5 papers
What Drives Compositional Generalization? The Importance of Continuous Training Objectives in Visual Generative Models
Karim Farid, Rajat Sahay, Yumna Ali Alnaggar +4
Compositional generalization, the ability to generate novel combinations of known concepts, is a key ingredient for visual generative models. Yet, not all mechanisms that enable or…
Towards Understanding Subliminal Learning: When and How Hidden Biases Transfer
Simon Schrodi, Elias Kempf, Fazl Barez +1
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…
Simple LLM Baselines are Competitive for Model Diffing
Elias Kempf, Simon Schrodi, Bartosz CywiÅski +3
Standard LLM evaluations only test capabilities or dispositions that evaluators designed them for, missing unexpected differences such as behavioral shifts between model revisions…
When and How Does CLIP Enable Domain and Compositional Generalization?
Elias Kempf, Simon Schrodi, Max Argus +1
The remarkable generalization performance of contrastive vision-language models like CLIP is often attributed to the diversity of their training distributions. However, key questio…
Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language Models
Simon Schrodi, David T. Hoffmann, Max Argus +2
Contrastive vision-language models (VLMs), like CLIP, have gained popularity for their versatile applicability to various downstream tasks. Despite their successes in some tasks, l…