34 citations · 137 across the 37 of their papers we have counts for
11 papers · 1 filter
Do Sparse Autoencoders Learn Meaningful Concept Hierarchies?
Nils Grandien, David Steinmann, Felix Friedrich +1
Sparse autoencoders (SAEs) have become an important tool for unsupervised concept discovery in large models. To make the resulting feature spaces more interpretable and manageable,…
The Reward Was in Your Data All Along: Correcting Flow Matching with Discriminator-Guided RL
Nicolas Beltran-Velez, Felix Friedrich, Zhang Xiaofeng +4
Score- and flow-matching models often rely on preference-based reinforcement learning for two purposes: aligning with subjective preferences and, surprisingly, recovering propertie…
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…
ActivationReasoning: Logical Reasoning in Latent Activation Spaces
Lukas Helff, Ruben Härle, Wolfgang Stammer +6
Large language models (LLMs) excel at generating fluent text, but their internal reasoning remains opaque and difficult to control. Sparse autoencoders (SAEs) make hidden activatio…
Navigating Shortcuts, Spurious Correlations, and Confounders: From Origins via Detection to Mitigation
David Steinmann, Felix Divo, Maurice Kraus +4
Shortcuts, also described as Clever Hans behavior, spurious correlations, or confounders, present a significant challenge in machine learning and AI, critically affecting model gen…
Learning to Intervene on Concept Bottlenecks
David Steinmann, Wolfgang Stammer, Felix Friedrich +1
While deep learning models often lack interpretability, concept bottleneck models (CBMs) provide inherent explanations via their concept representations. Moreover, they allow users…
One Explanation Does Not Fit XIL
Felix Friedrich, David Steinmann, Kristian Kersting
Current machine learning models produce outstanding results in many areas but, at the same time, suffer from shortcut learning and spurious correlations. To address such flaws, the…
Class Attribute Inference Attacks: Inferring Sensitive Class Information by Diffusion-Based Attribute Manipulations
Lukas Struppek, Dominik Hintersdorf, Felix Friedrich +3
Neural network-based image classifiers are powerful tools for computer vision tasks, but they inadvertently reveal sensitive attribute information about their classes, raising conc…
Fair Diffusion: Instructing Text-to-Image Generation Models on Fairness
Felix Friedrich, Manuel Brack, Lukas Struppek +4
Generative AI models have recently achieved astonishing results in quality and are consequently employed in a fast-growing number of applications. However, since they are highly da…
Does CLIP Know My Face?
Dominik Hintersdorf, Lukas Struppek, Manuel Brack +3
With the rise of deep learning in various applications, privacy concerns around the protection of training data have become a critical area of research. Whereas prior studies have…
A Typology for Exploring the Mitigation of Shortcut Behavior
Felix Friedrich, Wolfgang Stammer, Patrick Schramowski +1
As machine learning models become increasingly larger, trained weakly supervised on large, possibly uncurated data sets, it becomes increasingly important to establish mechanisms f…