Ada Görgün

I am a PhD student in the Computer Vision and Machine Learning department at the Max Planck Institute for Informatics, under the supervision of Prof. Dr. Bernt Schiele and Dr. Jonas Fischer. Prior to this role, I served as a computer vision and machine learning researcher at the METU Center for Image Analysis (OGAM). I have completed my master’s degree in electrical and electronics engineering at the Middle East Technical University (METU) under the supervision of Prof. Dr. Aydın Alatan and Dr. Yeti Gürbüz, where my thesis delved into the interpretability of neural networks, their correlation with signal processing techniques, and the application of knowledge distillation. I also earned my bachelor’s degree in electrical and electronics engineering from the Middle East Technical University (METU).

My research focuses on representation learning, generative AI and explainability of deep networks in the context of computer vision.

Email / CV / Google Scholar / Github / LinkedIn

News

01/2026	One paper is accepted at ICLR 2026! Check it out: PCI.
06/2025	One paper is accepted at ICCV 2025! Check it out: VITAL.
07/2024	I started my PhD at the Max Planck Institute for Informatics!
01/2024	I joined the Max Planck Institute for Informatics as a research scientist!
09/2023	Our work on knowledge distillation is accepted at BMVC'23!

Publications

	Temporal Concept Dynamics in Diffusion Models via Prompt-Conditioned Interventions Ada Görgün, Fawaz Sammani, Nikos Deligiannis, Bernt Schiele, Jonas Fischer (equal contribution) ICLR, 2026* Paper \| Code \| Website
	VITAL: More Understandable Feature Visualization through Distribution Alignment and Relevant Information Flow Ada Görgün, Bernt Schiele, Jonas Fischer ICCV, 2025 Paper \| Code \| Website
	Knowledge Distillation Layer that Lets the Student Decide Ada Görgün, Yeti Ziya Gürbüz, A. Aydın Alatan (equal contribution) BMVC, 2023* Paper \| Code
	Feature Embedding by Template Matching as a ResNet Block Ada Görgün, Yeti Ziya Gürbüz, A. Aydın Alatan BMVC, 2022 Paper

Resources

I maintain a curated repository of papers and tools on generative model explainability, aiming to foster collaboration and understanding in the field. You can explore and contribute to it here: awesome-generative-explainability .

Academic Service

Reviewer: AAAI AIR-FM Workshop 2026, NeurIPS Mech Interp Workshop 2025, ICCV XAI Workshop 2025, CVPR XAI Workshop 2025, ICML MI Workshop 2024, ECCV XAI Workshop 2024, BMVC 2023.

Template from Jon Barron.