Research Group Björn Eskofier
Björn Eskofier
is Director of the Institute for Artificial Intelligence in Medicine at LMU University Hospital Munich.
His research focuses on the development and application of machine learning and data analytics methods in medicine, with a particular emphasis on sensor-based monitoring, motion analysis, and AI-assisted therapy decision-making. Before joining LMU in 2025, he was Chair of Machine Learning and Data Analytics and founding speaker of the Department of Artificial Intelligence in Biomedical Engineering (AIBE) at FAU Erlangen-Nürnberg. He has held visiting professorships at Harvard Medical School, the Massachusetts Institute of Technology, and Stanford University.
Team members @MCML
PostDocs
PhD Students
Jan Petermann
→ Group Björn Eskofier
Artificial Intelligence in Medicine
Maximilian Renz
→ Group Björn Eskofier
Artificial Intelligence in Medicine
Recent News @MCML
Publications @MCML
2027
You Only Flow Once: Calibrated and Real-Time Radar Pose Estimation with Multi-Hypothesis Normalizing Flows.
WACV 2027 - IEEE/CVF Winter Conference on Applications of Computer Vision. Buena Vista, FL, USA, Jan 04-08, 2027. To be published. Preprint available. arXiv
2026
Not All Nodes Are Created Equal: Homophily-Aware Stratification for Stable GNN Evaluation.
LoG 2026 - 5th Learning on Graphs Conference. Boston, MA, USA, Nov 20-22, 2026. To be published. Preprint available. arXiv GitHub
How LLMs Build Fictional Worlds: Setting and Narrative Space in AI-Generated Creative Storytelling.
EMNLP 2026 - Conference on Empirical Methods in Natural Language Processing. Budapest, Hungary, Oct 24-29, 2026. DOI GitHub
Cross-Corpus Depression Detection in Semi-Structured Clinical Interviews.
EMNLP 2026 - Conference on Empirical Methods in Natural Language Processing. Budapest, Hungary, Oct 24-29, 2026. DOI
How Human-Like Are Large Language Models? A Register-Aware Linguistic Evaluation Framework.
EMNLP 2026 - Conference on Empirical Methods in Natural Language Processing. Budapest, Hungary, Oct 24-29, 2026. Oral Presentation. DOI GitHub
Pose-Robust Facial Thermography through Per-Pixel Emissivity Correction.
BSN 2026 - 22nd Annual International Conference on Body Sensor Networks. Porto, Portugal, Oct 10-12, 2026. To be published. Preprint available. URL
Beyond the Chest: Comparative Radar-Based Heartbeat Detection Across Body Regions.
BSN 2026 - 22nd Annual International Conference on Body Sensor Networks. Porto, Portugal, Oct 10-12, 2026. To be published. Preprint available. URL
Beat-to-beat aortic valve opening detection from impedance cardiography using machine learning.
Frontiers in Digital Health 8. Oct. 2026. DOI
Enhancing IMU-Based Online Handwriting Recognition via Contrastive Learning with Zero Inference Overhead.
ICDAR 2026 - 20th International Conference on Document Analysis and Recognition. Vienna, Austria, Aug 30-Sep 04, 2026. To be published. Preprint available. arXiv
Do Depressive Facial Patterns Transfer Across Cultures and Contexts? Evidence from a German RCT and E-DAIC.
AI4Mental @KDD 2026 - International Workshop on AI for Cognitive and Mental Health Support at the 32nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Jeju Island, Republic of Korea, Aug 09-13, 2026. PDF GitHub
RadProPoser: Probabilistic Radar Tensor Human Pose Estimation That Knows Its Limits.
IJCNN 2026 - International Joint Conference on Neural Networks. Maastricht, Netherlands, Jun 21-26, 2026. DOI GitHub
Radar-based inspiratory-to-expiratory time ratio estimation: a validation study.
Scientific Reports 16.8256. Mar. 2026. DOI
Tokenization vs. Augmentation: A Systematic Study of Writer Variance in IMU-Based Online Handwriting Recognition.
Preprint (Mar. 2026). arXiv
ContraLog: Log File Anomaly Detection with Contrastive Learning and Masked Language Modeling.
Preprint (Feb. 2026). arXiv
2025
REECAP: Contrastive learning of retinal aging reveals genetic loci linking morphology to eye disease.
Preprint (Nov. 2025). DOI
2023
Federated electronic health records for the European Health Data Space.
The Lancet Digital Health 5.11. Nov. 2023. DOI
©all images: LMU | TUM
2025-10-06 - Last modified: 2026-10-23