molecular dynamics with time steps up to 64fs for any atomistic system, from Al(110) to Ala2? Thanks to 🧑‍🚀 Filippo Bigi and Sanggyu Chong, with some help from Agustinus Kristiadis, this is not as crazy as it sounds. Let us briefly introduce FlashMD⚡ arxiv.org/html/2505.19...

Scheme of the GNN architecture of the FlashMD method.

13712

Reposted by Joe Abbott

COSMO Lab @labcosmo.bsky.social · 19/03/2025

📢 PET-MAD has just landed! 📢 What if I told you that you can match & improve the accuracy of other "universal" #machinelearning potentials training on fewer than 100k atomic structures? And be *faster* with an unconstrained architecture that is conservative with tiny symmetry breaking? Sounds like 🧑‍🚀

Polar plot showing the errors of several machine-learning potential of different test sets. Smaller is better here!

Plots showing the evaluation time per atom for several machine-learning potentials as a function of the number of atoms in a simulation. Smaller is better

1289