Our paper has been accepted as an oral to NeurIPS Conference ! 😃🥳 📜Updated paper at arxiv.org/abs/2305.11141 💻Updated code (including Colab tutorial) at github.com/DavidRuhe/clif…

Our paper: “Clifford Group Equivariant Simplicial Message Passing Networks” has been accepted at #ICLR2024! With David Ruhe and Floor Eijkelboom, we explored the synergy of geometry and topology for better representations in geometric graphs! 📐 More details will come soon!

Happy to see more triangles dance in space ❤️ Amazing work by Cong Liu and David Ruhe accepted to #ICLR2024 - thanks for having me be a part of this! 🪿

Accepted at ICLR! github.com/ebekkers/ponita We derived pair-wise invariants that capture all geometric info needed to build simple + efficient SE(n) equivariant networks 🐴🔥 SOTA on 5 benchmarks (incl generation of molecules). Oh right, and ✨convolution is still all you need!

Looking for a simple+powerful *equivariant* graph neural network? Visit ICLR's poster sesh 2 tomorrow 7 May 16:30 CEST, Halle B #246. Imagine this poster but with amazing people around it; At least Sharvaree Vadgama ✈️ @ICML 2025, David W. Romero and me will be there :D, hope to see you too!

Are you interested in higher-order message passing on geometric graphs with steerable Clifford representations? Drop by our poster session2 at 16:30 7 May, Halle B #96! #ICLR2024

📣 This year at #ICML2024 we are hosting ✨ Gram Workshop ✨ Geometry-grounded representation learning and generative modeling. We welcome submissions in multiple tracks i.e. 📄 Proceedings, 🆕 extended abstract, 📝Blogpost/tutorial track as well as🏆 TDA challenge.

Clifford Group Equivariant Diffusion Models for 3D Molecular Generation by Cong Liu Sharvaree Vadgama David Ruhe Erik Bekkers Patrick Forré ➡️ arxiv.org/abs/2504.15773 ⚠️ Frontiers in Probabilistic Inference: Sampling Meets Learning

Introducing 𝗣𝗫𝗗𝗲𝘀𝗶𝗴𝗻 — fast, modular, accurate de novo binder design. 🧪 Wet-lab: 20–73% nanomolar hits on 5 targets; 2–6× vs AlphaProteo. 👀 Project: protenix.github.io/pxdesign/ ⌛️ 𝗦𝗲𝗿𝘃𝗲𝗿 𝗴𝗼𝗲𝘀 𝗹𝗶𝘃𝗲 𝗼𝗻𝗰𝗲 𝗮 𝗺𝗶𝗻𝗼𝗿 𝗹𝗼𝗴𝗶𝗻 𝗶𝘀𝘀𝘂𝗲 𝗶𝘀 𝗳𝗶𝘅𝗲𝗱.

Cool news: our extended Riemannian Gaussian VFM paper is out! 🔮 We define and study a variational objective for probability flows 🌀 on manifolds with closed-form geodesics. Floor Eijkelboom Alison Cong Liu Max Welling Jan-Willem van de Meent Erik Bekkers 🔥 📜 arxiv.org/abs/2502.12981