Floor Eijkelboom

@FEijkelboom

PhD student @UvA_Amsterdam | prev intern @cusp_ai | Exploring Flow-Based Foundation Models

Amsterdam

flooreijkelboom.github.io

Joined February 2022

308 Following

1,790 Followers

Replies Reposts Media

Pinned
Floor Eijkelboom
@FEijkelboom
Jul 9, 2025
Flow Matching (FM) is one of the hottest ideas in generative AI - and it’s everywhere at #ICML2025. But what is it? And why is it so elegant? 🤔 This thread is an animated, intuitive intro into (Variational) Flow Matching - no dense math required. Let's dive in! 🧵👇
GIF
109
Floor Eijkelboom
@FEijkelboom
Nov 4
Excited to share! 🎉 @Maria__Esteban shows how we can properly move beyond Gaussian kernels, improving both the theoretical foundations and empirical performance of drifting, with natural extensions to manifolds and discrete data! 🚀 Come talk to her at #NeurIPS2026 :D 🇦🇺
Maria Esteban
@Maria__Esteban
Nov 4
Excited to share that our paper, “Kernel-Gradient Drifting Models,” has been accepted to NeurIPS 2026! ❤️ 📄 Paper: arxiv.org/pdf/2605.10727… 💻 Code: github.com/jcarrascopollo…
GIF
Floor Eijkelboom
@FEijkelboom
Nov 3
Without a doubt one of the most inspiring researchers to work with ❤️ I could not recommend this opportunity enough
Nabil Iqbal
@nblqbl
Nov 2
I am hiring multiple PhD positions at AMLab at the University of Amsterdam to work on deep learning from a physically inspired point of view. come work with me! (link below) 1/n
1
Floor Eijkelboom
@FEijkelboom
Oct 21
The sheer ambition and scope of what's possible here are staggering. So incredibly inspiring. Huge congratulations to everyone involved!
Kieran Didi
@DidiKieran
Oct 21
Avengers assemble: 1 year BakerLab + NVIDIA GenAIR = 🔥 rfd4-proteina.org Presenting RFD4-Proteina, our latest protein design model, significantly better and faster than everything we compared against, both in silico and in the lab! 1/30
1
Floor Eijkelboom
@FEijkelboom
Oct 14
🚀 🐈
Oscar Davis
@osclsd
Oct 14
Continuous Diffusion LMs went from niche to contender this year, but the recipe is shaky: why self-conditioning? How to embed tokens? 🤨 Our new work takes your one-hot flow from 4% to 50% on TinyGSM without self-conditioning, and explores the design space of CDLMs. 🔥🚀 (1/6)

Floor Eijkelboom

Floor Eijkelboom’s posts