Advertisement Β· 728 Γ— 90

Posts by marcel βŠ™

running greek guy

running greek guy

πŸƒπŸ»β€β™‚οΈ largely because the name was too tempting, partially to support the upcoming LOREM release & make CI less annoying, my hackable personal jax training infra is now on PyPI pypi.org/project/mara... β€” featuring a beautiful logo drawn by a dear friend

1 month ago 2 0 0 0

you need to think with AI, the future is text

2 months ago 0 0 0 0
Preparing JOSS for a generative AI future: From code to human creativity and design | Journal of Open Source Software Blog Blog for the Journal of Open Source Software β€’ <a href='https://joss.theoj.org'>https://joss.theoj.org</a>

good reaction: blog.joss.theoj.org/2026/01/prep...

2 months ago 0 0 0 0
Preview
AGI is here (and I feel fine) I propose to begin this year with an acknowledgment that is strategic but/and also sincere.

www.robinsloan.com/winter-garde...

2 months ago 1 0 0 0

my long bet to not bother to learn vim commands has finally paid off #sloperator

2 months ago 4 0 1 1

thank you adrian, thatβ€˜s a very poignant quote πŸ˜”

4 months ago 1 0 0 0

congrats to you two! well deserved!

4 months ago 2 0 0 0

i may be biased but this is a very nice example of a universal MLIP paper

4 months ago 1 0 0 0

those are the shiniest potatoes i’ve ever seen

4 months ago 1 0 0 0

reality is proving @adrianhill.de more right by the minute -- now all reviews have been reverted to their pre-discussion state. someone remind me why i spent a week+ preparing rebuttals and reading author comments?

4 months ago 3 0 1 0
Advertisement

ICLR2026 is truly the gift that keeps on giving

4 months ago 3 0 0 1

When it comes to drama, ICLR 2026 is truly the gift that keeps on giving.

4 months ago 4 1 1 0
a meme with scilla and cariddi and ulysses ship trying to sail through, making fun of the peer review process at ICLR

a meme with scilla and cariddi and ulysses ship trying to sail through, making fun of the peer review process at ICLR

made by a friend of a colleague. iykyk

4 months ago 4 2 0 0

seems like i was the only ICLR reviewer that bothered to declare LLM usage

5 months ago 2 0 0 0

This also shows that @typst.app is already a viable alternative to LaTeX for top conferences in ML!

7 months ago 38 5 3 0

Our paper on XAI + Automatic Differentiation got accepted at #NeurIPS2025. Can't wait to share the camera-ready soon! πŸ₯³

7 months ago 11 1 0 1
Orbits for a periodic 3-body system, showing the stability of a ML long-time integrator

Orbits for a periodic 3-body system, showing the stability of a ML long-time integrator

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...

8 months ago 13 2 1 0
Advertisement

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

8 months ago 0 0 0 0
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...

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...

8 months ago 6 2 2 1

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.

8 months ago 2 1 0 1

Absolute insanity. IPAM is where I first heard about equivariant NNs! What a loss.

8 months ago 1 0 0 0

this is work at @labcosmo.bsky.social with Egor, Tulga, Philip & @micheleceriotti.bsky.social!

8 months ago 0 0 0 0
Preview
Learning Long-Range Representations with Equivariant Messages Machine learning interatomic potentials trained on first-principles reference data are quickly becoming indispensable for computational physics, biology, and chemistry. Equivariant message-passing neu...

... overall, it seems that we need more challenging benchmarks. or maybe LR behaviour is simply "not that complicated". we will see. the manuscript is here: arxiv.org/abs/2507.19382 & code & data are coming out soon-ish, once i run a few more ablations. looking forward to feedback!

8 months ago 0 0 1 0

... and show that it works pretty well on a few long-range benchmark datasets. but we also find that many benchmark tasks are easily solved even by short-range message passing, so we run a few more targeted experiments to see where it fails & confirm that LOREM works for these ...

8 months ago 0 0 1 0

✨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 ...

8 months ago 3 0 1 0
Advertisement

very proud of filippo

10 months ago 1 0 0 0
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...

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

10 months ago 10 5 1 2

So kudos to πŸ§‘β€πŸš€ 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!

10 months ago 6 1 0 0
numpy.load access performance – marcel's notes marcel's science notes

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...

10 months ago 0 0 0 0
Post image

ok then thanks

10 months ago 0 0 0 0