Anna Penzkofer

Hi, my name is Anna. I’m a PhD student at University of Stuttgart at the Institute for visualization and interactive systems (VIS), affiliated with the collaborative artificial intelligence group. I’ve been doing research since my bachelor’s degree at Stuttgart in 2018, where I published my first paper at ICMI’21.

My personal research goal is understanding and developing a biologically plausible model of human visual processing, from bottom-up vision to spatial and abstract reasoning on natural images. I am particularly interested in integrating cognitive models with machine learning methods.

I regularly work with vision-language models for tasks such as object detection, or visual question answering. Additionally, I am interested in reinforcement learning agents and their strong link to human adaptive learning processes.

If you’re interested in a master/bachelor thesis with us, check out our projects page.

news

Aug 28, 2025	My paper SSPictR: A Biologically-plausible Image Representation has been accepted at the Artificial Intelligence and Cognition Workshop @ ECAI’25
Aug 13, 2025	The Overcooked Generalisation Challenge (OGC) has been accepted in TMLR
Jul 30, 2025	Excited to participate remotely and present my poster at CogSci’25.
May 01, 2025	Starting my internship at the Computational Neuroscience Research Group (CNRG) @ University of Waterloo, Canada.
Apr 05, 2025	My new paper A Cognitively Plausible Visual Working Memory Model has been accepted at CogSci’25

selected publications

2025

A Cognitively Plausible Visual Working Memory Model

Anna Penzkofer, Michael Furlong , Chris Eliasmith , and Andreas Bulling

In The 47th Annual Meeting of the Cognitive Science Society (CogSci) , 2025

Bib PDF Code Poster Website

@inproceedings{penzkofer25_cogsci,
  title = {A {Cognitively} {Plausible} {Visual} {Working} {Memory} {Model}},
  booktitle = {The 47th {Annual} {Meeting} of the {Cognitive} {Science} {Society} (CogSci)},
  author = {Penzkofer, Anna and Furlong, Michael and Eliasmith, Chris and Bulling, Andreas},
  year = {2025},
  pages = {1-6},
  google_scholar_id = {maZDTaKrznsC},
  doi = {https://escholarship.org/uc/item/3928d5s4}
}

The Overcooked Generalisation Challenge: Evaluating Cooperation with Novel Partners in Unknown Environments Using Unsupervised Environment Design

Constantin Ruhdorfer, Matteo Bortoletto, Anna Penzkofer, and Andreas Bulling

Transactions on Machine Learning Research (TMLR), 2025

PDF Code Website
SSPictR: A Biologically-plausible Image Representation

Anna Penzkofer, Karim Habashy , Chris Eliasmith , and Andreas Bulling

In ECAI Workshop on Artificial Intelligence and Cognition (AIC) , 2025

Website

2024

VSA4VQA: Scaling A Vector Symbolic Architecture To Visual Question Answering on Natural Images

Anna Penzkofer, Lei Shi, and Andreas Bulling

In Proc. 46th Annual Meeting of the Cognitive Science Society (CogSci) , 2024

Bib PDF Code Website

@inproceedings{penzkofer2024vsa4vqa,
  title = {VSA4VQA: Scaling A Vector Symbolic Architecture To Visual Question Answering on Natural Images},
  author = {Penzkofer, Anna and Shi, Lei and Bulling, Andreas},
  booktitle = {Proc. 46th Annual Meeting of the Cognitive Science Society (CogSci)},
  year = {2024},
  google_scholar_id = {TFP_iSt0sucC},
}

Int-HRL: towards intention-based hierarchical reinforcement learning

Anna Penzkofer, Simon Schaefer , Florian Strohm , Mihai Bâce , Stefan Leutenegger , and Andreas Bulling

Neural Computing and Applications, Dec 2024

Bib PDF Website

@article{penzkofer24_ncaa,
  title = {Int-{HRL}: towards intention-based hierarchical reinforcement learning},
  issn = {1433-3058},
  shorttitle = {Int-{HRL}},
  url = {https://doi.org/10.1007/s00521-024-10596-2},
  doi = {10.1007/s00521-024-10596-2},
  journal = {Neural Computing and Applications},
  author = {Penzkofer, Anna and Schaefer, Simon and Strohm, Florian and Bâce, Mihai and Leutenegger, Stefan and Bulling, Andreas},
  month = dec,
  year = {2024},
  volume = {36},
  google_scholar_id = {R3hNpaxXUhUC},
  keywords = {Eye Gaze, Artificial Intelligence, Hierarchical Reinforcement Learning, Intention Prediction, Montezuma’s Revenge, Sub-goal Extraction}
}

2021

Conan: A usable tool for multimodal conversation analysis

Anna Penzkofer, Philipp Müller , Felix Bühler , Sven Mayer, and Andreas Bulling

In Proceedings of the 2021 International Conference on Multimodal Interaction , Dec 2021

Bib PDF Code Website

@inproceedings{penzkofer2021conan,
  title = {Conan: A usable tool for multimodal conversation analysis},
  author = {Penzkofer, Anna and M{\"u}ller, Philipp and B{\"u}hler, Felix and Mayer, Sven and Bulling, Andreas},
  booktitle = {Proceedings of the 2021 International Conference on Multimodal Interaction},
  pages = {341--351},
  year = {2021},
  url = {https://doi.org/10.1145/3462244.3479886},
  google_scholar_id = {-f6ydRqryjwC},
}