🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

New work on Geometric Clifford Algebra Networks (GCANs). We propose geometric templates for modeling dynamical systems. A 🧵on geometric / Clifford algebras, and symmetry group transformations in neural networks. 📜arxiv.org/abs/2302.06594

🚨1 PhD position in high-dimensional #causal inference with @stephanievdpas Amsterdam UMC as part of her European Research Council (ERC) Starting Grant🚨 We will try to combine reliable causal discovery and effect estimation in high-dimensional settings. Deadline: April 2 werkenbij.amsterdamumc.org/en/vacatures/r…

I am deeply worried about the risks that come with building increasingly capable AI systems. It's a big part of why I went into ML seven years ago. Recently, I have been asked to talk about this more. My newest blog post on the AI alignment problem: tbbakker.nl/post/ai_alignm…

Yesterday, I presented our work "Simulation-based Inference with the Generalized Kullback-Leibler Divergence" which combines ratio and posterior estimation methods! It can even do it within the same (hybrid) model. openreview.net/forum?id=tPb1F…

Together with the amazing Johannes Brandstetter and Patrick Forré, we present Clifford Group Equivariant Neural Networks: a new E(n) steerable equivariant neural architecture that respects rotations, reflections, and more symmetries that operates on multivectors!

Proud to present Denoising Diffusion Models, where we connect the learned score of a diffusion model with force fields to do sampling and simulations🎉 Work done during a wonderful collaborative internship Microsoft Research JCIM & JCTC Journals pubs.acs.org/doi/10.1021/ac…, arxiv.org/abs/2302.00600

AMLab will be presenting 8 papers at NeurIPS 2023, including 2 oral presentations! Please see our blog for the full list. 📰: amlab.science.uva.nl/blog/2023/neur…

We have now released the denoising diffusion model codebase! It includes: 🏋️ Pretrained models ✅ Easy sampling and evaluation 💻 Full model and training scripts Check out our repository here: github.com/microsoft/two-…

At #ICLR2024 presenting our latent protein simulation poster with the amazing Marco Federici! Tuesday at 10:45, Halle B #64 Also happy to discuss proteins sampling, latent sim., and graph contrastive rep. learning, hit me up. iclr.cc/virtual/2024/p…

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

🔎 Are you interested in designing minimal representations to better simulate and understand complex dynamical systems? Join me and Bas Veeling 💪 at #ICLR2024 today at 10:45 in Halle B @ poster #64 to hear more about our Time-Lagged Information Bottleneck! 📊

📣 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.

We are hiring a postdoc! Come work with us in the booming AI ecosystem of beautiful Amsterdam on generative AI and/or uncertainty quantification 🤗 🎇vacatures.uva.nl/UvA/job/Postdo…