Eric Tillmann Bill • Home

Hi, I’m Eric! 👋

I’m a master’s student at ETH Zurich, where I work on generative image models. I started at RWTH Aachen, where I wrote my bachelor’s thesis on graph neural networks with Christopher Morris. I then moved into generative modeling at ETH Zurich, studying magnitude-preservation methods for Diffusion Transformers with Cristian Perez Jensen (NeurIPS’26 OPT). More recently, I’ve focused on multi-subject text-to-image generation: first with JEDI (ICML’25 PUT), and then with FOCUS (CVPR’26 CVEU), which frames multi-subject fidelity as a stochastic optimal control problem and improves on JEDI, in collaboration with Enis Simsar and Thomas Hofmann.

Along the way, I completed industry internships in Stuttgart and Singapore. I recently finished my master’s thesis on vision-language models via discrete flow matching under the supervision of Enis Simsar and Alessio Tionioni, and graduated in May 2026.

I’m happy to announce that I’ll be joining Adobe Adobe Switzerland full time in August!

News

Mar 2026, FOCUS accepted as oral to CVPR'26 CVEU Workshop 🖼️
Sep 2025, Map-DiT accepted to NeurIPS'25 Workshop on Optimization for ML 🧶
Jul 2025, JEDI accepted to ICML’25 Workshop on Test-Time Adaptation 🔬

Selected Publications

FOCUS: Optimal Control for Multi-Entity World Modeling in Text-to-Image Generation

Eric Tillmann Bill, Enis Simsar, Thomas Hofmann

CVPRW 2026, Creative Video Editing and Understanding, Oral

Proceedings Preprint Code Webpage

BibTeX

@InProceedings{Bill_2026_CVPR,
    author    = {Bill, Eric Tillmann and Simsar, Enis and Hofmann, Thomas},
    title     = {FOCUS: Optimal Control for Multi-Entity World Modeling in Text-to-Image Generation},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
    month     = {June},
    year      = {2026}
}

Exploring Magnitude Preservation and Rotation Modulation in Diffusion Transformers

Eric Tillmann Bill, Cristian Perez Jensen, Sotiris Anagnostidis, Dimitri von Rütte

NeurIPS 2025, Optimization for Machine Learning Workshop

Preprint OpenReview Code

BibTeX

@inproceedings{bill2025exploring,
	title={Exploring Magnitude Preservation and Rotation Modulation in Diffusion Transformers},
	author={Anonymous},
	booktitle={OPT 2025: Optimization for Machine Learning},
	year={2025},
	url={https://openreview.net/forum?id=j5NB2cpxIQ}
	}

JEDI: The Force of Jensen-Shannon Divergence in Disentangling Diffusion Models

Eric Tillmann Bill, Enis Simsar, Thomas Hofmann

ICML 2025, Putting Updates to the Test Workshop

Preprint OpenReview Code Webpage

BibTeX

@inproceedings{
	 bill2025jedi,
	 title={{JEDI}: The Force of Jensen-Shannon Divergence in Disentangling Diffusion Models},
	 author={Eric Tillmann Bill and Enis Simsar and Thomas Hofmann},
	 booktitle={Second Workshop on Test-Time Adaptation: Putting Updates to the Test! at ICML 2025},
	 year={2025},
	 url={https://openreview.net/forum?id=HVQ3wL2jPI}
}