Fascinating new work from the Gabe Gomes group. The team developed Stereoelectronics-Infused Molecular Graphs (SIMGs) that incorporate quantum chemical orbital interactions into molecular representations. This work goes beyond traditional molecular graph representations by

In Nature Machine Intelligence, Carnegie Mellon Chemical Engineering and CMU Chemistry's Gabe Gomes incorporates quantum-chemical interactions in a new molecular ML model, enhancing existing molecular representations and enabling rapid generation of new quantum-informed graphs. cheme.engineering.cmu.edu/news/2025/05/2…

I like the research topic "AI Scientist" because it's now unclear if you're a scientist studying AI or trying to build an AI that can do science. That ambiguity would have been insane 3 years ago.

Although Rowan is a computational company, my background is experimental—I ran calculations in my PhD, but I didn't really understand how things worked. From Aug 2021 to Dec 2023, I obsessively self-studied quantum chemistry. My goal was to rebuild my entire stack from scratch.

This was fulfilling, but very hard; the key references were often obscure or hard to find, and it's tough to understand how everything fits together. I wrote up a guide to make it easier for future aspiring quantum chemists to learn this material: corinwagen.github.io/public/blog/20…

Thank you, NSF! Congrats to Emma Bouchard a CMU Chemistry graduate student in my lab for receiving NSF GRFP! This fellowship will support Emma’s work on AI-driven computation and automated robotic experiment in molecular discovery! Cc: CMU Mellon College of Science Carnegie Mellon University #nsffunded

In Nature Machine Intelligence, Faculty member Gabe Gomes Gabe Gomes, PhD student Daniil Boiko, and their collaborators propose a new type of molecular ML representation that includes quantum-chemical interaction cmu.edu/mcs/news-event…

i made ChatGPT (o3-pro + deep research) work for 63m on a task. i’ve never had it take any longer than 30 min on anything before this one. nice.

Our new ChemRxiv preprint: AIMNet2-rxn: A #MachineLearning Potential for Generalized Reaction Modeling on a Millions-of-Pathways Scale! #compchem Collaboration with Brett Savoie group. Funded by Office of Naval Research (ONR) under #MURI program chemrxiv.org/engage/chemrxi…

In the age of LLMs, research–and the role of the researcher–are changing. Gabe Gomes sees the potential to combine human creativity with machine capability by strategically implementing frontier AI models. engineering.cmu.edu/news-events/ne… CMU Chemistry

🚀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

Sharing an update on Figma: we publicly filed our S-1 with the SEC today, and have applied to list on the New York Stock Exchange under the symbol “FIG.” figma.com/blog/s1-public

Excited to share our new strategy to access carbenes - of all electronic types! Congrats to Khue, Xueling, Bethany, Mohamed, Jake, Young, & Ilias on their beautiful work in Science Magazine! science.org/doi/10.1126/sc…

BioEmu now published in Science Magazine !! What is BioEmu? Check out this video: youtu.be/LStKhWcL0VE?si…

Today in Science Magazine, we report a method to replace the C2 of pyridines with N, affording pyridazines. The change from electronically consonant (pyridine) to dissonant (pyridazine) opens retrosyntheses not typically available to the latter. science.org/doi/10.1126/sc…

HLE has recently become the benchmark to beat for frontier agents. We FutureHouse took a closer look at the chem and bio questions and found about 30% of them are likely invalid based on our analysis and third-party PhD evaluations. 1/7

In case you missed it, check out the video of my talk on OMol25, where I discuss how we built the dataset + how MLIPs trained on OMol25 are revolutionizing computational chemistry! youtube.com/watch?v=ROajuR…

Good morning

Attention is all you need - but how does it work? In our new paper, we take a big step towards understanding it. We developed a way to integrate attention into our previous circuit-tracing framework (attribution graphs), and it's already turning up fascinating stuff! 🧵