“Balancing Efficiency and Expressiveness: Subgraph GNNs with Walk-Based Centrality” is at #ICML2025! Drop by our poster on Tuesday 11:00–13:30, East Exhib. Hall A-B # E-3005. Joint work w/ @JoshSouthern13 @ytn_ym @GuyBarSh @mmbronstein @HaggaiMaron arxiv.org/abs/2501.03113 🧵

Knowledge Graph Foundation Models (KGFMs) are at the frontier of graph learning - but we didn’t have a principled understanding of what we can (or can’t) do with them. Now we do! 💡🚀 🧵 with Pablo Barcelo, @ismaililkanc, @mmbronstein, @michael_galkin, @JuanLReutter, @OrthMiguel

Really excited: 2/2 our papers got accepted to @iclr_conf! Thanks to all amazing co-authors and hope to see you in Singapore! 🇸🇬 If you're interested in generative models and RL agents for drug design check our papers in the thread 🧵

Amazing week - Understanding Virtual Nodes accepted to ICLR: openreview.net/forum?id=NmcO… - Hit my first 180 🎯 - Passed my PhD without corrections Thank you to everyone involved!

⭐️LOGML is back and we are looking for mentors!⭐️ Do you work in geometry or machine learning? Apply by February 16th! Mentors lead a group of 6 students to work on a project during the week and some groups end up publishing their work. More information at logml.ai/

Dear Network, Jesse Read and I would like to advertise the attached PhD position (start date: September 2025). We would like to work with you in the intersection of Graph Neural Networks, Reinforcement Learning, and Graph Signal Processing. We look forward to hearing from you!

The use of #AI to increase success of IVF by identifying the right follicle sizes (13-18 mm) to optimize timing of "trigger" shots nature.com/articles/s41467-0…

Might get AGI soon but guarantee it can't throw double 10 like Luke Littler

Hi!👋Emily Simons here, @FulbrightPrgrm Student Researcher with @HelmholtzMunich's AIDOS Lab. Happy to be sharing my first contribution to AIDOS in this 🧵. Say hiya to SCOTT, the perfect holiday (software) package🎁for the #curvature and #graph enthusiast in your life. 🧵1/n

Join us in NYC as a graduate student intern @PrescientDesign, @genentech this summer to work on fundamental research in 3D generative models, with applications to protein design! Apply directly, and please share with anyone who may be interested! Link below 👇👇

🌟 GLOW is coming back in December with amazing speakers: Emily Jin and @JoshSouthern13! 🗓️ Dec 18th @ 17 CET on Zoom, don't miss that! 🌐 Find more here: sites.google.com/view/graph-…

The year is 2100... there is a new SOTA on Zinc of 0.012 and Fast and Furious 40 is in cinemas

RT @mweber_PU: A postdoc position is available in my group at Harvard @hseas to perform research at the intersection of Geometry & Machine…

I am very happy to be selected as a top reviewer for #neurips2024 but still shocked by the lack of resources online on how to write one. Congrats also to old lab friends @gbouritsas @ffabffrasca who I also noticed on the list!

Great to make the journey out to Denver to present our recent work on genomic-driven ML interventions for #PCOS at #ASRM2024 @JoshSouthern13 @ChiomaIzzi @WaljitD @robertobaggio99 @ImperialMDR

Exploring “dark-matter” protein folds using deep learning @CellSystemsCP • Introducing Genesis VAE, a convolutional variational autoencoder that transforms low-resolution protein fold sketches into designable, stable 3D models. • Genesis VAE enables rapid exploration of “dark-matter” protein folds, creating novel protein architectures that have never been observed in nature. • Coupled with trRosetta, Genesis can design protein sequences for both known and novel folds, validated through experimental protease resistance assays. • One major innovation is Genesis’ ability to learn structural patterns from low-resolution sketches, refining them into native-like protein backbones. • The framework successfully designed five native folds and three novel “dark-matter” folds, demonstrating its capacity to generalize beyond natural protein spaces. • High-throughput experimental validation showed several of the designed proteins were stable, with folding behavior on par with natural proteins. • Genesis opens the door for the de novo design of proteins with entirely new functions, breaking through current limitations in protein design. @zanderharteveld @mmbronstein @befcorreia @JoshSouthern13 @CasperGoverde @m_deff @loukasa_tweet @trekkinglemon 💻Code: github.com/zanderharteveld/g… 📜Paper: cell.com/cell-systems/fullte…

🎓 And that's a wrap on the LOGML Summer School! 🥰 It was an incredible experience organizing it. A huge thank you to all our speakers for their insightful talks, to our mentors for making it an unforgettable experience for the students, and to all of you for attending! 👏

protein design is getting weird ... and increasingly functional ! These are very weird designs ! biorxiv.org/content/10.1101/… fun collaboration with @karla_mcastro @_JosephWatson @jueseph @UWproteindesign

We are hiring a postdoc at Imperial as a full-fledged affiliate of our new Erlangen Programme for Mathematical & Computational Foundations of AI Hub! Check it out, spread the word, and apply! 🤓👇 imperial.ac.uk/jobs/search-j…