Your Photo

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:

Apart from research I am very passionate about writing and playing music (see below :)).

Selected Publications

Show me in Google Scholar

Publication Image

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]
Publication Image

Object-Centric Concept Bottlenecks

David Steinmann, Wolfgang Stammer, Antonia Wüst, Kristian Kersting

[NeurIPS 2025] [GitHub]
Publication Image

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]
Publication Image

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)]
Publication Image

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]
Publication Image

The Value of Symbolic Concepts for AI Explanations and Interactions (Dissertation)

Wolfgang Stammer

[Technical University Darmstadt]
Publication Image

Human-in-the-loop or AI-in-the-loop? Automate or Collaborate?

Sriraam Natarajan, Saurabh Mathur, Sahil Sidheekh, Wolfgang Stammer, Kristian Kersting

[AAAI 2025]
Publication Image

Neural Concept Binder

Wolfgang Stammer, Antonia Wüst, David Steinmann, Kristian Kersting

[NeurIPS 2024] [GitHub]
Publication Image

Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents

Quentin Delfosse, Sebastian Sztwiertnia, Mark Rothermel, Wolfgang Stammer, Kristian Kersting

[NeurIPS 2024] [GitHub]
Publication Image

Pix2code: Learning to compose neural visual concepts as programs

Antonia Wüst, Wolfgang Stammer, Quentin Delfosse, Devendra Singh Dhami, Kristian Kersting

[UAI 2024] (oral) [GitHub]
Publication Image

Learning by Self-Explaining

Wolfgang Stammer, Felix Friedrich, David Steinmann, Hikaru Shindo, Kristian Kersting

[TMLR 2024] [GitHub]
Publication Image

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]
Publication Image

Learning to Intervene on Concept Bottlenecks

David Steinmann, Wolfgang Stammer, Felix Friedrich, Kristian Kersting

[ICML 2024] [GitHub]
Publication Image

Leveraging explanations in interactive machine learning: An overview

Stefano Teso, Öznur Alkan, Wolfgang Stammer, Elizabeth Daly

[Frontiers in AI 2023]
Publication Image

A typology for exploring the mitigation of shortcut behaviour

Felix Friedrich, Wolfgang Stammer, Patrick Schramowski, Kristian Kersting

[Nature Machine Intelligence 2023] [GitHub]
Publication Image

Boosting Object Representation Learning via Motion and Object Continuity

Quentin Delfosse, Wolfgang Stammer, Thomas Rothenbacher, Dwarak Vittal, Kristian Kersting

[ECML-PKDD 2023] [GitHub]
Publication Image

Revision Transformers: Instructing Language Models to Change Their Values

Felix Friedrich, Wolfgang Stammer, Patrick Schramowski, Kristian Kersting

[ECAI 2023]
Publication Image

Interactive Disentanglement: Learning Concepts by Interacting with their Prototype Representations

Wolfgang Stammer, Marius Memmel, Patrick Schramowski, Kristian Kersting

[CVPR 2022] [GitHub]
Publication Image

Neural-Probabilistic Answer Set Programming

Arseny Skryagin, Wolfgang Stammer, Daniel Ochs, Devendra Singh Dhami, Kristian Kersting

[KR 2022] [GitHub]
Publication Image

Right for better reasons: Training differentiable models by constraining their influence functions

Xiaoting Shao, Arseny Skryagin, Wolfgang Stammer, Patrick Schramowski, Kristian Kersting

[AAAI 2021]
Publication Image

Right for the Right Concept: Revising Neuro-Symbolic Concepts by Interacting With Their Explanations

Wolfgang Stammer, Patrick Schramowski, Kristian Kersting

[CVPR 2021] [GitHub]
Publication Image

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

Spiderwebs & Foam

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.