Yanbo Wang

I am currently a Postdoctoral Researcher in the AMR Lab at TU Delft working on world models with generative modeling, supervised by Prof. Javier Alonso-Mora. I received my PhD from TU Delft in 2026, supervised by Prof. Justin Dauwels and Prof. Geert Leus. I received my master's degree from George Mason University in the U.S., honored with Outstanding Academic Achievement Award. I was a Best Student Paper Finalist at Asilomar 2020.

I was a Research Intern at Qualcomm AI Research, Amsterdam, June-October 2025.

Research

I am interested in generative models, world models, object-centric learning, and compositional modeling, with focus on generalization to novel settings beyond training data. The applications include visual content generation, scene understanding, physical reasoning, and robotic manipulation.

News

• 2026.05    I have successfully defended my PhD. Thesis: Compositional Generative Models.
• 2025.05    Paper "Compositional Scene Understanding through Inverse Generative Modeling" accepted by ICML 2025.
• 2025.01    I will be joining Qualcomm AI Research Amsterdam as a Research Scientist Intern in the summer of 2025.
• 2024.05    I give a talk on "Compositional Generative Models" at ASML, the Netherlands.
• 2024.04    Paper "Compositional Image Decomposition with Diffusion Models" accepted by ICML 2024.

Selected Publications (* stands for equal contribution)

Miscellanea

Compositional Inference for Generalizing beyond Training Distribution, SPS Seminar, TU Delft, 2025.
Composing EBMs and Diffusion Models, ASML, Eindhoven, 2024.
Object-Centric Image Generation with Hierarchical VAE, SPS Seminar, TU Delft, 2024

This webpage template is forked from source code.