Sign in

Michele Ceriotti

@micheleceriotti.bsky.social
362 followers 93 following 77 posts

Italian in Switzerland, @lab_COSMO PI. Husband of one, father of three. Increasing the entropy of the universe since 1982.

PostsRepliesMedia
Reposted by Michele Ceriotti
marcel ⊙ @marceldotsci.bsky.social · 18/09/2026
✨ new work: "Truncated automatic sparse differentiation for MLIPs" with @adrianhill.de & @micheleceriotti.bsky.social has arrived on the arXiv. In a 🥥: we exploit that MLIP Hessians are sparse and decay with distance with a "truncated" variant of automatic sparse differentiation. See figure. 👇
Truncated automatic sparse differentiation (ASD). (a) Toy chain of 7 atoms, model reach K = 2 hops. The Hessian H is recovered from Hessian-vector products (HVPs) with the columns of a seed matrix S, giving the compressed product HS. Since H is sparse, star coloring needs 5 colors, hence 5 HVPs instead of 7. Each entry of H is read from one entry of HS (its hue), directly or via its symmetric partner; entries that are sums are never read (crossed). Truncating to one hop needs only 3 HVPs, but the neglected two-hop couplings (gray) now contaminate entries that are read (dots), causing errors. (b) MOF-177 with PET-XS: atoms within K = 5 hops of one Zn atom in the model's graph, with its cutoff sphere and one-hop edges; rest of the cell in gray. (c) Same atoms colored by the force-constant block norm ‖Φᵢⱼ‖ to the marked atom, decaying with distance. (d) Whole Hessian of MOF-177, one cell per atom pair, graph neighbors adjacent: hop count above the diagonal, ‖Φᵢⱼ‖ below, zeros white.
1116
Reposted by Michele Ceriotti
Matthias Kellner @matthiaskellner.bsky.social · 18/09/2026
We have released ShiftML4! ShiftML4 comes with built-in molecular corrections, elevating the chemical shielding predictions to hybrid-DFT level quality. Try it yourself on shiftml.org, or from the PyPi package.
044
Reposted by Michele Ceriotti
Kay Severin @kay-severin.bsky.social · 13/08/2026
Faculty position in our institute @EPFL: www.epfl.ch/about/workin...
01417
Reposted by Michele Ceriotti
COSMO Lab @labcosmo.bsky.social · 30/07/2026
A little holiday reading from 🧑‍🚀: arxiv.org/html/2607.26... , or how Michelangelo used #AI to break equivariant atom-centered descriptors all the way to 7 neighbors (and arbitrary many neighbors when considering a finite, practical level of discretization). 🤯
Atomic structures that are indistinguishable by atom-centered descriptors for ML potentials
141
Michele Ceriotti @micheleceriotti.bsky.social · 20/07/2026
Keeping up with the tradition we started in 2016 of having path integral themed coffee cups, piqm2026.org brings it on an entirely different level.
A path-integral themed espresso cupA path integral themed teapot
031
Michele Ceriotti @micheleceriotti.bsky.social · 19/07/2026
George Trenins doing a great job filling in for @mahrossi.bsky.social, who could not join in Shanghai for the (wonderfully organized by Wei Fang) piqm2026.org conference. If you have FOMO, you'll find this and other tutorials on the 🧑‍🍳📖 at the end of the school!
021
Reposted by Michele Ceriotti
COSMO Lab @labcosmo.bsky.social · 10/06/2026
Time to learn the action 🏃 ! Today I'm sharing a paper, just published on @physrevlett.bsky.social, showing how to construct a symplectic #machinelearning predictor of classical mechanics by learning the Hamilton-Jacobi action.
162
Reposted by Michele Ceriotti
Peter Spackman @crystalexplorer.net · 05/06/2026
I don’t have the budget for hundreds of GPUs or even a backend, so I had to make mine use your local resources 🤓 peterspackman.github.io/mlip.cpp/
peterspackman.github.io
mlip.js - ML Interatomic Potentials in the Browser
062
Reposted by Michele Ceriotti
Simon Olsson @smnlssn.bsky.social · 04/04/2026
Join us in Gothenburg! Excellent conditions, scientific independence, and low teaching load on the tenure track. Feel free to reach out if you have any questions.
