marcel ⊙
@marceldotsci.bsky.social
Trying to build better machine-learning surrogate models for DFT. Postdoc @ COSMO Lab (EPFL) 👨🏻🚀.
https://marcel.science
https://marcel.science
seems like i was the only ICLR reviewer that bothered to declare LLM usage
November 12, 2025 at 9:21 AM
seems like i was the only ICLR reviewer that bothered to declare LLM usage
Reposted by marcel ⊙
This also shows that @typst.app is already a viable alternative to LaTeX for top conferences in ML!
Our paper on XAI + Automatic Differentiation got accepted at #NeurIPS2025. Can't wait to share the camera-ready soon! 🥳
September 19, 2025 at 11:54 AM
This also shows that @typst.app is already a viable alternative to LaTeX for top conferences in ML!
Reposted by marcel ⊙
Our paper on XAI + Automatic Differentiation got accepted at #NeurIPS2025. Can't wait to share the camera-ready soon! 🥳
September 19, 2025 at 11:48 AM
Our paper on XAI + Automatic Differentiation got accepted at #NeurIPS2025. Can't wait to share the camera-ready soon! 🥳
Reposted by marcel ⊙
If you are excited about 30x longer time steps in molecular dynamics using FlashMD, but are worried about it not being symplectic, Filippo has something new cooking that should make you even more excited. Head to the #arxiv for a preview arxiv.org/html/2508.01...
August 8, 2025 at 5:46 AM
If you are excited about 30x longer time steps in molecular dynamics using FlashMD, but are worried about it not being symplectic, Filippo has something new cooking that should make you even more excited. Head to the #arxiv for a preview arxiv.org/html/2508.01...
for the jax kids, i just made my personal training infra repo public: github.com/sirmarcel/ma... -- happy for some feedback/ideas/takes!
August 8, 2025 at 12:47 PM
for the jax kids, i just made my personal training infra repo public: github.com/sirmarcel/ma... -- happy for some feedback/ideas/takes!
Reposted by marcel ⊙
I benefited massively from www.ipam.ucla.edu/programs/lon.... I got into ML for science through that program. Now IPAM may be gone mathstodon.xyz/@tao/1149568...
Terence Tao (@tao@mathstodon.xyz)
The current administration in the US has, through various funding agencies such as the NSF and NIH, has recently suspended virtually all federal grants to my home university, UCLA (including my own p...
mathstodon.xyz
August 3, 2025 at 5:24 PM
I benefited massively from www.ipam.ucla.edu/programs/lon.... I got into ML for science through that program. Now IPAM may be gone mathstodon.xyz/@tao/1149568...
Reposted by marcel ⊙
This, if true, is incredible. A long program in 2011 at IPAM that I attended practically wrote the book on machine learning in materials science, which is now AI. Not funding IPAM would be deeply destructive to US leadership in critical future technologies! Hard to fathom.
I benefited massively from www.ipam.ucla.edu/programs/lon.... I got into ML for science through that program. Now IPAM may be gone mathstodon.xyz/@tao/1149568...
Terence Tao (@tao@mathstodon.xyz)
The current administration in the US has, through various funding agencies such as the NSF and NIH, has recently suspended virtually all federal grants to my home university, UCLA (including my own p...
mathstodon.xyz
August 5, 2025 at 11:21 PM
This, if true, is incredible. A long program in 2011 at IPAM that I attended practically wrote the book on machine learning in materials science, which is now AI. Not funding IPAM would be deeply destructive to US leadership in critical future technologies! Hard to fathom.
✨preprint alert: "learning long-range representations w/ equivariant messages" in which we get into the fray of long-range MLIPs and propose to use equivariant charges w/ classical electrostatics as long-range MP mechanism. we design LOREM, an equivariant MLIP, around this ...
August 5, 2025 at 2:54 PM
✨preprint alert: "learning long-range representations w/ equivariant messages" in which we get into the fray of long-range MLIPs and propose to use equivariant charges w/ classical electrostatics as long-range MP mechanism. we design LOREM, an equivariant MLIP, around this ...
very proud of filippo
Very proud to send Filippo Bigi to Vancouver to give an oral presentation at @icmlconf.bsky.social about our investigation of the use of "dark-side forces" in atomistic simulations. The final version is here openreview.net/forum?id=OEl... and it's worth a read even if you already read the #preprint
The dark side of the forces: assessing non-conservative force...
The use of machine learning to estimate the energy of a group of atoms, and the forces that drive them to more stable configurations, have revolutionized the fields of computational chemistry and...
openreview.net
June 20, 2025 at 6:58 PM
very proud of filippo
Reposted by marcel ⊙
Very proud to send Filippo Bigi to Vancouver to give an oral presentation at @icmlconf.bsky.social about our investigation of the use of "dark-side forces" in atomistic simulations. The final version is here openreview.net/forum?id=OEl... and it's worth a read even if you already read the #preprint
The dark side of the forces: assessing non-conservative force...
The use of machine learning to estimate the energy of a group of atoms, and the forces that drive them to more stable configurations, have revolutionized the fields of computational chemistry and...
openreview.net
June 20, 2025 at 3:53 PM
Very proud to send Filippo Bigi to Vancouver to give an oral presentation at @icmlconf.bsky.social about our investigation of the use of "dark-side forces" in atomistic simulations. The final version is here openreview.net/forum?id=OEl... and it's worth a read even if you already read the #preprint
Reposted by marcel ⊙
So kudos to 🧑🚀 Filippo and @marceldotsci.bsky.social bsky.app/profile/labc..., thanks to funders @erc.europa.eu @snf-fns.ch @cscsch.bsky.social and @nccr-marvel.bsky.social, and go to Filippo's talk if you are at #icml25, to see this nice mix of #compchem and #machinelearning!
