← Search

Elias Kempf

2 accepted papers

2026

Towards Understanding Subliminal Learning: When and How Hidden Biases Transfer

ICLR 2026poster

Language models can transfer hidden biases during distillation. For example, a teacher that "likes owls" can make its student "like owls" too, even when the training data consists only of lists of numbers. This surprising phenomenon is called *subliminal learning*. Subliminal learning can be expecte…

Cited by 0SourcecodeScholar
2025

When and How Does CLIP Enable Domain and Compositional Generalization?

ICML 2025spotlight

The remarkable generalization performance of contrastive vision-language models like CLIP is often attributed to the diversity of their training distributions. However, key questions remain unanswered: Can CLIP generalize to an entirely unseen domain when trained on a diverse mixture of domains (do…

Cited by 0SourcePDFScholar