0103
Reposted by Michele Ceriotti
COSMO Lab @labcosmo.bsky.social · 03/03/2026
📢 We have been working on a new universal atomistic dataset that combines the principles of MAD with a meta-GGA level of theory, so we can all simulate water that does not freeze at 500K 🧊 , and have all our bases covered, with reference data for every isotope with a half-life above 24 hours ☢️
1124
Reposted by Michele Ceriotti
COSMO Lab @labcosmo.bsky.social · 03/03/2026
So let us show you just how *universal* #PET-MAD-1.5 can be. This is a movie of a parallel tempering simulation, with replicas from 300K to 3000K, of what we call a "Mendeleev cluster" - one atom each of every element from 1 to 102.
2115
Reposted by Michele Ceriotti
COSMO Lab @labcosmo.bsky.social · 23/02/2026
New recipe just landed on the atomistic-cookbook.org 🧑‍🍳📖. Thanks to @yairlitman.bsky.social for explaining how to use ipi-code.org to perform ring-polymer instanton calculations of reaction rates that include quantum tunneling effects ⚛️⚡. Check it out 👉 atomistic-cookbook.org/examples/rin...
Snapshot of a ring-polymer instanton calculation for the reaction of methane with a H radical
061
Reposted by Michele Ceriotti
COSMO Lab @labcosmo.bsky.social · 18/02/2026
📢 New #preprint is out! Investigating the many flavors of last-layer #UQ, Moritz and 🧑‍🚀Matthias propose a practitioners' guide on "how to train a shallow ensemble". TL;DR? for good calibration use NLL, include force, and optimize the backbone, fine-tuning for speed! 📃🔗➡️ arxiv.org/html/2602.15...
arxiv.org
How to Train a Shallow Ensemble
032
Reposted by Michele Ceriotti
Matthias Kellner @matthiaskellner.bsky.social · 17/02/2026
No Install. No Setup. Just Chemical Shift Predictions. At shiftml.materialscloud.io we host the latest ShiftML3 in the web and you can predict chemical shifts of organic crystals for free in the web!
shiftml.materialscloud.io
ShiftML-3 predictor
032
Reposted by Michele Ceriotti
COSMO Lab @labcosmo.bsky.social · 14/02/2026
Many #machinelearning potentials are built (or understood) in terms of "atomic cluster expansions" that link directly to a body-ordered energy decomposition that can be computed explicitly with a sequence of electronic structure calculations. But what kind of expansion do they learn in practice? A🧵
The body ordered expansion, equations
182
Reposted by Michele Ceriotti
COSMO Lab @labcosmo.bsky.social · 08/02/2026
If you want to learn about materials modeling, from DFT to MD, well marinated in a spicy ML sauce, don't miss out the @ictp.bsky.social / @nccr-marvel.bsky.social college. Details and application instructions here indico.ictp.it/event/11146/. See you in Miramare!
093
Reposted by Michele Ceriotti
LFIM - Wendy L. Queen @lfim-epfl.bsky.social · 30/01/2026
We are delighted to announce the launch of NCCR Separations — a new National Center of Competence in Research dedicated to breakthrough separation technologies for a sustainable future! Read more: actu.epfl.ch/news/a-new-n... #NCCRSeparations #EPFL #GreenChemistry #EnergyTransition #ClimateTech
actu.epfl.ch
A new national research programme recognizes EPFL's expertise
The Swiss Confederation launches six new National Centres of Competence in Research (NCCRs). The NCCR “Separations”, which aims to accelerate research in separation sciences - the quest for chemical a...
