most citedBeyond Overconfidence: Foundation Models Redefine Calibration in Deep Neural Networks

1 citations · 1 across the 4 of their papers we have counts for

collaborators

6 papers

cs.LG2025

Improving Perturbation-based Explanations by Understanding the Role of Uncertainty Calibration

Thomas Decker, Volker Tresp, Florian Buettner

Perturbation-based explanations are widely utilized to enhance the transparency of machine-learning models in practice. However, their reliability is often compromised by the unkno…

cs.AI2025

An autonomous agent for auditing and improving the reliability of clinical AI models

Lukas Kuhn, Florian Buettner

The deployment of AI models in clinical practice faces a critical challenge: models achieving expert-level performance on benchmarks can fail catastrophically when confronted with…

cs.LG2025

Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations

Thomas Decker, Volker Tresp, Florian Buettner

Perturbation-based explanations are widely utilized to enhance the transparency of modern machine-learning models. However, their reliability is often compromised by the unknown mo…

cs.LG20251 cited

Beyond Overconfidence: Foundation Models Redefine Calibration in Deep Neural Networks

Achim Hekler, Lukas Kuhn, Florian Buettner

Reliable uncertainty calibration is essential for safely deploying deep neural networks in high-stakes applications. Deep neural networks are known to exhibit systematic overconfid…

cs.LG2025

Incremental Uncertainty-aware Performance Monitoring with Active Labeling Intervention

Alexander Koebler, Thomas Decker, Ingo Thon +2

We study the problem of monitoring machine learning models under gradual distribution shifts, where circumstances change slowly over time, often leading to unnoticed yet significan…

cs.LG2025

MoRE-LLM: Mixture of Rule Experts Guided by a Large Language Model

Alexander Koebler, Ingo Thon, Florian Buettner

To ensure the trustworthiness and interpretability of AI systems, it is essential to align machine learning models with human domain knowledge. This can be a challenging and time-c…