🔥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

🔥 3/4 #ICLR2025 Grounding Continuous Representations in Geometry: Equivariant Neural Fields (ENF), for geometry-informed continuous signal representations. Learn more: openreview.net/forum?id=A4eCz… with D. Wessels, David M. Knigge Samuele Papa Riccardo Valperga Sharvaree Vadgama Erik Bekkers

Want to improve content safety and NSFW detection in CLIP? Hyperbolic geometry can make this possible. Check out our #CVPR2025 paper, Hyperbolic Safety-Aware Vision-Language Models. With: @TobiaP93332, Pascal Mettes, Lorenzo Baraldi, Rita Cucchiara #ELLISforEurope #Ellis_Amsterdam

🚀Exciting News! 🚀 Join us for the first UniReps x UCL_NeuroAI (inactive) Meetup at UCL SWC on Sept 8, 2025! 🎉 📍 Register now! 👉docs.google.com/forms/d/e/1FAI… 🔬 Exploring unifying representations in neural models—both artificial & biological. 🎙️ Keynote by Iris Groen (University

Praying for the sadgati of all the people killed in Bail Gaon (बैल गाँव, Palgham).

Grounding Continuous Representations in Geometry: Equivariant Neural Fields by David Wessels David M. Knigge Samuele Papa Riccardo Valperga Sharvaree Vadgama Efstratios Gavves Erik Bekkers ➡️ openreview.net/forum?id=A4eCz… ⚠️ Hall 3 + Hall 2B #558 x.com/Dafidofff/stat…

AdS-GNN - a Conformally Equivariant Graph Neural Network by Max Zhdanov Nabil Iqbal Erik Bekkers Patrick Forré ➡️ openreview.net/forum?id=8aTDq… ⚠️ Multiscale AI

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

Mark your calendars! The @WiMLWorkshop Social returns to ICLR 2026! 📅 🗓️ Friday, April 25th, 2025 ⏰ 12:30 PM - 2:00 PM 📍 Hall 1 Apex, Singapore Expo iclr.cc/virtual/2025/s… lu.ma/ftdnjnf9 #ICLR2025

📐 On the Importance of Embedding Norms in Self-Supervised Learning by Andrew Draganov, Sharvaree Vadgama, Sebastian Damrich, Jan Niklas Böhm, Lucas Maes, Dmitry Kobak, Erik Bekkers 📜 arxiv.org/abs/2502.09252 🧵3 / 7

🐳 Controlled Generation with Equivariant Variational Flow Matching by Floor Eijkelboom, Heiko Zimmermann 🦋 [email protected], Sharvaree Vadgama, Erik Bekkers, Max Welling, Christian A. Naesseth*, Jan-Willem van de Meent* 📜 soon! 🧵7 / 7

ICML Spotlight 🚨 Equivariance is too slow and expensive, especially when you need global context. It makes us wonder if it even worths the cost, especially in high-dimensional problems? We present Geometric Hyena Networks — a simple equivariant model orders of magnitude more

Great discussion, Chaitanya K. Joshi! We also explored this with extensive experiments in our recent paper: arxiv.org/abs/2501.01999. We find, among others, that equiv mods in a sense scale even better than non-equiv ones. Going more or less completely against the vibes from your post😅1/5

Here horizontal axis is train time: on an exactly equal computate budget, equiv models greatly outperform non-equiv ones. Scale all you want 😉(we tried!), the performance gap just could not be closed🤷‍♂️. Even on non-equivariant tasks equivariant models performed favorably. 2/5

Re: Chaitanya K. Joshi & equivariant models being 'orders of magnitude slower' – this perhaps needs some nuance 🧐. Our work shows slowness isn't unavoidable with equivariance. IMO, the main challenge isn't scalability, but the know-how for careful model design🛠️ 3/5

What is the probability of an image? What do the highest and lowest probability images look like? Do natural images lie on a low-dimensional manifold? In a new preprint with Zahra Kadkhodaie Eero Simoncelli, we develop a novel energy-based model in order to answer these questions: 🧵

Deeply saddened to hear this news. Sending prayers and strength to all affected. 🙏🙏

🌍 From earthquake prediction to robot navigation - what connects them? Eikonal equations! We developed E-NES: a neural network that leverages geometric symmetries to solve entire families of velocity fields through group transformations. Grid-free and scalable! 🧵👇

Thrilled to announce the first TAG-DS: TAG…We’re It! event Dec 1-2, 2025 in San Diego (Right before NeurIPS)! Please join us for this 2-day workshop featuring keynotes, submitted work, an associated proceedings and collaboration activities! More at tagds.com/events/tag-ds-…!

BREAKING: MIT just completed the first brain scan study of ChatGPT users & the results are terrifying. Turns out, AI isn't making us more productive. It's making us cognitively bankrupt. Here's what 4 months of data revealed: (hint: we've been measuring productivity all wrong)