Matthias Althoff

Out of the Shadows: Exploring a Latent Space for Neural Network Verification

Supporting High-Stakes Decision Making Through Interactive Preference Elicitation in the Latent Space

Provably Explaining Neural Additive Models

Training Verifiably Robust Agents Using Set-Based Reinforcement Learning

PyTupli: A Scalable Infrastructure for Collaborative Offline Reinforcement Learning Projects

Abstracting and Refining Provably Sufficient Explanations of Neural Network Predictions

Explaining, Fast and Slow: Abstraction and Refinement of Provable Explanations

Towards Formally Verifying LLMs: Taming the Nonlinearity of the Transformer