2 citations · 7 across the 14 of their papers we have counts for
17 papers
AnyBottle: A Recipe to Only Keep the Concepts You Really Need
Wolfgang Stammer, Sukrut Rao, Hevra Petekkaya +2
Concept bottleneck models (CBMs) make predictions inspectable and intervenable by routing them through human-interpretable concepts, but originally required concept annotations. An…
Steering Fields: Adaptive Vector Fields for Safe Image Generation and Beyond
Simone Facchiano, Jan Eric Lenssen, Bernt Schiele +3
As state-of-the-art text-to-image flow models achieve near-photorealistic quality, controlling their outputs, e.g., suppressing harmful content while promoting benign alternatives,…
Playing ZendoWorld: Challenging AI Agents on Active Visual Concept Induction
Sophia Koehler, Antonia Wüst, Inga Ibs +5
A central challenge in building intelligent systems is enabling agents to jointly perceive complex inputs, form hypotheses about hidden patterns, and design informative experiments…
COCOLogic-V2: Identifying Logical Inconsistencies via Truly Hard-Negatives
David Steinmann, Antonia Wüst, Kristian Kersting +1
While interpretable models such as concept bottleneck models (CBMs) and program synthesis methods enable verification of model decisions, their evaluation is typically limited to s…
LLMs Gaming Verifiers: RLVR can Lead to Reward Hacking
Lukas Helff, Quentin Delfosse, David Steinmann +6
As reinforcement Learning with Verifiable Rewards (RLVR) has become the dominant paradigm for scaling reasoning capabilities in LLMs, a new failure mode emerges: LLMs gaming verifi…
Seeing Through Circuits: Faithful Mechanistic Interpretability for Vision Transformers
Nina Żukowska, Wolfgang Stammer, Bernt Schiele +1
Transparency of neural networks' internal reasoning is at the heart of interpretability research, adding to trust, safety, and understanding of these models. The field of mechanist…
Rethinking Concept Bottleneck Models: From Pitfalls to Solutions
Merve Tapli, Quentin Bouniot, Wolfgang Stammer +2
Concept Bottleneck Models (CBMs) ground predictions in human-understandable concepts but face fundamental limitations: the absence of a metric to pre-evaluate concept relevance, th…
Synthesizing Visual Concepts as Vision-Language Programs
Antonia Wüst, Wolfgang Stammer, Hikaru Shindo +3
Vision-Language models (VLMs) achieve strong performance on multimodal tasks but often fail at systematic visual reasoning tasks, leading to inconsistent or illogical outputs. Neur…
Neural Concept Verifier: Scaling Prover-Verifier Games via Concept Encodings
Berkant Turan, Suhrab Asadulla, David Steinmann +3
While Prover-Verifier Games (PVGs) offer a promising path toward verifiability in nonlinear classification models, they have not yet been applied to complex inputs such as high-dim…
SLR: Automated Synthesis for Scalable Logical Reasoning
Lukas Helff, Ahmad Omar, Felix Friedrich +7
We introduce SLR, an end-to-end framework for systematic evaluation and training of Large Language Models (LLMs) via Scalable Logical Reasoning. Given a user's task specification,…
Fodor and Pylyshyn's Legacy: Still No Human-like Systematic Compositionality in Neural Networks
Tim Woydt, Moritz Willig, Antonia Wüst +4
Strong meta-learning capabilities for systematic compositionality are emerging as an important skill for navigating the complex and changing tasks of today's world. However, in pre…
Object Centric Concept Bottlenecks
David Steinmann, Wolfgang Stammer, Antonia Wüst +1
Developing high-performing, yet interpretable models remains a critical challenge in modern AI. Concept-based models (CBMs) attempt to address this by extracting human-understandab…
Human-in-the-loop or AI-in-the-loop? Automate or Collaborate?
Sriraam Natarajan, Saurabh Mathur, Sahil Sidheekh +2
Human-in-the-loop (HIL) systems have emerged as a promising approach for combining the strengths of data-driven machine learning models with the contextual understanding of human e…
Neural Concept Binder
Wolfgang Stammer, Antonia Wüst, David Steinmann +1
The challenge in object-based visual reasoning lies in generating concept representations that are both descriptive and distinct. Achieving this in an unsupervised manner requires…
Pix2Code: Learning to Compose Neural Visual Concepts as Programs
Antonia Wüst, Wolfgang Stammer, Quentin Delfosse +2
The challenge in learning abstract concepts from images in an unsupervised fashion lies in the required integration of visual perception and generalizable relational reasoning. Mor…
Where is the Truth? The Risk of Getting Confounded in a Continual World
Florian Peter Busch, Roshni Kamath, Rupert Mitchell +3
A dataset is confounded if it is most easily solved via a spurious correlation, which fails to generalize to new data. In this work, we show that, in a continual learning setting w…
Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents
Quentin Delfosse, Sebastian Sztwiertnia, Mark Rothermel +2
Goal misalignment, reward sparsity and difficult credit assignment are only a few of the many issues that make it difficult for deep reinforcement learning (RL) agents to learn opt…