Lucas Stoffl
I’m a postdoctoral researcher working on multi-agentic AI for medicine - specifically at the intersection of computer vision, natural language processing, and clinical decision support.
My broader goal is to build AI systems that help us better understand and improve human (and animal) lives, by making machine learning not only powerful, but also transparent and trustworthy.
I earned my PhD from EPFL, where I focused on pose estimation, tracking, self-supervised learning, and hierarchical action segmentation. I’ve also spent time at NAVER Labs Europe working on 3D foundation models for real-time navigation.
Selected Publications
- VERITAS: A Multi-Agent Co-Scientist for Verifiable Image-Derived Hypothesis Testing
- A Multimodal 3D Foundation Model for Light Sheet Fluorescence Microscopy
- MUST3R: Multi-view Network for Stereo 3D Reconstruction
Research Interests
- Agentic AI for medicine
- Computer vision and clinical decision support
- Trustworthy and interpretable AI
- 3D reconstruction and foundation models
Google Scholar