#GeometricDeepLearning

Happy to share a major milestone: after years of development, we are officially launching Version 1.0 of the GeometricKernels library! To top it off, our accompanying paper has just been published in JMLR (MLOSS)! 🎉

Huge thanks to my co-authors Peter Mostowsky, @vdutor, @IAzangulov, Noémie Jaquier, @MHutchinson141, Aditya Ravuri, @LeonelRozo, @avt_im, all contributors and all users!

💻 GitHub: 📄 JMLR Paper: #MachineLearning #GeometricDeepLearning #GaussianProcesses #Kernels #Graphs #Manifolds #JMLR #OpenSource

👇Our probabilistic lifted inference book is out! 🙏 to everyone who contributed ! #Symmetries play an important role not only in physics but also in #AI. Strong connections to #geometricdeeplearning preview 👉 @mitpress url 👉

What is in common between CNNs, GNNs, LSTMs, Transformers, DeepSets, mesh CNNs? In a new post with @joanbruna @TacoCohen @PetarV_93 we show this zoo of neural nets can be seen through the lens of symmetry. #geometricdeeplearning is all you need!

"Foundation Models in Graph & Geometric Deep Learning" by @mmbronstein, @michael_galkin, @zhu_zhaocheng, @AndyJiananZhao, @haitao_mao_ #graphneuralnetworks #geometricdeeplearning

Just a quick reminder to check out my Ph.D. thesis if you are looking for a comprehensive introduction to Topological Deep learning through the lens of signal processing 🎼 ➡ #TopologicalDeepLearning #GeometricDeepLearning

Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges Bronstein et al.: #ArtificialIntelligence #DeepLearning #GeometricDeepLearning

"Masked Attention is All You Need for Graphs" by @davidbuterez , Jon Paul Janet, @DinoOglic, and @pl219_Cambridge Paper: #graphneuralnetwork #geometricdeeplearning

Do we need deep graph neural networks? In a new blog post @TDataScience I try to find out #geometricdeeplearning #graphneuralnetworks

Deep Learning and Geometric Deep Learning: an introduction for mathematicians and physicists R. Fioresi, F. Zanchetta : #ArtificialIntelligence #DeepLearning #GeometricDeepLearning

A piece at @CACMmag by Samuel Greengard on #geometricdeeplearning with quotes from @wellingmax @TacoCohen @joanbruna and your truly

Get ready to be amazed by the power of #MAGIK! Our new research in @NatMachIntell uncover hidden dynamics in microscopic motion. #GeometricDeepLearning at its finest! Work with @Jesuspicas @BMidtvedt @harshi_b7 @carlomanzo78

The paper authored by the stellar team at @fabula_ai on using #geometricdeeplearning for #FakeNews detection We show that news spread features can be learned to identify fakes with high accuracy

EXCITING time to be in #GeometricDeepLearning

Videos from the First Italian Summer School on #geometricdeeplearning are finally online! Dive into DL from the perspectives of differential geometry, topology, category theory, and physics with @pimdehaan @maurice_weiler @crisbodnar @Francesco_dgv

LOGML 2026 mentor applications are still open! Deadline extended to 22 March 2026(AoE). Mentor a small team at Imperial College London during 13–17 July'26. Travel/accommodation support available. 🔗 #LOGML #GeometricDeepLearning #GraphML #MachineLearning

Geometric deep learning for drug discovery is a really promising research direction to work on. I recently gave a tutorial on this topic. #GeometricDeepLearning #DrugDiscovery The slides are available here:

I can't wait to attend MICCAI conference @MICCAI2020 and present my paper "Topology-Aware Generative Adversarial Network for Joint Prediction of Multiple Brain Graphs from a Single Brain Graph". arxiv link: #geometricdeeplearning #brainconnectome

Ask Us Anything: Altair's physicsAI & Geometric Deep Learning🎙️ I am excited to dive into Geometric Deep Learning and how it transforms Finite Element Analysis (FEA) and Computational Fluid Dynamics (CFD) simulations with Eamon Whalen & Jonathan Ollar! Send us your questions👇

🔍 What to Expect: Join us as we speak with the experts behind Altair physicsAI and explore the cutting-edge applications of AI in simulation. We'll uncover how geometric deep learning enhances simulation accuracy, and speeding up iteration cycles.

💡 Tune in to learn how Altair is leveraging physicsAI to reduce prototyping costs, improve accuracy, and enable a new era of design innovation: #GeometricDeepLearning #Altair #PhysicsAI #Simulation #AI #FEA #CFD

📣 LOGML'26 Speaker Series 🎤 Soledad Villar @SoledadVillar5 (Johns Hopkins) Her research spans equivariant ML, GNNs, with applications to computational biology. 📍 Imperial College London 📅 13–17 July 2026 🔗 #LOGML #GraphML #GeometricDeepLearning

Our ⁦@CVPRConf⁩ oral on hand reconstruction in the wild using #geometricdeeplearning w Dominik Kulon, Stefanos Zafeiriou, Iasonas Kokkinos, Riza Alp Güler