
Floor Eijkelboom
@feijkelboom
PhD candidate @UvA_Amsterdam | Symmetry-Informed Generative Modeling
ID: 1497868823235604485
27-02-2022 09:39:07
116 Tweet
521 Followers
216 Following

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! 🌈




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 ♥️


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


🌊 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
