collaborators

6 papers

cs.CV2026

LD-ViCE: Latent Diffusion Model for Video Counterfactual Explanations

Payal Varshney, Adriano Lucieri, Christoph Balada +2

Video-based AI systems are increasingly adopted in safety-critical domains such as autonomous driving and healthcare. However, interpreting their decisions remains challenging due…

cs.LG2026

Unifying VXAI: A Systematic Review and Framework for the Evaluation of Explainable AI

David Dembinsky, Adriano Lucieri, Stanislav Frolov +3

Modern AI systems frequently rely on opaque black-box models, most notably Deep Neural Networks, whose performance stems from complex architectures with millions of learned paramet…

cs.CV2025

Towards Facilitated Fairness Assessment of AI-based Skin Lesion Classifiers Through GenAI-based Image Synthesis

Ko Watanabe, Stanislav Frolov, Aya Hassan +3

Recent advances in deep learning and on-device inference could transform routine screening for skin cancers. Along with the anticipated benefits of this technology, potential dange…

cs.CV2025

Discovering Concept Directions from Diffusion-based Counterfactuals via Latent Clustering

Payal Varshney, Adriano Lucieri, Christoph Balada +2

Concept-based explanations have emerged as an effective approach within Explainable Artificial Intelligence, enabling interpretable insights by aligning model decisions with human-…

cs.LG2025

The Directed Prediction Change - Efficient and Trustworthy Fidelity Assessment for Local Feature Attribution Methods

Kevin Iselborn, David Dembinsky, Adriano Lucieri +1

The utility of an explanation method critically depends on its fidelity to the underlying machine learning model. Especially in high-stakes medical settings, clinicians and regulat…

cs.LG2025

Generating Counterfactual Trajectories with Latent Diffusion Models for Concept Discovery

Payal Varshney, Adriano Lucieri, Christoph Balada +2

Trustworthiness is a major prerequisite for the safe application of opaque deep learning models in high-stakes domains like medicine. Understanding the decision-making process not…