Couldn't have asked for better timing #NobelPrize Our new work on 'Molecular Simulations with a Pretrained Neural Network and Universal Pairwise Force Fields' is now out on ChemRxiv! #MachineLearning #compchem

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

Our technical report from the team at Orbital is now on Arxiv: arxiv.org/abs/2410.22570 Feedback welcome - a reminder to sign up for our Seminar Series if these directions in Comp Matsci interest you. orbitalmaterials.com/post/seminar-s…

1/ What are key design principles for scaling neural network interatomic potentials? Our exploration leads us to top results on the Open Catalyst Project (OC20, OC22), SPICE, and MPTrj, with vastly improved efficiency! Accepted at #NeurIPS2024: arxiv.org/abs/2410.24169

Such a honer COSMO Lab UnifrChemistry

We curated 40+ quantum mechanics datasets covering 250+ quantum methods & 1.5B geometries. All of this is easily accessible through the OpenQDC library. 🧵 Harness the power of QM data with a single line of code: openqdc.io Blog: valencelabs.com/blog-posts/ope…

It was a lovely symposium! Enjoyed it much

⚛️🤗 Announcing LeMaterial ⚛️🤗 Hugging Face & Entalpic are teaming up to release LeMaterial -- an open source initiative aiming to facilitate (AI for) materials discovery ! Datasets, hash function, tools to explore the chemical space & more ! huggingface.co/blog/lematerial

Join the dark side of the forces (or not!). TL;DR - Using forces that are not conservative is not a great idea. Latest and greatest, now on the arXiv.org , from Filippo Bigi and marcel ⊙.

the recording of the talk i gave a while back about the "invariance is easy to learn" paper with Sergey Pozdnyakov and Michele Ceriotti is out!

LLMs are pretty bad at writing molecules, but quite good at analyzing mols and reactions! In our new work we use LLMs+search in chemical tasks, unlocking steerable synth. planning and mechanism prediction 🌟 1/ Theo Neukomm Daniel Armstrong Zlatko Jončev Philippe Schwaller (he/him) arxiv.org/abs/2503.08537

We just released a preprint with my wonderful coworkers Andrés M Bran Daniel Armstrong Zlatko Jončev Philippe Schwaller (he/him) showcasing how LLMs can refine a search in the chemical space using natural language as their compass. Preprint can be found at arxiv.org/abs/2503.08537, more on that below: 1/🧵

🤫 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 👋

Excited to announce Orb-v3, a new family of universal Neural Network Potentials from me and my team at Orbital, led by Ben Rhodes and @sanderhaute! These new potentials span the Pareto frontier of models for computational chemistry.

Generate property-optimized small molecules with 𝘴𝘵𝘦𝘦𝘳𝘢𝘣𝘭𝘦 𝘢𝘯𝘥 𝘨𝘳𝘢𝘯𝘶𝘭𝘢𝘳 synthesizability control - allowing complete user-flexibility to impose various reaction constraints! Pre-print: arxiv.org/abs/2505.08774 Code: github.com/schwallergroup… (1/4)

Started with some slides for AutoAdsorbate-ended up with an animated deep dive into surface site detection. It works on any surface, no bulk symmetry needed. Here’s what this one-liner really does: s=Surface(slab211) code: github.com/basf/autoadsor… paper: tinyurl.com/yfbxnbds

🚀Exciting news! We are releasing new UMA-1.1 models (Small and Medium) today and the UMA paper is now on arxiv! UMA represents a step-change in what’s possible with a single machine learning interatomic potential (short overview in the post below). The goal was to make a model

AI4Mat is back for NeurIPS! time to crystallize those ideas and make a solid-state submission by august 22, 2025 💪 new this year: opt-in your work for our Research Learning from Speaker Feedback program -- a new structured discussion format where spotlight presenters receive

b-12 (b12-labs.com) is building AI agents that help chemists design experiments and automatically run them on lab robots. They turn months of manual chemistry work into minutes of automated execution. Congrats on the launch Andrés M Bran & Zlatko Jončev! ycombinator.com/launches/O3V-b…