6 papers
LeVLJEPA: End-to-End Vision-Language Pretraining Without Negatives
Lukas Kuhn, Giuseppe Serra, Randall Balestriero +1
Vision-language pretraining remains dominated by contrastive objectives, whereas vision-only self-supervised learning has largely adopted non-contrastive methods. At the same time,…
LVLM-Aided Alignment of Task-Specific Vision Models
Alexander Koebler, Lukas Kuhn, Ingo Thon +1
In high-stakes domains, small task-specific vision models are crucial due to their low computational requirements and the availability of numerous methods to explain their results.…
From Entropy to Calibrated Uncertainty: Training Language Models to Reason About Uncertainty
Azza Jenane, Nassim Walha, Lukas Kuhn +1
Large Language Models (LLMs) that can express interpretable and calibrated uncertainty are crucial in high-stakes domains. While methods to compute uncertainty post-hoc exist, they…
Non-Contrastive Vision-Language Learning with Predictive Embedding Alignment
Lukas Kuhn, Giuseppe Serra, Florian Buettner
Vision-language models have transformed multimodal representation learning, yet dominant contrastive approaches like CLIP require large batch sizes, careful negative sampling, and…
An autonomous agent for auditing and improving the reliability of clinical AI models
Lukas Kuhn, Florian Buettner
The deployment of AI models in clinical practice faces a critical challenge: models achieving expert-level performance on benchmarks can fail catastrophically when confronted with…
Beyond Overconfidence: Foundation Models Redefine Calibration in Deep Neural Networks
Achim Hekler, Lukas Kuhn, Florian Buettner
Reliable uncertainty calibration is essential for safely deploying deep neural networks in high-stakes applications. Deep neural networks are known to exhibit systematic overconfid…