0122
Reposted by Michele Ceriotti
COSMO Lab @labcosmo.bsky.social · 30/01/2026
Fantastic news from the @snf-fns.ch, who despite the budget cuts managed to fund six new NCCRs. Looking forward to doing some cool simulations to advance separation science! actu.epfl.ch/news/a-new-n...
actu.epfl.ch
A new national research programme recognizes EPFL's expertise
The Swiss Confederation launches six new National Centres of Competence in Research (NCCRs). The NCCR “Separations”, which aims to accelerate research in separation sciences - the quest for chemical a...
051
Michele Ceriotti @micheleceriotti.bsky.social · 24/01/2026
PIMD Kusama
0111
Reposted by Michele Ceriotti
COSMO Lab @labcosmo.bsky.social · 23/01/2026
If you got curious by the PET-OAM results a week ago, you can learn more reading up arxiv.org/abs/2601.16195. Including some general considerations on how to train and use safely an unconstrained ML potential.
Table showing results of a few representative universal model on the matbench leaderboard
121
Reposted by Michele Ceriotti
CECAM @cecamevents.bsky.social · 19/01/2026
We just kick-started our first workshop of the year, the CECAM Flagship workshop “A Roadmap for an Atomistic Machine Learning Software Ecosystem” - laptops open, ideas humming, and the groove has begun. www.cecam.org/workshop-det...
194
Reposted by Michele Ceriotti
COSMO Lab @labcosmo.bsky.social · 14/01/2026
Not going to make a big deal out of a benchmark table, but PET just got the top spot on matbench-discovery.materialsproject.org. And don't be fooled by the huge parameters count, it's faster and can handle larger structures than eSEN-30M 🚀. Kudos to 🧑‍🚀 Filippo, Arslan and Paolo!
Screenshot of the matbench discovery leaderboard as of 14.01.2026, showing a PET based model in the top position
182
Reposted by Michele Ceriotti
Caroline Lynn Kamerlin ☀️ @lynnkamerlin.bsky.social · 08/01/2026
The Iranian regime has shut down the Internet. They do this every time there are mass protests as a prelude to massacre. That the international media is not properly covering all this is a disgrace. Don't look away. #Iran
071
Reposted by Michele Ceriotti
Materials Science & Engineering @EPFL @materials-epfl.bsky.social · 06/01/2026
Join the next IMX talk 🗓️ Thursday, 8 January 2026 at 15:00 🎙️ Dr. Christian Leinenbach, EMPA and EPFL 🔎 From Powder to Performance: Microstructure Engineering in Metal Additive Manufacturing for Advanced Applications Find out more: memento.epfl.ch/event/imx-ta...
012
Reposted by Michele Ceriotti
COSMO Lab @labcosmo.bsky.social · 05/01/2026
📢 chemiscope.org 1.0.0rc1 just dropped on pypi! We are making (a few) breaking changes to the interfaces, fixing a ton of bugs and introducing some exciting features (you can finally load datasets with > 100k points!). We'd be grateful if you test, break and report 🐛 github.com/lab-cosmo/ch...
Zooming in on a large-scale dataset to showcase the new adaptive resolution features in chemiscope
042
Michele Ceriotti @micheleceriotti.bsky.social · 14/12/2025
Playing around with humidity sensitive salts with the kiddos. Pink/blue is CoCl2, green/brown is CuCl2, light blue Cu(OH)2. Other ideas? Possibly not too toxic, and possibly that I can make with scrap metals, HCl, H2O2 and ammonia.
020
Michele Ceriotti @micheleceriotti.bsky.social · 12/12/2025
Teachers have been striking two days a week for a month in Vaud. As a parent, it's a pain, but they're right to strike. Cutting public services that work well when there is no budget crisis and no debt is idiotic and self-damaging. Taxes are so effing low in 🇨🇭 anyway!
120
Reposted by Michele Ceriotti
Materials Science & Engineering @EPFL @materials-epfl.bsky.social · 04/12/2025
👏 Congratulations to Prof. Dirk Grundler, head of the Laboratory of Nanoscale Magnetic Materials and Magnonics (LMGN) on his promotion to Full Professor of Materials Science in the School of Engineering! More info: actu.epfl.ch/news/nominat...
