activity
20242026
collaborators

31 papers

cs.CV2026

Geometry-Aware Uncertainty Coresets for Robust Visual In-Context Learning in Histopathology

Franciskus Xaverius Erick, Johanna Paula Müller, Bernhard Kainz

Vision-language models (VLMs) can couple visual perception with open-ended clinical reasoning, making them attractive for computational histopathology. However, fine-tuning billion…

cs.CV2026

Wasserstein-Aligned Localisation for VLM-Based Distributional OOD Detection in Medical Imaging

Bernhard Kainz, Johanna P Mueller, Matthew Baugh +1

Zero-shot anomaly localisation via vision-language models (VLMs) offers a compelling approach for rare pathology detection, yet its performance is fundamentally limited by the abse…

cs.CV2026

Vision-Language Models as Zero-Annotation Oracles in Histopathology

Vishal Jain, Giorgio Buzzanca, Sarah Cechnicka +6

Foreground segmentation is the critical first step of every computational pathology pipeline, yet existing methods rely on hand-tuned heuristics or supervised models that overfit t…

cs.CV2026

Wasserstein Equilibrium Decoding for Reliable Medical Visual Question Answering

Luca Hagen, Johanna P. Müller, Weitong Zhang +2

Small vision-language models (2-8B) are well-suited for clinical deployment due to privacy constraints, limited connectivity, and low-latency requirements favouring on-device or on…

cs.CV2026

Stain-Aware Wavelet Regularization for Instant Adversarial Purification in Histopathology

Zhe Li, Bernhard Kainz

Deep learning has become prevalent in computational pathology pipelines that support tasks such as cancer screening and digital pathology analysis. However, the susceptibility of n…

cs.CV2026

The Learnability Gap in Medical Latent Diffusion

Mischa Dombrowski, Felix Nützel, Bernhard Kainz

Generative data augmentation with latent diffusion models is a promising strategy for addressing class imbalance in medical imaging, yet current approaches focus on perceptual fide…