Very proud to send Filippo Bigi to Vancouver to give an oral presentation at @icmlconf.bsky.social about our investigation of the use of "dark-side forces" in atomistic simulations. The final version is here openreview.net/forum?id=OEl... and it's worth a read even if you already read the #preprint
The dark side of the forces: assessing non-conservative force...
The use of machine learning to estimate the energy of a group of atoms, and the forces that drive them to more stable configurations, have revolutionized the fields of computational chemistry and...
openreview.net
June 20, 2025 at 3:56 PM
So kudos to 🧑🚀 Filippo and @marceldotsci.bsky.social bsky.app/profile/labc..., thanks to funders @erc.europa.eu @snf-fns.ch @cscsch.bsky.social and @nccr-marvel.bsky.social, and go to Filippo's talk if you are at #icml25, to see this nice mix of #compchem and #machinelearning!
obvious in hindsight but news to me: accessing np.load-ed arrays by index is orders of magnitude slower than forcing them to RAM. notes.marcel.science/2025/numpy-l...
numpy.load access performance – marcel's notes
marcel's science notes
notes.marcel.science
June 16, 2025 at 5:41 PM
obvious in hindsight but news to me: accessing np.load-ed arrays by index is orders of magnitude slower than forcing them to RAM. notes.marcel.science/2025/numpy-l...
very annoying when papers don‘t include raw data for plots
June 4, 2025 at 1:54 PM
very annoying when papers don‘t include raw data for plots
⚡️
📢 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...
May 27, 2025 at 7:48 AM
⚡️
🍾
📢 For those who missed the #preprint, torch-pme is now published in @aip.bsky.social #JChemPhys. #compchem classics like Ewald and P3M meet #machine learning. Read all about it here pubs.aip.org/aip/jcp/arti...
Fast and flexible long-range models for atomistic machine learning
Most atomistic machine learning (ML) models rely on a locality ansatz and decompose the energy into a sum of short-ranged, atom-centered contributions. This lea
pubs.aip.org
April 8, 2025 at 3:41 PM
🍾
cosmo has joined the universal FF club!
📢 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 🧑🚀
March 19, 2025 at 7:49 AM
cosmo has joined the universal FF club!
watch out cancer, mihail is coming for you 🔥
Really happy to announce that I started working at D. E. Shaw Research this week. It's been an exciting first week at the company and I can't wait to start contributing to the very cool and ambitious research being done here!
February 16, 2025 at 4:05 PM
watch out cancer, mihail is coming for you 🔥
Reposted by marcel ⊙
Completed my post preprint project: a split keyboard to help with my wrist pain (pictured with the pain-relieving gel it is trying to replace).
February 13, 2025 at 1:10 PM
Completed my post preprint project: a split keyboard to help with my wrist pain (pictured with the pain-relieving gel it is trying to replace).
anyone at the lausanne applied ML days?
February 11, 2025 at 1:38 PM
anyone at the lausanne applied ML days?
Reposted by marcel ⊙
@marceldotsci.bsky.social getting into very dangerous territory.
February 5, 2025 at 4:08 PM
@marceldotsci.bsky.social getting into very dangerous territory.
we're having an interesting seminar next tuesday on equivariance in deep ensembles, for the EPFL squad: actu.epfl.ch/news/seminar...
Seminar by Jan Gerken: Emergent Equivariance in Deep Ensembles
Join us for a seminar by Jan Gerken on Tuesday, February 4th, at 10:30 AM in MED 2 1124 (Coviz2). Jan is an Assistant Professor in the Division of Algebra and Geometry at Chalmers University of Techno...
actu.epfl.ch
January 30, 2025 at 5:08 PM
we're having an interesting seminar next tuesday on equivariance in deep ensembles, for the EPFL squad: actu.epfl.ch/news/seminar...
Reposted by marcel ⊙
You think Jacobian and Hessian matrices are prohibitively expensive to compute on your problem? Our latest preprint with @gdalle.bsky.social might change your mind!
arxiv.org/abs/2501.17737
🧵1/8
arxiv.org/abs/2501.17737
🧵1/8
January 30, 2025 at 2:32 PM
You think Jacobian and Hessian matrices are prohibitively expensive to compute on your problem? Our latest preprint with @gdalle.bsky.social might change your mind!
arxiv.org/abs/2501.17737
🧵1/8
arxiv.org/abs/2501.17737
🧵1/8
the recording of my talk at orbital materials, together with jonathan schmidt, is out: www.youtube.com/watch?v=0xpR...!
Big Data & Symmetry in Machine Learning Models, with Marcel Langer & Jonathan Schmidt
YouTube video by Orbital
www.youtube.com
January 28, 2025 at 9:15 AM
the recording of my talk at orbital materials, together with jonathan schmidt, is out: www.youtube.com/watch?v=0xpR...!
now on day ~2 of debugging bizarre multiprocessing issues with Google Grain, the alleged hot new data loading framework. has anyone here actually used it by any chance?
January 17, 2025 at 5:45 PM
now on day ~2 of debugging bizarre multiprocessing issues with Google Grain, the alleged hot new data loading framework. has anyone here actually used it by any chance?