021
Reposted by Michele Ceriotti
COSMO Lab @labcosmo.bsky.social · 10/12/2025
Congrats to 🧑‍🚀 Sergey Pozdnyakov who received a distinction (best 8% of theses at @materials-epfl.bsky.social) for his PhD thesis "Advancing understanding and practical performance of machine learning interatomic potentials". Поїхали 🚀! infoscience.epfl.ch/entities/pub...
0102
Reposted by Michele Ceriotti
COSMO Lab @labcosmo.bsky.social · 09/12/2025
No day goes by without a new universal #ML potential. But how different they really are? Sanggyu and Sofiia tried to give a quantitative answer by comparing the reconstruction errors between their latent-space features. If you are curious, check out the #preprint arxiv.org/html/2512.05...
Features reconstruction errors between the latent spaces of several universal MLIPs
0113
Michele Ceriotti @micheleceriotti.bsky.social · 04/12/2025
San Diego! Must admit I did miss the perpetual summer.
0120
Michele Ceriotti @micheleceriotti.bsky.social · 03/12/2025
Another day, another talk. Looking forward to the impromptu workshop organized by Yang Shao-Horn's lab!
020
Michele Ceriotti @micheleceriotti.bsky.social · 02/12/2025
Boston dawn at the #MRS25. One talk done, two to go for this 🇺🇸 pre-xmas grand tour. May the saint protector of jet lag help me.
010
Michele Ceriotti @micheleceriotti.bsky.social · 30/11/2025
Yearly reminder that growing food is hard.
Our yearly potato harvest
140
Michele Ceriotti @micheleceriotti.bsky.social · 28/11/2025
the ICLR review process is rapidly turning into a theater of the absurd 🍿
010
Reposted by Michele Ceriotti
COSMO Lab @labcosmo.bsky.social · 28/11/2025
📢 PET-MAD is here! 📢 It has been for a while for those who read the #arXiv, but now you get it preciously 💸 typeset by @natcomms.nature.com Take home: unconstrained architecture + good train set choices give you fast, accurate and stable universal MLIP that just works™️ www.nature.com/articles/s41...
nature.com
PET-MAD as a lightweight universal interatomic potential for advanced materials modeling - Nature Communications
PET-MAD is a fast and lightweight universal machine-learning potential, trained on a small but diverse dataset, that delivers near-quantum accuracy in atomistic simulations for both organic and inorga...
0156
Michele Ceriotti @micheleceriotti.bsky.social · 27/11/2025
If you're at EPFL and want to know about the new hybrid B200+B40s cluster Lyra 😋, that will arrive mid-2026, don't miss the user meeting on Thursday, December 11th, from 2:30 to 3:30pm. Check your e-mail or ask scitas@epfl.ch to get the zoom link 😁
010
Michele Ceriotti @micheleceriotti.bsky.social · 26/11/2025
made by a friend of a colleague. iykyk
a meme with scilla and cariddi and ulysses ship trying to sail through, making fun of the peer review process at ICLR
052
Michele Ceriotti @micheleceriotti.bsky.social · 12/11/2025
I was very curious of the @iclr-conf.bsky.social experiment of allowing LLM use in reviews, as I've used LLMs to "self-review" @labcosmo.bsky.social manuscripts and found it quite powerful. Sadly, what I'm seeing is all slop. I thought CS grad students would be better at LLMs. Experiment failed 🤷
240
Reposted by Michele Ceriotti
Materials Science & Engineering @EPFL @materials-epfl.bsky.social · 31/10/2025
💡Exciting innovation from the Laboratory of Photonic Materials and Fiber Devices! Prof. Fabien Sorin and his team have developed a innovative stretchable electronic fiber. Read more in Nature Electronics: www.nature.com/articles/s41...
nature.com
Electronic fibres via the thermal drawing of liquid-metal-embedded elastomers - Nature Electronics
A thermal drawing method can be used to create stretchable electronic fibres from a liquid-metal-embedded elastomer that can contain conductive and insulating domains across the fibre cross-section.
