Bartlomiej Sobieski — accepted AI-conference papers

2026

Auditing Sybil: Explaining Deep Lung Cancer Risk Prediction Through Generative Interventional Attributions

Bartlomiej Sobieski, Jakub Grzywaczewski, Karol Dobiczek, Mateusz Wójcik, Tomasz Bartczak, Szatkowski Patryk +3

ICML 2026poster

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 effort is Sybil, a deep learning model capable of predicting future risk solely from computed tomography (CT) with high …

Cited by 0 Source ↗Scholar ↗

2026

Faithfulness Under the Distribution: A New Look at Attribution Evaluation

Zhiyu Zhu, Zhibo Jin, Jiayu Zhang, Bartlomiej Sobieski, Przemyslaw Biecek, Fang Chen +1

ICLR 2026poster

Evaluating the faithfulness of attribution methods remains an open challenge. Standard metrics such as Insertion and Deletion Scores rely on heuristic input perturbations (e.g., zeroing pixels), which often push samples out of the data distribution (OOD). This can distort model behavior and lead to…

Cited by 0 Source ↗Scholar ↗

2025

Rethinking Visual Counterfactual Explanations Through Region Constraint

Bartlomiej Sobieski, Jakub Grzywaczewski, Bartłomiej Sadlej, Matthew Tivnan, Przemyslaw Biecek

ICLR 2025poster

Visual counterfactual explanations (VCEs) have recently gained immense popularity as a tool for clarifying the decision-making process of image classifiers. This trend is largely motivated by what these explanations promise to deliver -- indicate semantically meaningful factors that change the class…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗

2025

System-Embedded Diffusion Bridge Models

Bartlomiej Sobieski, Matthew Tivnan, Yuang Wang, Siyeop yoon, Pengfei Jin, Dufan Wu +2

NeurIPS 2025poster

Solving inverse problems—recovering signals from incomplete or noisy measurements—is fundamental in science and engineering. Score-based generative models (SGMs) have recently emerged as a powerful framework for this task. Two main paradigms have formed: unsupervised approaches that adapt pretrained…

Cited by 0 Source ↗Scholar ↗