Manuel Pfeuffer

Omitted variable bias in deep learning can be effectively controlled, leading to unbiased predictions and improved model performance even in the presence of confounding variables.

Orthogonal projection reveals that protein language model embeddings capture critical biochemical features, with their removal leading to significant drops in predictive performance.

ICON decomposition reveals the true reliance of deep models on concepts, debunking misleading correlations that traditional methods often overlook.