Wolfgang Stammer
Symbolic Concepts, Explanations and Interactions
Postdoctoral Researcher
CV & ML Group, Max Planck Institute for Informatics
Associated Member, "Neuroexplicit Models" Research Training Group
Email: wolfgang [dot] stammer [at] mpi-inf [dot] mpg [dot] de
My research revolves around the question: "How can we create performative AI models that allow users to understand and interact with their internal representations?"
I believe that for AI systems to explain their decisions effectively, they must communicate with human stakeholders using verifiable, concept-level statements. Importantly, this communication should not be one-sided; like human conversations, it should involve active discussion and interaction. Much of my recent work focuses on large-scale vision–language models, where I aim to achieve both comprehensible and reliable real-world performance.
As part of this, I'm also interested in how cognitive systems—whether biological or artificial—can learn abstract concepts without strong supervision. How can they bind information to a specific representation? What kind of representation is it?
I completed my PhD in Kristian Kerstings AI & ML lab at the TU Darmstadt.
Events I co-organised:
- "Semantic, Symbolic and Interpretable Machine Learning" ELLIS Workshop at Elise Wrap Up Conference 2024
- "Interactive Machine Learning" Workshop at AAAI 2022
- "Explanations in Interactive Machine Learning" Tutorial at AAAI 2022
- "Perspectives on Learning" Doctoral Symposium on Cognitive Science of German Society for Cognitive Science, 2022
Apart from research I am very passionate about writing and playing music (see below :)).
Selected Publications
Show me in Google Scholar
ActivationReasoning: Logical Reasoning in Latent Activation Spaces
Lukas Helff, Ruben Härle, Wolfgang Stammer, Felix Friedrich, Manuel Brack, Antonia Wüst, Hikaru Shindo, Patrick Schramowski, Kristian Kersting
[Arxiv]
Object-Centric Concept Bottlenecks
David Steinmann, Wolfgang Stammer, Antonia Wüst, Kristian Kersting
[NeurIPS 2025] [GitHub]
Neural Concept Verifier: Scaling Prover-Verifier Games via Concept Encodings
Berkant Turan, Suhrab Asadulla, David Steinmann, Wolfgang Stammer, Sebastian Pokutta
[Actionable Interpretability Workshop @ICML 2025]
Where is the Truth? The Risk of Getting Confounded in a Continual World
Florian Peter Busch, Roshni Kamath, Rupert Mitchell, Wolfgang Stammer, Kristian Kersting, Martin Mundt
[ICML 2025 (spotlight)]
Bongard in Wonderland: Visual Puzzles that Still Make AI Go Mad?
Antonia Wüst, Tim Tobiasch, Lukas Helff, Inga Ibs, Wolfgang Stammer, Devendra S. Dhami, Constantin A. Rothkopf, Kristian Kersting
[ICML 2025]
The Value of Symbolic Concepts for AI Explanations and Interactions (Dissertation)
Wolfgang Stammer
[Technical University Darmstadt]
Human-in-the-loop or AI-in-the-loop? Automate or Collaborate?
Sriraam Natarajan, Saurabh Mathur, Sahil Sidheekh, Wolfgang Stammer, Kristian Kersting
[AAAI 2025]
Neural Concept Binder
Wolfgang Stammer, Antonia Wüst, David Steinmann, Kristian Kersting
[NeurIPS 2024] [GitHub]
Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents
Quentin Delfosse, Sebastian Sztwiertnia, Mark Rothermel, Wolfgang Stammer, Kristian Kersting
[NeurIPS 2024] [GitHub]
Pix2code: Learning to compose neural visual concepts as programs
Antonia Wüst, Wolfgang Stammer, Quentin Delfosse, Devendra Singh Dhami, Kristian Kersting
[UAI 2024] (oral) [GitHub]
Learning by Self-Explaining
Wolfgang Stammer, Felix Friedrich, David Steinmann, Hikaru Shindo, Kristian Kersting
[TMLR 2024] [GitHub]
V-LoL: A Diagnostic Dataset for Visual Logical Learning
Lukas Helff, Wolfgang Stammer, Hikaru Shindo, Devendra Singh Dhami, Kristian Kersting
[DMLR 2024] [Project Page] [HuggingFace]
Learning to Intervene on Concept Bottlenecks
David Steinmann, Wolfgang Stammer, Felix Friedrich, Kristian Kersting
[ICML 2024] [GitHub]
Leveraging explanations in interactive machine learning: An overview
Stefano Teso, Öznur Alkan, Wolfgang Stammer, Elizabeth Daly
[Frontiers in AI 2023]
A typology for exploring the mitigation of shortcut behaviour
Felix Friedrich, Wolfgang Stammer, Patrick Schramowski, Kristian Kersting
[Nature Machine Intelligence 2023] [GitHub]
Boosting Object Representation Learning via Motion and Object Continuity
Quentin Delfosse, Wolfgang Stammer, Thomas Rothenbacher, Dwarak Vittal, Kristian Kersting
[ECML-PKDD 2023] [GitHub]
Revision Transformers: Instructing Language Models to Change Their Values
Felix Friedrich, Wolfgang Stammer, Patrick Schramowski, Kristian Kersting
[ECAI 2023]
Interactive Disentanglement: Learning Concepts by Interacting with their Prototype Representations
Wolfgang Stammer, Marius Memmel, Patrick Schramowski, Kristian Kersting
[CVPR 2022] [GitHub]
Right for better reasons: Training differentiable models by constraining their influence functions
Xiaoting Shao, Arseny Skryagin, Wolfgang Stammer, Patrick Schramowski, Kristian Kersting
[AAAI 2021]
Right for the Right Concept: Revising Neuro-Symbolic Concepts by Interacting With Their Explanations
Wolfgang Stammer, Patrick Schramowski, Kristian Kersting
[CVPR 2021] [GitHub]
Making deep neural networks right for the right scientific reasons by interacting with their explanations
Patrick Schramowski, Wolfgang Stammer, Stefano Teso, Anna Brugger, Franziska Herbert, Xiaoting Shao, Hans-Georg Luigs, Anne-Katrin Mahlein, Kristian Kersting
[Nature Machine Intelligence 2020] [GitHub]Music
In addition to my work in AI and machine learning, I am also passionate about music. I play and write lyrics and music in the semi-professional band Spiderwebs & Foam. Our band blends various genres, from Rock, Jazz, Electronic, Folk. We have performed at several venues and continue to create and share our music with the world.