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

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

Just before my last week in @labcosmo.bsky.social. Our metatensor and metatomic paper is out! A collection of the hard work we’ve done at @labcosmo.bsky.social to make atomistic machine learning easier to use for experts and not alike.

🚨 #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 🔍.

Filippo Bigi, et al.: Metatensor and metatomic: foundational libraries for interoperable atomistic machine learning https://arxiv.org/abs/2508.15704 https://arxiv.org/pdf/2508.15704 https://arxiv.org/html/2508.15704

You can also use anything you can call from torch, including other tools from the #metatensor ecosystem, such as metatensor.github.io/featomic, and of course you can then use this with whatever code uses PLUMED, from LAMMPS to ipi-code.org.

#metatensor day about to start! Join us on zoom if you're not at #EPFL epfl.zoom.us/j/68368776745 @nccr-marvel.bsky.social

In particular, this recipe relies on metatensor.github.io/featomic to compute the features, and the docs.metatensor.org/latest/torch... backend of #metatensor to export a self-contained ASE-compatible calculator. Easy to use, fast, and accurate.

We use the atomistic module of the metatensor library docs.metatensor.org/latest/index... to specify the capabilities of this model, and export it as a torchscript module.

As usual, everything is open source (github.com/metatensor/f...), and you can now use `pip install featomic` or `pip install featomic-torch` to install it! 7/n

Featomic output is using the metatensor (docs.metatensor.org) format, keeping the data as sparse as possible to minimize memory usage; and fully annotating the representation with metadata to help you understand the complex objects you are manipulating. 6/n

Happy new year everyone! After more than three years of work, and splitting out a whole separate package, I am extremely happy to announce the first full public release of featomic, a package to compute representations for atomistic machine learning! github.com/metatensor/f... 1/n

We actually already have a basic metatensor <=> OpenMM interface, contact me if you want to give it a try! The main blocking point for now is that we need to put some packages on conda-forge since OpenMM relies on conda for everything.

Want to help 😅? Jokes aside, we're thinking of doing this for metatensor, which would make also torch-pme instantly compatible. If you're interested in contributing we'd love that.

I'm getting into the habit of announcing new code releases!

So today's release is version 0.3.0 of vesin (luthaf.fr/vesin/), a small library to compute neighbor/pair lists for atomistic systems! This releases adds an option to sort the pairs and better integration with metatensor atomistic models.