Luis Wiedmann

I am an ELLIS PhD student at EML Munich, part of the Technical University of Munich (TUM). My PhD advisors are Zeynep Akata and Cordelia Schmid.

I have an M.Sc. in Robotics, Cognition, Intelligence and a B.Sc. in Mechanical Engineering from TUM with stays abroad at the University of California San Diego and the École Polytechnique (Paris). I did various internships, e.g. at the German Aerospace Center (DLR) working on Robotics and at Hugging Face working on VLMs.

GitHub  /  Google Scholar  /  LinkedIn

profile photo

Research

I'm interested in foundation models, computer vision, machine learning, and robotics.

project image

FineVision: Open Data Is All You Need


Luis Wiedmann, Orr Zohar, Amir Mahla, Xiaohan Wang, Rui Li, Thibaud Frere, Leandro von Werra, Aritra Roy Gosthipaty, Andrés Marafioti
arxiv, 2025
arxiv / website /

project image

DCSEG: Decoupled 3D Open-Set Segmentation using Gaussian Splatting


Luis Wiedmann, Luca Wiehe, David Rozenberszki
CVPR Workshop on Open-World 3D Scene Understanding and Representations, 2025
paper / code /

project image

AI-based Robust and Failure-Tolerant Processes for In-Orbit Manufacturing of Modular Small Satellites


Maximilian Mühlbauer, Florian Leutert, Christian Plesker, Luis Wiedmann, Alessandro M. Giordano, João Silvério, Thomas Hulin, Freek Stulp, Jonas Voges, Robert Knobloch, Klaus Schilling, Benjamin Schleich, Alin Albu-Schäffer
International Astronautical Congress (IAC), 2024
paper /




Other Projects

These include unpublished research work and side projects.

project image

nanoVLM


Luis Wiedmann, Aritra Roy Gosthipaty, Andrés Marafioti
Repository
2025
website / code /

Simple repository for training/finetuning a small sized Vision-Language Model with a lightweight implementation in pure PyTorch.

Design and source code from Leonid Keselman's website