Conference and Journal Publications

• Explainable AI-based analysis of human pancreas sections identifies traits of type 2 diabetes
  Lukas Klein*, Sebastian Ziegler*, Yanni Morgenroth*, [...], Eyke Schoeniger, Michele Solimena, Felicia Gerst, Robert Wagner, Fabian Isensee, Klaus Maier-Hein, Paul Jäger
  Nature Communications · NeurIPS 2024 IAI Workshop · Covered by GEN · Download the DIADEM Dataset
• nnActive: A Framework for Evaluation of Active Learning in 3D Biomedical Segmentation
  Carsten T. Lüth*, Jeremias Traub*, Kim-Celine Kahl, Till J. Bungert, Lukas Klein, Lars Krämer, Paul F. Jaeger, Fabian Isensee, Klaus Maier-Hein
  Transactions on Machine Learning Research (TMLR)
• Finally Beating the Random Baseline: A Simple and Effective Active Learning Method for 3D Biomedical Segmentation
  Carsten T. Lüth*, Jeremias Traub*, Kim-Celine Kahl, Till J. Bungert, Lukas Klein, Lars Krämer, Paul F. Jaeger, Klaus Maier-Hein, Fabian Isensee
  Transactions on Machine Learning Research (TMLR)
• Navigating the Maze of Explainable AI: A Systematic Approach to Evaluating Methods and Metrics
  Lukas Klein, Carsten Lüth, Udo Schlegel, Till Bungert, Mennatallah El-Assady, Paul Jäger
  NeurIPS 2024
• Enhancing predictive imaging biomarker discovery through treatment effect analysis
  Shuhan Xiao, Lukas Klein, Paul Jäger, Jens Petersen, Klaus Maier-Hein
  WACV 2025
• Discovering Process Dynamic for Scalable Perovskite Solar Cell Manufacturing with Explainable AI
  Lukas Klein*, Sebastian Ziegler*, Felix Laufer*, Charlotte Debus, Markus Götz, Klaus Maier-Hein, Ulrich W. Paetzold, Fabian Isensee, Paul Jäger
  Advanced Materials · Covered by The Independent · NeurIPS 2023 XAI in Action Workshop (Top Paper Award)
• Navigating the Pitfalls of Active Learning Evaluation: A Systematic Framework for Meaningful Performance Assessment
  Carsten T. Lüth, Till J. Bungert, Lukas Klein, Paul Jäger
  NeurIPS 2023
• Semi-supervised automated Gleason Grading on WSI
  Lukas Klein*, Maximilian Fischer*, Lars Krämer*, Sebastian Ziegler*, Paul Jäger, Marco Nolden, Peter Neher, Fabian Isensee, Klaus Maier-Hein
  ECDP 2024 (Oral)
• A Call to Reflect on Evaluation Practices for Failure Detection in Image Classification
  Paul Jäger, Carsten T. Lüth, Lukas Klein, Till J. Bungert
  ICLR 2023 (Oral, Top 1% Paper)
• Improving Explainability of Disentangled Representations using Multipath-Attribution Mappings
  Lukas Klein, João Carvalho, Mennatallah El-Assady, Paolo Penna, Joachim M. Buhmann, Paul Jäger
  MIDL 2022

Preprints

• Why context matters in VQA & Reasoning: Semantic interventions for VLM input modalities
  Lukas Klein*, Kenza Amara*, Carsten Lüth, Antonio Rodríguez, Hendrik Strobelt, Mennatallah El-Assady, Paul Jäger
• Interactive Semantic Interventions for VLMs: Breaking VLMs with Human Ingenuity
  Lukas Klein*, Kenza Amara*, Carsten Lüth, Antonio Rodríguez, Hendrik Strobelt, Mennatallah El-Assady, Paul Jäger
  NeurIPS 2024 Safe Generative AI Workshop · Causality & Large Models Workshop
• From Correlation to Causation: Formalizing Interpretable Machine Learning as a Statistical Process
  Lukas Klein, Mennatallah El-Assady, Paul Jäger
  IJCAI 2022 Workshop on XAI