Profile

Jessie Bader is a PhD researcher in the Explainable Machine Learning group supervised by Zeynep Akata at the Technical University of Munich, starting in 2024. She completed her Master’s degree in Machine Learning at the University of Tübingen in 2023 and her Bachelor’s degree in Computer Engineering at Iowa State University in 2020.

Her primary research interests center on text-to-image generation, particularly enhancing T2I models’ prompt-following abilities and their capacity to produce unusual or out-of-distribution images.

Publications

"Stitch: Training-Free Position Control in Multimodal Diffusion Transformers"
Jessica Bader *, Mateusz Pach *, María Bravo, Serge Belongie, Zeynep Akata
Under review 2025

"SUB: Benchmarking CBM Generalization via Synthetic Attribute Substitutions"
Jessica Bader, Leander Girrbach, Stephan Alaniz, Zeynep Akata
International Conference on Computer Vision, ICCV 2025

"DataDream: Few-shot Guided Dataset Generation"
Jae Myung Kim *, Jessica Bader *, Stephan Alaniz, Cordelia Schmid, Zeynep Akata
European Conference on Computer Vision, ECCV 2024

Community Service

Reviewer for

• ICLR '26 & '25, NeurIPS '25 & '24, GCPR '24

Supervision

Theses:

• Does Feasibility Matter? Understanding the Impact of Feasibility on Synthetic Training Data, Yiwen Liu. Master Thesis June 2024, with Jae Myung Kim. Workshop Paper, Oral spotlight.
• Align-then-Unlearn: Embedding Alignment for LLM Unlearning, Philipp Spohn. Bachelor Thesis March 2025, with Leander Girrbach. Workshop Paper.
• Aligning Signal Leakage Matters for Synthetic Data Generation of Satellite Imagery, Ying Hua. Master Thesis June 2025, with Jae Myung Kim. Paper submission.