Matthias Kellner (@linuskellner) 's Twitter Profile
Matthias Kellner

@linuskellner

PhD student in @lab_COSMO

ID: 1761858099395141632

calendar_today25-02-2024 20:58:26

28 Tweet

45 Followers

119 Following

Machine Learning: Science and Technology (@mlstjournal) 's Twitter Profile Photo

Great new work by marcel ⊙ Sergey Pozdnyakov Michele Ceriotti COSMO Lab NCCR-MARVEL EPFL - 'Probing the effects of broken symmetries in #machinelearning' - iopscience.iop.org/article/10.108… #compchem #materials #statphys #molecules #compphys #simulation #atomistic

Great new work by <a href="/marceldotsci/">marcel ⊙</a> <a href="/spozdn/">Sergey Pozdnyakov</a> <a href="/MicheleCeriotti/">Michele Ceriotti</a> <a href="/lab_COSMO/">COSMO Lab</a> <a href="/nccr_marvel/">NCCR-MARVEL</a> <a href="/EPFL_en/">EPFL</a> - 'Probing the effects of broken symmetries in #machinelearning' - iopscience.iop.org/article/10.108… #compchem #materials #statphys #molecules #compphys #simulation #atomistic
marcel ⊙ (@marceldotsci) 's Twitter Profile Photo

New: Fast and flexible range-separated models for atomistic machine learning, spearheaded by Kevin and Philip, with many cosmonauts and Michele Ceriotti ! We present a fast and differentiable torch and JAX implementation of (Particle Mesh) Ewald. ✨ arxiv.org/abs/2412.03281

COSMO Lab (@lab_cosmo) 's Twitter Profile Photo

🤫 you can get a better universal #machinelearning potential by training on fewer than 100k structures. too good to be true? head to arxiv:2503.14118, to the atomistic cookbook, or to the better science social if you want to find out more about PET-MAD. 🧑‍🚀 over and out 👋

🤫 you can get a better universal #machinelearning potential by training on fewer than 100k structures. too good to be true? head to arxiv:2503.14118, to the atomistic cookbook, or to the better science social if you want to find out more about PET-MAD. 🧑‍🚀 over and out 👋
Davide Tisi (@tis930) 's Twitter Profile Photo

Last week, we continued COSMO Lab's study of solid-state electrolytes, focusing on the properties of the LPS surfaces arxiv.org/abs/2504.11553. Many thanks to my office mate Hanna Tuerk who did a lot of the work

Jean-Philip Piquemal (@jppiquem) 's Twitter Profile Photo

#compchem What could we do if we had a fast and accurate foundation #MachineLearning learning model for condensed phase molecular dynamics simulation of biological systems? 👉Check the ChemRxiv preprint: "A Foundation Model for Accurate Atomistic Simulations in Drug Design":

#compchem What could we do if we had a fast and accurate foundation #MachineLearning  learning model for condensed phase molecular dynamics simulation of biological systems?

👉Check the <a href="/ChemRxiv/">ChemRxiv</a> preprint: "A Foundation Model for Accurate Atomistic Simulations in Drug Design":
Kyle Tretina, Ph.D. (@allthingsapx) 's Twitter Profile Photo

AI + physics turns dynamics into a data engine. FeNNix-Bio1: a foundation model that drives QM-level, reactive MD on a single GPU, hydration, folding, binding ΔG within ≈1 kcal/mol, yet pushes 7M-atom boxes at force-field speed

AI + physics turns dynamics into a data engine.

FeNNix-Bio1: a foundation model that drives QM-level, reactive MD on a single GPU, hydration, folding, binding ΔG within ≈1 kcal/mol, yet pushes 7M-atom boxes at force-field speed
marcel ⊙ (@marceldotsci) 's Twitter Profile Photo

✨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...

Matthias Kellner (@linuskellner) 's Twitter Profile Photo

Apax is a really nice MLIP framework. The GMNN implementation strikes a great balance between speed and accuracy for many applications.

marcel ⊙ (@marceldotsci) 's Twitter Profile Photo

for the jax kids, i just made my personal training infra repo public: github.com/sirmarcel/mara… -- happy for some feedback/ideas/takes!

Signal (@signalapp) 's Twitter Profile Photo

We are alarmed by reports that Germany is on the verge of a catastrophic about-face, reversing its longstanding and principled opposition to the EU’s Chat Control proposal which, if passed, could spell the end of the right to privacy in Europe. signal.org/blog/pdfs/germ…