14 citations · 15 across the 6 of their papers we have counts for
6 papers
Consistency Training while Mitigating Obfuscation via Rate Matching
Sohaib Imran, Prakhar Gupta, Jannes Elstner +1
Large language models are often influenced by extraneous input features, such as cues revealing a user's preferred answer. Consistency training reduces this influence by training m…
Evaluating and Understanding Scheming Propensity in LLM Agents
Mia Hopman, Jannes Elstner, Maria Avramidou +2
As frontier language models are increasingly deployed as autonomous agents pursuing complex, long-term objectives, there is increased risk of scheming: agents covertly pursuing mis…
The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence
Tom Wollschläger, Jannes Elstner, Simon Geisler +3
The safety alignment of large language models (LLMs) can be circumvented through adversarially crafted inputs, yet the mechanisms by which these attacks bypass safety barriers rema…
Optimizing CAD Models with Latent Space Manipulation
Jannes Elstner, Raoul G. C. Schönhof, Steffen Tauber +1
When it comes to the optimization of CAD models in the automation domain, neural networks currently play only a minor role. Optimizing abstract features such as automation capabili…
Simplified Learning of CAD Features Leveraging a Deep Residual Autoencoder
Raoul Schönhof, Jannes Elstner, Radu Manea +3
In the domain of computer vision, deep residual neural networks like EfficientNet have set new standards in terms of robustness and accuracy. One key problem underlying the trainin…
Feature Visualization within an Automated Design Assessment leveraging Explainable Artificial Intelligence Methods
Raoul Schönhof, Artem Werner, Jannes Elstner +3
Not only automation of manufacturing processes but also automation of automation procedures itself become increasingly relevant to automation research. In this context, automated c…