Curriculum Vitae

Education

• Ph.D in Computer Science (summa cum laude), Karlsruhe Institute of Technology, 2023
• M.Sc. in Computer Science (study profile artificial intelligence), Karlsruhe Institute of Technology, 2020
• B.Sc. in Software Engineering, University of Stuttgart, 2016

Academic work experience

• Since Nov ‘23 Postdoc at Computer Vision for Human-Computer Interaction Lab, Karlsruhe Institute of Technology (KIT)
• Dec ‘20 – Jun ‘23 Multiple research stays at ZEISS Group in Jena / Oberkochen, Germany
• Apr ‘20 – Nov ‘23 Research associate, PhD student at Computer Vision for Human-Computer Interaction Lab at KIT working in a collaboration project with ZEISS Group. Topic: Semantic image segmentation with few and coarse annotations
• Feb ‘20 Master’s thesis at Computer Vision for Human-Computer Interaction Lab at KIT
  Supervision: M.Sc. A. Roitberg
  Examination: Prof. Dr.-Ing. Rainer Stiefelhagen
  Topic: Zero-shot recognition of composite activities in context of driver observation
• Aug ‘18 – Feb ‘20 Student research assistant at Computer Vision for Human-Computer Interaction Lab at KIT working on in-vehicle human activity recognition
  Supervision: M.Sc. A. Roitberg
  Topics: Action recognition, image-to-image translation
• Nov ‘16 Bachelor’s thesis at Fraunhofer Institute for Industrial Engineering IAO
  Supervision: M. Sc. Julien Ostermann, M. Sc. Kristian Lehmann, Dipl.-Inf. Sebastian Wagner
  Examination: Prof. Dr. Dr. h. c. Frank Leymann
  Topic: Services for data platforms – module to analyze and process urban time-based sensor data

Teaching experience

Theses: Master’s and Bachelor’s Thesis Projects

Lecture: Deep Learning for Computer Vision II: Advanced Topics

Lecture: Deep Learning for Computer Vision I: Basics

Seminar: Multimodal Large Language Models

Seminar: Computer Vision for Human-Computer Interaction

Practical Course: Computer Vision for Human-Computer Interaction

Additional experience

• Patents: Two published AI patents with ZEISS Group on efficient medical image segmentation (link, link).
• Grants: Successful joint grant application for Helmholtz Information & Data Science School for Health between Karlsruhe Institute of Technology and University Hospital Essen. Multiple granted applications for compute resources at high-performance computers.
• Mentoring: Serving as mentor in Computer Vision Hackathons
• Reviewing duties: Active reviewing at prime conferences in computer vision, including CVPR (2020 - present), ICCV (2021 - present), ECCV (2022 - present), in machine learning, NeurIPS (2025), in robotics, IROS (2021), ICRA (2024), as well as in medical computer vision, MICCAI (2025).
• Conference visits:
  • IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, Vancouver, Canada
  • European Conference on Computer Vision, 2022, Tel Aviv, Israel
  • IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, virtual
  • IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, virtual
  • IEEE Intelligent Vehicles Symposium, 2020, virtual
• Award: Participant in the CVPR 2023 Doctoral Consortium

Publications

Semantic Segmentation for Preoperative Planning in Transcatheter Aortic Valve Replacement

Is Visual in-Context Learning for Compositional Medical Tasks within Reach?

Conquering the Retina: Bringing Visual in-Context Learning to OCT

Good Enough: Is it Worth Improving your Label Quality?

CHAOS: Chart Analysis with Outlier Samples

Every Component Counts: Rethinking the Measure of Success for Medical Semantic Segmentation in Multi-Instance Segmentation Tasks

Foreign object segmentation in chest x-rays through anatomy-guided shape insertion

Muscles in Time: Learning to Understand Human Motion In-Depth by Simulating Muscle Activations

Anatomy-Guided Pathology Segmentation

Data Diet: Can Trimming PET/CT Datasets Enhance Lesion Segmentation?

SciEx: Benchmarking Large Language Models on Scientific Exams with Human Expert Grading and Automatic Grading

Behind every domain there is a shift: Adapting distortion-aware vision transformers for panoramic semantic segmentation

Style Transfer and Pseudo-Label Filtering Improve Transferability in Cell Organelle Segmentation Scenarios

360bev: Panoramic semantic mapping for indoor bird’s-eye view

Mirror U-Net: Marrying Multimodal Fission with Multi-Task Learning for Semantic Segmentation in Medical Imaging

Delivering arbitrary-modal semantic segmentation

Decoupled Semantic Prototypes Enable Learning From Diverse Annotation Types for Semi-Weakly Segmentation in Expert-Driven Domains

Accurate Fine-Grained Segmentation of Human Anatomy in Radiographs via Volumetric Pseudo-Labeling

Detailed Annotations of Chest X-Rays via CT Projection for Report Understanding

Graph-Constrained Contrastive Regularization for Semi-weakly Volumetric Segmentation

Breaking with fixed set pathology recognition through report-guided contrastive training

Reference-guided Pseudo-Label Generation for Medical Semantic Segmentation

Bending Reality: Distortion-Aware Transformers for Adapting to Panoramic Semantic Segmentation

Let’s Play for Action: Recognizing Activities of Daily Living by Learning from Life Simulation Video Games

From Driver Talk To Future Action: Vehicle Maneuver Prediction by Learning from Driving Exam Dialogs

Capturing Omni-Range Context for Omnidirectional Segmentation

Every annotation counts: Multi-label deep supervision for medical image segmentation

Deep Classification-driven Domain Adaptation for Cross-Modal Driver Behavior Recognition

CNN-based Driver Activity Understanding: Shedding Light on Deep Spatiotemporal Representations

Activity-Aware Attributes for Zero-Shot Driver Behavior Recognition

Drive&Act: A Multi-Modal Dataset for Fine-Grained Driver Behavior Recognition in Autonomous Vehicles

Talks

Poster presentation of ‘Is Visual in-Context Learning for Compositional Medical Tasks within Reach?’

October 19, 2025

Paper Presentation at ICCV, Honolulu, Hawai'i, United States

Three poster presentations at MICCAI Workshops

September 23, 2025

Paper Presentation at MICCAI, Daejeon, Republic of Korea

Talk on Artificial Intelligence at SRH Holding

March 18, 2024

Talk at SRH Campus Conventioncenter, Heidelberg, Germany

Two poster presentations and visiting the Doctoral Consortium at CVPR

June 21, 2023

Paper Presentation at CVPR, Vancouver, Canada

Poster presentation of ‘Graph-Constrained Contrastive Regularization for Semi-Weakly Volumetric Segmentation’

October 26, 2022

Paper Presentation at ECCV, Tel Aviv, Israel

Talk on Semi- and Weakly Supervised Segmentation at Web Computing GmbH

April 08, 2022

Invited Talk at virtual, Karlsruhe/Münster, Germany

Presentation on Scarce Resources in Segmentation at the Zeiss Innovation Hub@KIT

March 31, 2022

Research Presentation at virtual, Karlsruhe, Germany

Virtual presentation of ‘Every Annotation Counts: Multi-label Deep Supervision for Medical Image Segmentation’

June 23, 2021

Paper Presentation at CVPR, virtual

Virtual presentation of ‘Deep Classification-driven Domain Adaptation for Cross-Modal Driver Behavior Recognition’

November 10, 2020

Paper Presentation at Intelligent Vehicles Symposium, virtual

Virtual presentation of ‘Activity-aware attributes for zero-shot driver behavior recognition’

June 19, 2020

Paper Presentation at CVPR Workshop, virtual