011
Michele Ceriotti @micheleceriotti.bsky.social · 28/10/2025
Time to reach for the wallet. And maybe time for the PSF to consider relocating to a country that is not sliding into the dark ages, or at least not so quickly.
172
Reposted by Michele Ceriotti
AIhub.org @aihub.org · 15/10/2025
‪In this blog post, Filippo Bigi, Marcel Langer (@labcosmo.bsky.social‬) and @micheleceriotti.bsky.social write about the need to balance speed and physical laws when using ML for atomic-scale simulations aihub.org/2025/10/10/m...
aihub.org
Machine learning for atomic-scale simulations: balancing speed and physical laws - ΑΙhub
052
Reposted by Michele Ceriotti
COSMO Lab @labcosmo.bsky.social · 10/10/2025
A primer for non conservative (& rotationally unconstrained) MLIPs, and how to use them safely. Thanks @aihub.org for the space! aihub.org/2025/10/10/m...
aihub.org
Machine learning for atomic-scale simulations: balancing speed and physical laws - ΑΙhub
084
Reposted by Michele Ceriotti
Materials Science & Engineering @EPFL @materials-epfl.bsky.social · 06/10/2025
🌍 EPFL’s Institute of Materials (IMX) is offering 6-month funded fellowships for external Master’s students in Materials Science. Join one of IMX’s world-class labs and gain hands-on research experience at the cutting edge of materials science. 👉 lnkd.in/enNeKmTh
011
Michele Ceriotti @micheleceriotti.bsky.social · 06/10/2025
Are you or do you know a smart, motivated Master student in a materials-adjacent area interested in doing a research project at EPFL? The @materials-epfl.bsky.social MX Fellowship applications open today sti.epfl.ch/smx/mx-fello.... Choose a lab, send your file, and spend up to six months at EPFL!
Aerial view of the EPFL campus
131
Michele Ceriotti @micheleceriotti.bsky.social · 05/10/2025
Looks like @ox.ac.uk forbids their researchers to do any kind of literature search, though it seems that thankfully they can still submit to the arxiv arxiv.org/abs/2510.00027 🤷
arxiv.org
Learning Inter-Atomic Potentials without Explicit Equivariance
Accurate and scalable machine-learned inter-atomic potentials (MLIPs) are essential for molecular simulations ranging from drug discovery to new material design. Current state-of-the-art models enforc...
0103
Reposted by Michele Ceriotti
Giuseppe Carleo @gppcarleo.bsky.social · 26/09/2025
I have a new opening for several funded PHD positions in my group (the Computational Quantum Science Lab, at EPFL). If you are a talented, motivated student, please apply here www.epfl.ch/labs/cqsl/jo.... I am especially looking to hire in scientific ML applications/NQS; not in quantum computing.
epfl.ch
Job Opportunities at CQSL
At the Computational Quantum Science Lab we typically have several openings yearly (at the PhD/ Postdoc level). Applications are reviewed twice a year, at the beginning of April and at the beginning o...
1124
Michele Ceriotti @micheleceriotti.bsky.social · 24/09/2025
Flying ITA and 🤞 I'll make it alive. Total shitshow. I think they'll end up bankrupt like all the Alitalia descendants have before them, hope after I land.
010
Reposted by Michele Ceriotti
COSMO Lab @labcosmo.bsky.social · 23/09/2025
📝 We have been told (& been telling) that ML potentials are linked quite directly to the expansion of the atomic energy into pairs, triples, and so on. But is this actually true 🤔? Go read the latest from the 🧑‍🚀 team (w/QM help from Joonho's team at Harvard) to find out more arxiv.org/html/2509.14...
arxiv.org
Resolving the Body-Order Paradox of Machine Learning Interatomic Potentials
151
Michele Ceriotti @micheleceriotti.bsky.social · 21/09/2025
'this the season! 🍄
porcini in tha forestporcini on tha boardporcini mit botox
250