21.07.2026
Timo Heiß Receives Best Student Paper Award at XAI 2026
Improving Feature Effect Estimation in Explainable AI
MCML Junior Member Timo Heiß received the Best Student Paper Award at the 4th World Conference on eXplainable Artificial Intelligence (XAI 2026) for the paper Analyzing Error Sources in Global Feature Effect Estimation. Co-authored with Coco Bögel, Bernd Bischl, and Giuseppe Casalicchio, the work was recognized for its outstanding contribution to explainable AI.
The paper provides a systematic analysis of the different sources of error in global feature effect estimation, a key technique for interpreting machine learning models. By decomposing these errors, the researchers address the practical question of whether feature effects should be estimated on training or holdout data, offering guidance that helps make explainable AI methods more reliable and robust.
Related
21.07.2026
The Learning Rate Does More Than Set the Pace
New ICML 2026 research by Gitta Kutyniok and her team shows how learning rates balance competing biases that shape neural network generalization.
20.07.2026
How Fair Does AI Seem in Job Interviews?
A new study by Enkelejda Kasneci examines how applicants perceive fairness in AI-driven job interviews.
20.07.2026
TUM Develops Intelligent 3D Twins of Crime Scenes
AI-powered 3D twins enable investigators to analyze virtual crime scenes through interactive object recognition and scene understanding.
