8 papers
COGENT: Counterfactual Gaussian Explanations for Volumetric Medical Images
Dorian Rząsa, Bartosz Zabdyr, Krzysztof Piekarz +7
Explainability is essential for deploying deep learning models in high-stakes medical applications. Existing explainability methods for volumetric imaging predominantly operate in…
Explaining BiomedCLIP with Weighted Banzhaf Interactions Supported by Tree-Gram Parsing
Jakub Rymarski, Adam RempaÅa, BartÅomiej Sobieski +1
Vision-Language Models (VLMs) are demonstrating significant capabilities in medical tasks like radiology analysis, yet providing faithful and interpretable explanations remains a k…
Riemannian Geometry for Pre-trained Language Model Embeddings
Szczepan Konior, Alexandre Quemy, PrzemysÅaw Klocek +2
Understanding the geometric structure of pre-trained language model embeddings matters for interpretability and safety. We ask whether sentence-level classification signal lives in…
Auditing Sybil: Explaining Deep Lung Cancer Risk Prediction Through Generative Interventional Attributions
Bartlomiej Sobieski, Jakub Grzywaczewski, Karol Dobiczek +6
Lung cancer remains the leading cause of cancer mortality, driving the development of automated screening tools to alleviate radiologist workload. Standing at the frontier of this…
Local Intrinsic Dimension Unveils Hallucinations in Diffusion Models
Bartlomiej Sobieski, Matthew Tivnan, Dawid PÅudowski +4
Diffusion models are prone to generating structural hallucinations - samples that match the statistical properties of the training data yet defy underlying structural rules, result…
System-Embedded Diffusion Bridge Models
Bartlomiej Sobieski, Matthew Tivnan, Yuang Wang +5
Solving inverse problems -- recovering signals from incomplete or noisy measurements -- is fundamental in science and engineering. Score-based generative models (SGMs) have recentl…