🔥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

Singapore bound for #ICLR2025 next week! ✈️ Diving into foundation models for materials these days - would love to connect if you're in this space! Ping me for a chat ☕ Also excited to see the brilliant Takeru Miyato present our paper as an oral. Don't miss it! 🌈

Excited to be in Singapore next week for #ICLR2025! 🇸🇬 DM if you want to chat about geometric deep learning and/or generative models on manifolds, or just to enjoy some nice specialty coffee ☕️ I don't look like Barbie but my poster does 🪩😎

✨ Barbie loves geometry ✨

Be sure to pass by Olga's poster when you're at ICLR if you want to learn more why *Variational* Flow Matching works so well on manifolds! (or just to marvel at the poster design)

She’s not lost - she’s just in another coordinate chart. Check out our work on Variational Flow Matching on manifolds in Olga Zaghen 's oral ♥️

AMLab is going to present 2 papers + 5 workshop contributions at #ICLR25! See the thread for details 🔍

Towards Variational Flow Matching on General Geometries (Oral) by Olga Zaghen Floor Eijkelboom Alison Pouplin Erik Bekkers ➡️ openreview.net/forum?id=44OUH… ⚠️ Deep Generative Model in Machine Learning: Theory, Principle and Efficacy (DeLTa), Mon April 28th x.com/olgazaghen/sta…

🥇 3 Best Paper Awards for AMLab members! 1. Towards Variational Flow Matching on General Geometries by Olga Zaghen Floor Eijkelboom 2. Generative Uncertainty in Diffusion Models by Metod Jazbec 3. SDE Matching by Grigory Bartosh Congrats to everyone! 🔥

🦦 So glad our riemannian variational flow matching got recognition 🦦 Congrats Olga Zaghen Alison and Erik Bekkers - and the others ❤️ Paper 📄: arxiv.org/abs/2502.12981

AMLab is happy to have 7 papers accepted at #ICML2025! 🎉 See the thread below for the full list 📝 and meet us in Vancouver to discuss them! 🇨🇦 🧵0 / 7

🌊 Exponential Family Variational Flow Matching for Tabular Data Generation by Andrés Guzmán-Cordero*, Floor Eijkelboom*, Jan-Willem van de Meent 📜 soon! 🧵6 / 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

Two (out of two!) accepted papers to #ICML2025 from my lab! 1. SDE Matching: Scalable and Simulation-Free Training of Latent Stochastic Differential Equations 2. Controlled Generation with Equivariant Variational Flow Matching #GenAI #SDE #Bayes #ML #Diffusion #Flows #AI