Professional Summary
I am a PhD candidate in generative AI at the University of Amsterdam, supervised by Jan-Willem van de Meent and Max Welling. My research focuses on flow- and diffusion-based generative models. I develop simple, general, and efficient methods for learning flows over continuous, discrete, and geometric data (Variational Flow Matching), and extend these ideas to large-scale multimodal generative models, with an emphasis on foundation model integration, distillation, and controllable generation. I also work on inference-time control through sampling and reinforcement learning.
Education
PhD in Artificial Intelligence
University of Amsterdam
MSc in Artificial Intelligence (Cum Laude)
University of Amsterdam
BSc in Artificial Intelligence (Cum Laude)
Utrecht University
Interests
Preprint
Categorical Flow Maps
Daan Roos*, Oscar Davis*, Floor Eijkelboom*, Michael Bronstein, Max Welling, İsmail İlkan Ceylan, Luca Ambrogioni, Jan-Willem van de Meent
Discovering Lie Groups with Flow Matching
Jung Yeon Park, Yuxuan Chen, Floor Eijkelboom, Jan-Willem van de Meent, Lawson L.S. Wong, Robin Walters
Under review
Purrception: Variational Flow Matching for Vector-Quantized Image Generation
Răzvan-Andrei Matişan, Vincent Tao Hu, Grigory Bartosh, Björn Ommer, Cees GM Snoek, Max Welling, Jan-Willem van de Meent, Mohammad Mahdi Derakhshani*, Floor Eijkelboom*
ICLR 2026
Riemannian Variational Flow Matching for Material and Protein Design
Olga Zaghen, Floor Eijkelboom*, Alison Pouplin*, Cong Liu, Max Welling, Jan-Willem van de Meent, Erik J. Bekkers
ICLR 2026
Controlled Generation with Equivariant Variational Flow Matching
Floor Eijkelboom, Heiko Zimmermann, Sharvaree Vadgama, Erik J Bekkers, Max Welling, Christian A Naesseth*, Jan-Willem van de Meent*
ICML 2025
Exponential Family Variational Flow Matching for Tabular Data Generation
Andrés Guzmán-Cordero*, Floor Eijkelboom*, Jan-Willem van de Meent
ICML 2025
Towards Variational Flow Matching on General Geometries
Olga Zaghen, Floor Eijkelboom, Alison Pouplin, Erik J Bekkers
ICLR 2025 Workshop on Deep Generative Model in Machine Learning (Best Paper award)
Variational Flow Matching for Graph Generation
Floor Eijkelboom*, Grigory Bartosh*, Christian A. Naesseth, Max Welling, Jan-Willem van de Meent
NeurIPS 2024
Clifford Group Equivariant Simplicial Message Passing Networks
Cong Liu*, David Ruhe*, Floor Eijkelboom, Patrick Forré
ICLR 2024
E(n) Equivariant Message Passing Simplicial Networks
Floor Eijkelboom, Rob Hesselink, Erik J Bekkers
ICML 2024